The Internet of Things (IoT) is revolutionizing manufacturing, serving as a digital makeover tool that collects essential production data. The transition to IoT generates vast data volumes, requiring robust storage and system architecture. Cloud computing steps in here, accommodating these needs with ease. In this setup, a network of sensors across a manufacturing unit captures valuable data, which is transmitted to the cloud. Specialized software then transforms this data into operational performance insights. This digital integration can elevate a manufacturing business, coalescing with existing systems to deliver remarkable results. As the IoT gains popularity, digital manufacturing is poised to soar. However, security has become a paramount concern, especially for retrofitted IoT devices operating with limited human intervention. Researchers have proposed various solutions for IoT security issues. In this study, we conduct a literature review (LR) to identify the security requirements for retrofitting IoT devices in manufacturing. Our goal is to provide a straightforward roadmap for industry stakeholders, highlighting the most suitable security solutions for their retrofitted IoT systems. Our review focuses on scientific papers from the past four years, specifically addressing the security and simplicity of retrofitted IoT architecture in manufacturing. The overarching aim is to define the security needs for IoT retrofitted devices in manufacturing, facilitating the smooth integration of process data into cloud platforms.

In recent years, the demand for efficient and accurate measurement techniques has surged across various industries, driving the development of non-invasive methods that leverage computer vision technology. This paper explores the principles and applications of non-invasive measurement techniques utilizing computer vision, emphasizing their ability to deliver precise measurements without the need for physical contact or specialized sensors. We delve into the underlying algorithms, including image processing, machine learning, and deep learning methods, that enable the extraction of dimensional data from visual inputs. Case studies across diverse fields such as manufacturing, healthcare, and logistics illustrate the effectiveness of these techniques in enhancing operational efficiency and reducing measurement errors. Furthermore, we discuss the challenges and limitations of implementing computer vision-based measurement systems, including the need for robust algorithms capable of functioning in varied environmental conditions. By highlighting the transformative potential of non-invasive measurement techniques, this paper aims to provide insights into future developments in computer vision and its role in advancing measurement practices across multiple sectors.

Graph neural networks (GNNs) have been effectively implemented in a variety of real-world applications, while their underlying work mechanisms remain a mystery. To unveil this mystery and advocate trustworthy decision-making, many GNN explainers have been proposed. However, existing explainers often face significant challenges, such as: 1) explanations being tied to specific instances; 2) limited generalizability to unseen graphs; 3) potential generation of invalid graph structures; and 4) restrictions to particular tasks (e.g., node classification, graph classification). To address these challenges, we propose a novel explainer, GAN-GNNExplainer, which employs a generator to produce explanations and a discriminator to oversee the generation process, enhancing the reliability of the outputs. Despite its advantages, GAN-GNNExplainer still struggles with generating faithful explanations and underperforms on real-world datasets. To overcome these shortcomings, we introduce ACGAN-GNNExplainer, an improved approach that improves upon GAN-GNNExplainer by using a more robust discriminator that consistently monitors the generation process, thereby producing explanations that are both reliable and faithful. Extensive experiments on both synthetic and real-world graph datasets demonstrate the superiority of our proposed methods over existing GNN explainers.

In the rapidly evolving field of natural language processing (NLP), the processing of the Chinese language, with its unique complexities, presents significant challenges, especially in the context of Large Language Models (LLMs) like LLaMA2. These challenges are further exacerbated by the presence of non-standardized text prevalent across digital Chinese content. To address these challenges, this paper proposes a novel hybrid approach that seamlessly integrates deep contextual embeddings with Convolutional Neural Networks (CNNs) to enhance the processing of standardized Chinese text. Our approach involves a multi-stage process wherein deep contextual embeddings are first utilized to capture the nuanced semantic relationships within text. Following this, CNNs are employed to identify and exploit structural and syntactic patterns, facilitating a comprehensive understanding of the text. This hybrid model significantly improves LLaMA2’s efficiency and accuracy across various Chinese text processing tasks by ensuring that both semantic depth and structural nuances are accurately captured. The effectiveness of our model is demonstrated through rigorous testing across several benchmarks, showcasing its superiority in processing Chinese text with enhanced accuracy and speed. This research not only contributes to the advancement of text processing capabilities of LLMs but also opens new avenues for their application in tasks such as automated translation and sentiment analysis.

Predicting patient readmission is an important task for healthcare risk management, as it can help prevent adverse events, reduce costs, and improve patient outcomes. In this paper, we compare various conventional machine learning models on a multimodal dataset of electronic discharge records from an Irish acute hospital. We \khoi{evaluate the effectiveness of several widely-used Machine Learning models} that leverage patient demographics, historical hospitalization records, and clinical diagnoses codes, to forecast future clinical risks. \khoi{Our work focuses on addressing two key challenges in the medical fields: data imbalance and the variety of data types in order to boost the performance of Machine Learning algorithms. Through extensive benchmarking and the application of a variety of feature engineering techniques, we successfully improved the Area Under the Curve (AUROC) score from 0.628 to 0.7 across our models on the test dataset}. Furthermore, we also employ \khoiz{Shapley Additive Explanations (SHAP)} value visualization to\reviewertwo{v In the abstract line 6 SHAP is mentioned in initials should be written in details: SHAP (SHapley Additive exPlanations).} interpret the model predictions and identify both the key data features and disease codes associated to readmission risks, identifying a specific set of diagnoses codes that are significant predictors of readmission within 30 days. Our study demonstrates how we effectively utilize the routinely collected hospital data to forecast patient readmission through the use of conventional machine learning while applying explainable AI techniques to explore the correlation between data features and patient readmission rate.

Accurate sentiment prediction on digital platforms while ensuring user anonymity and privacy presents substantial challenges. Predominantly, existing methodologies are centralized, impeding the achievement of both robust analysis with strong privacy protections and model accuracy. This paper investigates federated learning (FL), augmented with a novel Data Obfuscation (DO) technique and Bidirectional Encoder Representations from Transformers (BERT), to develop a new framework addressing this issue. The proposed framework enables continuous supervision of mental states by autonomously learning from aggregated global data on federated servers. The use of the emotion data set for prediction demonstrated a considerable improvement in accuracy (82.74%), precision (83.30%) and recall (82.74%) and F-1 score (82.80%) over baseline results of precision (16.73%), precision (23.29%), recall (16.73%) and F-1 score (18.18%). In addition, two privacy attack scenarios were executed to evaluate system resilience. Membership Inference Attacks, which determine whether a specific data point was part of the training set, and Linkage Attacks, which attempt to associate data samples with a specific client. However, the system preserves its privacy guarantees despite these adversities. The proposed approach skillfully balances privacy and accuracy, establishing a foundation for scalable and secure mental health support systems. This research exemplifies a model for leveraging FL and Data Obfuscation to enhance both the privacy and effectiveness of predictive analytics in critical applications, offering transformative advantages for digital platforms by enabling deep emotional analysis of users while safeguarding their privacy.

As UAVs are increasingly employed across various industries, the demand for robust and accurate detection has become crucial. LiDAR has developed as a vital sensor technology because to its ability to offer rich 3D spatial information, particularly in applications such as security and airspace monitoring. This review systematically explores recent innovations in LiDAR-based drone detection, deeply focusing on the principle and components of LiDAR sensor, its classifications based on different parameters and scanning mechanisms, as well as the approaches for processing LiDAR data. The review briefly compares several deep learning approaches, including point-based, voxel-based, and hybrid models, that have improved drone detection, tracking, and classification. We also explore the integration of multi-modal sensor fusion, which combines LiDAR data with other complimentary modalities to improve UAV detection and tracking in complex environments such as GNSS-denied zones.

The expanding Arabic user base presents a unique opportunity for researchers to tap into vast online Arabic resources. However, the lack of reliable Arabic word embedding models and limited availability of Arabic corpora pose significant challenges. This paper aims to address these gaps by conducting an experiment to train word embedding models with Arabic corpora and examine the influence of varying hyperparameter values on different NLP tasks. To gather data for training the models, we collected information from three distinct sources: Wikipedia, newspapers, and 31 Arabic books. Each corpus’s specific impact on the outcomes was analyzed. The experiment involved assessing the models across diverse NLP tasks, including sentiment analysis, similarity tests, and analogy tests. The findings revealed that both the corpus size and hyperparameter values had distinct effects on each test. In the Analogy test, employing a larger vocabulary size positively influenced the outcomes, with Fasttext models using skip-gram approaches performing well in solving Analogy Test questions. For sentiment analysis, we discovered that vocabulary size played a crucial role. In the similarity score test, Fasttext models achieved the highest scores, with lower window sizes and smaller vector sizes leading to better results. Overall, our models performed well, achieving a score of 99%, 90% accuracies for sentiment analysis and Analogy Test, respectively. Moreover, they achieved a similarity score of 8 out of 10. Our findings indicate that our models can serve as a valuable resource for Arabic NLP researchers, equipping them with a robust tool for handling Arabic text.

In today’s fast-paced, modern world, parents often face significant challenges in balancing their professional responsibilities with the demands of child monitoring and nurturing. Our project addresses these challenges by developing an IoT-based Smart Cradle Monitoring System, designed to assist parents in ensuring their child's well-being while they are working. The smart cradle features an automatic swinging mechanism that activates upon detecting the sound of a baby crying, soothing the baby promptly without requiring immediate parental intervention. Additionally, a web camera provides continuous video surveillance, allowing parents to monitor their child remotely in real-time through dedicated alerts. The system leverages IoT technology to connect various components, including an Arduino microcontroller, Raspberry Pi high-sensitivity sound sensors, and a motorized swinging mechanism. This integration ensures seamless operation and remote access, offering peace of mind to working parents. By upgrading traditional cradles with modern electronics, our project provides a reliable and efficient solution that enhances child care, ensuring both the child’s well-being and the parent’s peace of mind. This smart cradle is designed to alleviate the challenges faced by working parents, offering superior results compared to conventional cradles, and helping parents focus on their work while being reassured of their child's safety and comfort.

The article addresses the issues of scalability and security in blockchain networks, with a focus on sharding algorithms and decentralized data storage. Key challenges include the low throughput and high transaction latency in public networks such as Bitcoin and Ethereum. Sharding is examined as a method to enhance performance through data distribution, but it raises concerns regarding node management and reliability. Sharding schemes, such as Elastico, OmniLedger, Pyramid, RepChain, and SSchain, are analyzed, each presenting its own advantages and drawbacks. Alternative architectures like Directed Acyclic Graphs (DAG) demonstrate potential for improved scalability but require further refinement to ensure decentralization and security. Protocols such as Brokerchain, Meepo, AHL, Benzene, and CycLedger offer unique approaches to addressing performance and transaction consistency issues. The article emphasizes the need for a comprehensive approach, including dynamic sharding, multi-level consensus, and inter-shard coordination. Additionally, a conceptual model is proposed that incorporates sharding of transactions, states, and networks, which enables greater scalability and efficiency.

Credit scoring is a cornerstone of financial risk management, enabling financial institutions to assess the likelihood of loan default. However, widely recognized contemporary credit risk metrics, like FICO or Vantage scores, remain proprietary and inaccessible to the public. This study aims to devise an alternative credit scoring metric that mirrors the FICO score, using an extensive dataset from Lending Club. The challenge lies in the limited insights available on both the precise analytical formula and the comprehensive suite of credit-specific attributes integral to the FICO score's calculation. Our proposed metric leverages basic information provided by potential borrowers, eliminating the need for extensive historical credit data. We aim to articulate this credit risk metric in a closed analytical form with variable complexity. To achieve this, we employ a symbolic regression method anchored in Genetic Programming (GP). Here, Occam's razor principle guides evolutionary bias towards simpler, more interpretable models. To ascertain our method's efficacy, we juxtapose the approximation capabilities of GP-based symbolic regression with established machine learning regression models, such as Gaussian Support Vector Machines (GSVMs), Multi-Layer Perceptrons (MLPs), Regression Trees and Radial Basis Function Networks (RBFNs). Our experiments indicate that GP-based symbolic regression offers comparable accuracy with these benchmark methodologies. Moreover, the resultant analytical model offers invaluable insights into credit risk evaluation mechanisms, enabling stakeholders to make informed credit risk assessments. This study contributes to the growing demand for transparent machine learning models by demonstrating the value of interpretable, data-driven credit scoring models.

In today’s world of software development technologies, serverless cloud computing with microservices is a big deal. Microservices gives modularity, agility and scalability, while serverless allows to code without having to maintain any internal hardware infrastructure, so processes are streamlined and costs are reduced by 60% compared to traditional server based systems. In this paper we looked at the challenges of microservices and serverless architecture and how to address them. We analyzed existing architectures and proposed a conceptual framework that will give you a complete solution for building scalable and efficient cloud native applications that reduces costs by 30-50%, improves resource utilization by 15-20%. Cold start latency, a common issue in serverless computing is reduced by 25% using standardized optimization techniques. This paper also compares server based and serverless technologies on scalability, resource efficiency and cost. These findings will give you a serverless approach to cloud software development and supports the trend of architectural adoption so you can have more dynamic and efficient systems.

Educational institutions are increasingly utilizing chatbots to enhance communication and streamline administrative tasks, including answering frequently asked questions (FAQs). Serving as the first review about employing chatbots in educational administration, this systematic review explores the potential of chatbots to improve educational administration. While research on chatbots in education has primarily focused on their role in learning, their application for administrative tasks remains underexplored. This gap necessitates a systematic investigation of how chatbots are utilized and implemented to streamline administrative processes. Following the PRISMA framework, this review analyzes 54 studies to address five key areas: functionalities performed, data employed, technologies used, evaluation methods, and future development challenges. The review reveals a critical need for a comprehensive framework for developing administrative chatbots that are specifically tailored to educational institutions. This review underscores the importance of such a framework in addressing identified gaps in the literature and in incorporating generative AI into educational administrative tasks management. The review also highlights a noticeable lack of research in this domain, including the potential of generative AI, like ChatGPT, to improve administrative efficiency. Furthermore, the study discusses the potential impact, practical applications of administrative chatbots in education and future research directions.

This paper investigates the application of Graph Neural Networks (GNNs) in solving the facility location decision problem. By adapting the learning objectives and structure of GNNs, this research bridges the gap between traditional optimization approaches and modern machine learning techniques. The proposed method demonstrates improved decision-making capabilities, providing promising results for facility location optimization. Additionally, potential future research directions are outlined, highlighting areas where GNNs can further enhance decision-making processes in complex supply chain networks. Hybrid GNN and Mixed Integer Programming solutions have been proposed.

The ever-growing student population and limited administrative resources strain traditional communication channels within educational institutions. Chatbot technology offers a promising solution, but current limitations can impede effective student-administration interaction. This paper proposes a hybrid chatbot model to enhance reliability in educational administration by addressing the limitations of generative models like ChatGPT. We investigate three individual chatbot approaches (rule-based, retrieval-based, and generative-based) to handle educational inquiries. An evaluation assessed their strengths, weaknesses, and user experience. Based on these findings, a hybrid model with an intelligent classifier for query routing was developed. This model leverages each approach's strengths and addresses uncertainty in the generative model to achieve increased accuracy and reliability. Our results demonstrate an accuracy improvement compared to individual models. This work contributes to developing adaptable chatbot systems capable of addressing a wider range of user inquiries, which is particularly beneficial in resource-constrained educational settings. Additionally, the proposed model demonstrates competitive performance when benchmarked against existing state-of-the-art administrative educational chatbots. Furthermore, by automating routine inquiries and offering 24/7 access to information and support, this model has the potential to reduce administrative workload and improve the overall student experience significantly. Moreover, the modular design of our hybrid model offers a foundation for future research on personalizing chatbot interactions and integrating domain-specific knowledge for enhanced communication within educational environments.

Simulated Annealing (SA), Tabu Search (TS), and Variable Neighborhood Search (VNS) are well-established single-solution-based metaheuristics known for their efficiency. In this paper, we explore the application of these techniques to enhance the performance of graph network models, specifically Graph Neural Networks (GNNs) and Graph Convolutional Networks (GCNs). By leveraging these metaheuristics, we aim to optimize key aspects of graph-based learning, such as hyperparameter tuning, architecture design, feature selection, and graph structure learning. Our approach demonstrates how these metaheuristics can improve the generalization, efficiency, and robustness of GNNs/GCNs, facilitating their use in large-scale graph-based tasks. The proposed framework illustrates the potential of combining advanced optimization techniques with state-of-the-art graph machine learning models.

This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Reconstruction Attacks, where adversaries attempt to infer or reconstruct data that should have been removed. In addition, we explore security attacks including Machine Unlearning Data Poisoning, Unlearning Request Attacks, and Machine Unlearning Jailbreak Attacks, which target the underlying mechanisms of unlearning to manipulate or corrupt the model. To mitigate these risks, various defense strategies are examined, including differential privacy, robust cryptographic guarantees, and Zero-Knowledge Proofs (ZKPs), offering verifiable and tamper-proof unlearning mechanisms. These approaches are essential for safeguarding data integrity and privacy in high-stakes financial and e-commerce contexts, where compromised models can lead to fraud, data leaks, and reputational damage. This survey highlights the need for continued research and innovation in secure machine unlearning, as well as the importance of developing strong defenses against evolving attack vectors.

Background/Objective: The Dark Web has played a pivotal role in the progress and sophistication of cybercrime. It provides an incubation network beyond the reach of traditional search engines where cybercriminals create and display exploit kits, offers illicit goods and services, and exchange confidential insider intelligence. Cybercriminals are extremely adept at selecting targets, applying tools to achieve their objectives, and minimizing red tape. The increasing sophistication of cybercriminals and the exponential rise of cybercrime against critical infrastructure underlines the necessity of identifying emerging threats. The objective of this research is to investigate the evolving threats within the Dark Web including crimeware-as-a-service and the integration of AI/ML into cyberattacks to inform risk management strategies and strengthen security measures.Research Problem: The exponential rise in cybercrime against critical infrastructure reflects growing sophisticationpresenting a significant challenge to organizations and society. The motivation behind cybercrime is fundamentally driven by self-greed which has contributed drastically to the magnitude and changes in methods used by cybercriminals to enhance profitability. The impact of cybercrime on business organizations presents an adverse impact on society and carries significant risks for the progress of individuals and the world at large. As cybercriminals adopt new technologies and services such as crimeware-as-a-service, identifying emerging trends becomes crucial to developing proactive strategies for the detection and prevention of cyber threats.Methodology: This research employs a systematic literature review approach to analyze emerging trends in cybercrime originating from the Dark Web. The review includes scholarly articles, news sources, and blog posts sourced from platforms like Google Scholar, IEEE Xplore, and various libraries. The key focus is to answer questions regarding the relationship between the Dark Web and cybercrime, accelerating cybercrime activities, and the benefits and implications of these new trends.Results: Key findings of this paper range from the rise of crimeware-as-a-service attacks and the increasing use of artificial intelligence and/or machine learning capabilities by cybercriminals to automate attacks across various businesses and organizations are also propounded along with information related to entry points and cybercrime attack pathways. The emergence of sophisticated cybercrime techniques, including ransomware-as-a-service, targeted attacks using AI, and exploitation of IoT vulnerabilities, are identified as critical trends. Social engineering, malware, and the rise of remote work have expanded the attack surface for cybercriminals.Discussion: As the use of cybercrime continues to metamorphose, the identification of new threats and extrapolation of emerging trends is critical to investigate the challenges associated with the monitoring and detection of illegitimate activities on the Dark Web as well as for the establishment of proactive risk management strategies and implementation of robust security measures. The research highlights the transformation of cybercrime into a structured and scalable ecosystem driven by technological advancements and service-based attack models. Cybercriminals now leverage AI/ML increasing the sophistication and success of their attacks. The commoditization of cybercrime has enabled less skilled individuals to participate amplifying the volume and diversity of threats faced by organizations.Conclusion: As cybercrime continues to evolve and adopt emerging technologies, organizations must remain vigilant and adaptable. The findings emphasize the need for proactive risk management, continuous monitoring of cybercrime trends, and robust security measures to mitigate the increasing threats originating from the Dark Web. Future research should focus on deeper exploration of AI-driven attacks and the development of more advanced countermeasures to safeguard critical infrastructure.

This paper analyzes the experience of first-person shooter (FPS) players when the game difficulty is adjusted by personalizing their audio cue settings, considering the balance between player performance, modeled using Gaussian Process Regression (GPR), and prior data serving as designer preference. In addition, we investigate the reason why player experience changes according to in-game audio cues. Previous studies have proposed various dynamic difficulty adjustment (DDA) methods for FPS games. However, few studies have considered the role of audio cues in the player experience. This paper compares the player experience of personalized enemy audio cue volume setting (GPR-DDA) and that of predetermined setting in an FPS game. Two comprehensive experimental phases, involving 80 participants, are conducted to assess the efficacy of GPR-DDA. The experience of our players is measured using questions taken from the Game User Experience Satisfaction Scale (GUESS) questionnaire and a final survey asking their open-ended feedback. A large language model (LLM) is used to analyze the natural language expressions of the players according to their native languages. To effectively have an LLM assist a limited number of qualified human evaluators in the classification of player responses, we develop an original procedure for this task. The GUESS results show that GPR-DDA can improve the player experience, and, in addition, the high consistency in the classification results over multiple runs of the selected LLM, as well as the similarity between its results and those of our human evaluators, reflect the reliability of the proposed LLM-assisted procedure.

The integration of Artificial Intelligence (AI) and the Internet of Things (IoT) in healthcare is transforming chronic disease management and pandemic response, particularly for vulnerable populations such as the elderly and those with multiple chronic conditions. This review systematically examines the current applications of AI and IoT technologies in managing chronic diseases like diabetes, cardiovascular disease, and chronic obstructive pulmonary disease (COPD), alongside their role in enhancing healthcare response during the COVID-19 pandemic. Key findings demonstrate significant improvements in patient outcomes, including enhanced glycemic control in diabetes management, early detection of cardiovascular anomalies, and a reduction in hospital admissions for chronic disease patients through AI-enabled remote monitoring. Despite these advancements, challenges remain, including data security, algorithmic bias, and the high cost of implementing AI and IoT systems. This review explores future directions for overcoming these obstacles, emphasizing the potential of multi-dimensional data integration, real-time predictive analytics, and personalized AI models to further revolutionize healthcare. Additionally, the accompanying Graphic Abstract visually illustrates how AI-driven insights, generated from IoT-enabled devices, are transforming healthcare delivery by facilitating real-time monitoring, personalized interventions, and proactive patient care. The article concludes with recommendations for addressing the technological, ethical, and regulatory challenges that must be overcome to fully realize the potential of AI and IoT in healthcare.

Pre-trained language models (PLMs) have significantly advanced natural language processing (NLP), establishing the "pre-training + fine-tuning" paradigm as a cornerstone approach in the field. However, the vast size and computational demands of Transformer-based PLMs present challenges, particularly regarding storage efficiency and processing speed. This paper addresses these limitations by proposing a novel lightweight PLM optimized for accurately understanding domain-specific computer terminology. Our method involves a pipeline parallelism algorithm designed to accelerate training. It is paired with an innovative mixed compression strategy that combines pruning and knowledge distillation to effectively reduce the model size while preserving its performance. The model is further fine-tuned using a dataset that mixes source and target languages to enhance its versatility. Comprehensive experimental evaluations demonstrate that the proposed approach successfully achieves a balance between model efficiency and performance, offering a scalable solution for NLP tasks involving specialized terminology.

This study presents the Bayesian-Optimized Attentive Neural Network (BOANN), a novel approach enhancing image classification performance by integrating Bayesian optimization with channel and spatial attention mechanisms. Traditional image classification struggles with the extensive data in today's big data era. Bayesian optimization has been integrated into neural networks in recent years to enhance model generalization, while channel and spatial attention mechanisms improve feature extraction capabilities. This paper introduces a model combining Bayesian optimization with these attention mechanisms to boost image classification performance. Bayesian optimization optimizes hyperparameter selection, accelerating model convergence and accuracy; the attention mechanisms augment feature extraction. Compared to traditional deep learning models, our model utilizes attention mechanisms for initial feature extraction, followed by a Bayesian-optimized neural network. On the CIFAR-100 dataset, our model outperforms classical models in metrics such as accuracy, loss, precision, recall, and F1 score, achieving an accuracy of 77.6%. These technologies have potential for broader application in image classification and other computer vision domains.

Situational awareness detection and characterization of mental states have a vital role in medicine and many other fields. An electroencephalogram (EEG) is one of the most effective tools for identifying and analyzing cognitive stress. Yet, the measurement, interpretation, and classification of EEG sensors is a challenging task. This study introduces a novel machine learning-based approach to assist in evaluating situational awareness detection using EEG signals and spiking neural networks (SNNs) based on a unique spike-continuous-time-neuron (SCTN). The implemented biologically inspired SNN architecture is used for effective EEG feature extraction by applying time-frequency analysis techniques and allows adept detection and analysis of the various frequency components embedded in the different EEG sub-bands. The EEG signal undergoes encoding into spikes and is then fed into an SNN model which is well-suited to the serial sequence order of the EEG data. We utilize the SCTN-based resonator for EEG feature extraction in the frequency domain which demonstrates a high correlation with the classical FFT features. A new SCTN-based 2-D neural network is introduced for efficient EEG feature mapping aiming to achieve a spatial representation of each EEG sub-band. To validate and evaluate the performance of the proposed approach a common publicly available EEG dataset is used. Experimental results show that by using the extracted EEG frequencies features and the SCTN-based SNN classifier the mental state can be accurately classified with an average accuracy of 96.8% for the common EEG dataset. Our proposed method outperforms existing machine learning-based methods and demonstrates the advantages of using SNN for situational awareness detection and mental state classifications.

Explainable AI (XAI) has emerged as a pivotal tool in healthcare diagnostics, offering much-needed transparency and interpretability in complex AI models. XAI techniques, such as SHAP, Grad-CAM, and LIME, enable clinicians to understand AI-driven decisions, fostering greater trust and collaboration between human and machine in clinical settings. This review explores the key benefits of XAI in enhancing diagnostic accuracy, personalizing patient care, and ensuring compliance with regulatory standards. However, despite its advantages, XAI faces significant challenges, including balancing model accuracy with interpretability, scaling for real-time clinical use, and mitigating biases inherent in medical data. Ethical concerns, particularly surrounding fairness and accountability, are also discussed in relation to AI's growing role in healthcare. The review emphasizes the importance of developing hybrid models that combine high accuracy with improved interpretability and suggests that future research should focus on explainable-by-design systems, reducing computational costs, and addressing ethical issues. As AI continues to integrate into healthcare, XAI will play an essential role in ensuring that AI systems are transparent, accountable, and aligned with the ethical standards required in clinical practice.

Abstract—Traditional automatic modulation classificationmethods operate under the closed-set assumption, which provesto be impractical in real-world scenarios due to the diversenature of wireless technologies and the dynamic characteristicsof wireless propagation environments. Open-set environments introduce substantial technical challenges, particularly in terms ofdetection effectiveness and computational complexity. To addressthe limitations of modulation classification and recognition inopen-set scenarios, this paper proposes a semi-supervised openset recognition approach, termed SOAMC (Semi-SupervisedOpen-Set Automatic Modulation Classification). The primaryobjective of SOAMC is to accurately classify unknown modulation types, even when only a limited subset of samples ismanually labeled. The proposed method consists of three keystages: (1) A signal recognition pre-training model is constructedusing data augmentation and adaptive techniques to enhancerobustness. (2) Feature extraction and embedding are performedvia a specialized extraction network. (3) Label propagation isexecuted using a graph convolutional neural network (GCN) toefficiently annotate the unlabeled signal samples. Experimentalresults demonstrate that SOAMC significantly improves classification accuracy, particularly in challenging scenarios with limitedlabeled data and high signal similarity. These findings are criticalfor the practical identification of complex and diverse modulationsignals in real-world wireless communication systems.

This work addresses the analysis and characterization of deadlocks in discrete-event systems modeled by labeled Petri nets (LPNs) with undistinguishable and unobservable transitions. To provide a solution for the notorious problem, it is essential to present an effective characterization such that deadlock control and synthesis are technically and methodologically possible. To this end, we introduce the notion of dangerous implicit vectors (DIVs) which implicitly threaten the system deadlock-freedom. The set of dead markings is divided into two subsets: dead basis markings (DBMs) and dangerous implicit markings (DIMs). An algorithm is designed to compute the sets of DIVs and DIMs at a given basis state of a system. Moreover, by virtue of linear algebraic equations, we formulate sufficient conditions to identify the existence of blocking markings in an LPN. Finally, an algorithm is developed to construct an observed graph that is a compact representation of the reachability graph of a Petri net with respect to the existence of dead reaches. At the end of this paper, experiment results that illustrate the correctness and effectiveness of the reported solution are presented.

UML (Unified Modeling Language) diagrams are graphical representations used in software engineering which play a vital role in the design and development of software systems and various engineering processes. Large, good-quality datasets containing UML diagrams are essential for different areas in the industry, research and teaching purposes, however few exist in the literature and it is common to find duplicate elements in the existing datasets. This might affect the evaluation of the models obtained when using these datasets. This paper addresses the challenge of creating a ground truth dastaset of UML diagrams, including semi-automated inspection to remove duplicates and ensure the correct labeling of all UML diagrams contained in the dataset. In particular, a dataset of six UML diagram classes has been assembled, comprising a total of 2,626 images (426 activity diagrams, 636 class diagrams, 352 component diagrams, 357 deployment diagrams, 435 sequence diagrams, and 420 use case diagrams). Importantly, unlike other existing datasets, ours contains no duplicate elements and all diagrams are correctly labeled. Our curated dataset is a valuable and unique resource for the research community because it serves as a foundation for training and evaluating various models. In this paper, we demonstrate this by training and testing several deep learning models using our dataset, achieving highly satisfactory results compared to those presented in other works in the literature. Additionally, our experimental results highlight the potential of Visual Transformers for UML diagram classification, setting our approach apart from others that predominantly used Convolutional Neural Networks for similar tasks.

The United States is facing an alarming surge in cyberattacks, with data breaches rising by 72% since 2021, presenting grave national security risks. Notable incidents, including Chinese hackers attempting to access high-level government information and Iranian-linked cyber groups targeting U.S. water systems, highlight the fragility of critical infrastructure. These attacks pose dangers not only to national security but also to economic stability and public health, amplified by the rapid growth of interconnected technologies and global digitalization. In response to these escalating threats, the U.S. must take a multifaceted approach. Key strategies include strengthening cybersecurity education and workforce development, enforcing more rigorous regulatory frameworks, and enhancing preparedness through incident response and recovery planning. Additionally, increased international cooperation is essential to address state-sponsored cyber threats and foster a global framework for cybersecurity defense. As cyber threats continue to evolve, future efforts will rely on technological advancements such as artificial intelligence (AI) for real-time threat detection, the adoption of zero-trust security models, and the development of adaptive, resilient cybersecurity infrastructures. Collaboration between the public and private sectors, coupled with ongoing innovation and education, will be critical to maintaining national security and promoting economic growth in an increasingly interconnected digital landscape.

This paper introduces the novel concept of Time-Traveling Turing Machines (TTTMs) — Turing Machines with the ability to read symbols that have been explicitly sent from their future computational state. We delve into their properties and behavior, particularly emphasizing the importance of maintaining a self-consistent computational timeline. We present theorems demonstrating the universality of these machines and the challenges in achieving faster computations than traditional Turing Machines.

Effective communication in automated chat systems hinges on the ability to understand and respond to context. Traditional models often struggle with determining when additional context is necessary for generating appropriate responses. This paper introduces Context-Aware BERT (CA-BERT), a transformer-based model specifically fine-tuned to address this challenge. CA-BERT innovatively applies deep learning techniques to discern context necessity in multi-turn chat interactions, enhancing both the relevance and accuracy of responses. We describe the development of CA-BERT, which adapts the robust architecture of BERT with a novel training regimen focused on a specialized dataset of chat dialogues. The model is evaluated on its ability to classify context necessity, demonstrating superior performance over baseline BERT models in terms of accuracy and efficiency. Furthermore, CA-BERT's implementation showcases significant reductions in training time and resource usage, making it feasible for real-time applications. The results indicate that CA-BERT can effectively enhance the functionality of chatbots by providing a nuanced understanding of context, thereby improving user experience and interaction quality in automated systems. This study not only advances the field of NLP in chat applications but also provides a framework for future research into context-sensitive AI developments.

This paper compares Demand Response algorithms suitable for Short-term Forecasting based on Advanced Metering Infrastructure (AMI). It selects ARIMA (AutoRegressive Integrated Moving Average), SARIMA (Seasonal ARIMA), LSTM (Long Short-Term Memory), and SVM (Support Vector Machine) as the primary research algorithms and delves into their theoretical foundations and functional characteristics. The theoretical background section explores each algorithm’s applicability in analyzing time-series data, recognizing nonlinear patterns, and solving optimization and classification problems. The methodology section will detail the methods of AMI data collection, the implementation of the algorithms, and the experimental setup. In the experiments and results section, the performance of each algorithm will be assessed by applying AMI data and presenting the outcomes of comparative analyses, with a focus on evaluating the predictive accuracy of the algorithms. The discussion will interpret the experimental results, analyzing the advantages and disadvantages of each algorithm and their applicability in the AMI system. It will also explore the limitations of the current research and directions for future research. The conclusion will summarize the key findings of the study and affirm how this research contributes to understanding and improving short-term forecasting and demand response systems based on AMI.

In the fast-evolving landscape of web services, success relies on optimizing efficiency, reliability, and user satisfaction. Decision-making in real-world applications demands a blend of quantitative (numerical values of quality of Service factors) and qualitative data of experts’ ratings of the quality of service factors. This paper proposes an optimization technique that integrates Hesitant and Intuitionistic Fuzzy Linguistic Terms with TOPSIS, leveraging Entropy Objective weights. There is limited research on Hesitant Intuitionistic Fuzzy Linguistic terms and the need to model fuzziness, haste and intuition in data precisely from experts rating. Thus, this article introduces an Entropy-based model tailored for web service optimization. Using the WS-DREAM dataset, quantitative data was extracted and objective weights were determined through the Entropy algorithm and qualitative evaluations from five experts, employing Hesitant Intuitionistic Fuzzy Linguistic Terms, were integrated. The process involved computing criteria weights and experts' assessment of Quality of Service factors for four services (S1, S2, S3, and S4) to form the Fuzzy Decision Matrix using modified Online output software. Applying the proposed technique to a web service optimization problem validated its effectiveness. The results indicated optimal selection of S1 as the best web service, supported by Coefficient Index values (0.785). This study introduces a novel approach, Entrop – Hesitationistic - Fuzz-TOPSIS, for web service optimization, integrating quantitative and qualitative data through an Entropy-based model. The effectiveness of the proposed technique, validated through application on the WS-DREAM dataset, underscores its potential in addressing real-world decision-making challenges. The optimal selection of S1 as the best web service suggests practical utility. The study encourages further exploration of this technique's applicability to diverse Multiple Criteria Decision Making (MCDM) problems, opening avenues for future research and application.

With all the sophisticated threats to network security, intrusion detection is a section of the security technology industry that is becoming increasingly significant. In this research paper, we have discussed in detail the detection, effects, and prevention protocols of security issues. Security issues are a wide range of elements. Hence, we narrowed our research to two main sectors which are malware attacks and distributed denial of service (DDOS). To make the research more informative, we looked at three selected real-life cases of security intrusion that occurred around the world in recent years. Malware attacks and DDOS are constantly being developed creatively to challenge all the current security systems. In addition, we have analysed and highlighted the potential threats of the security issue and included proposed countermeasure ideas to avoid the security issues. The research findings also show us that malware is evolving simultaneously with our security technology growth. This gives us an understanding that prevention is significantly a continual improvement process.

Software quantum simulators are the most accessible tools for designing and testing quantum algorithms. This paper presents a comprehensive approach to building a software-based quantum simulator based on classical computing architectures. We explore fundamental quantum computing concepts, including state vector representations, quantum gates, and memory management techniques. The simulator prototype implements various memory optimization strategies, such as full-state representation, dynamic state pruning, and shared memory parallelization with OpenMP and distributed memory models using MPI. Additionally, data compression techniques, like ZFP, are explored to enhance simulation performance by reducing memory footprint. The results are validated through performance comparisons with leading open-source quantum simulators, such as Intel-QS, QuEST, and qsim. Our findings highlight the trade-offs between computational overhead and memory efficiency. This demonstrates that a hybrid approach using distributed memory and compression offers the best scalability for simulating large quantum systems. This work provides a foundation for developing efficient quantum simulators supporting more complex quantum algorithms on classical hardware.

This study introduces the Data-Driven Personalized Learning Model (DDPLM), a sophisticated framework designed to enhance foreign language acquisition through the integration of big data analytics. Implemented within the educational platforms Edmodo and Duolingo, DDPLM utilizes real-time data processing to tailor learning paths and content dynamically to individual learner needs. Our findings indicate significant improvements in language learning efficiency, engagement, and retention. The model's adaptability across different digital environments showcases its potential scalability and effectiveness in various educational contexts. Additionally, the research addresses the critical role of personalized feedback and adaptive challenges in maintaining learner motivation and promoting deeper linguistic comprehension. The outcomes suggest that DDPLM significantly transforms traditional language education, making it more personalized, efficient, and aligned with individual learning preferences.

Crypto-ransomware has emerged as one of the most significant cybersecurity threats in recent years. Ransomware attacks, particularly those involving the encryption of data and demanding payment in cryptocurrency, have caused severe disruptions across various critical industries, including healthcare, energy, and finance. The proliferation of these attacks is largely attributed to the anonymity provided by cryptocurrency transactions and the increasing sophistication of cybercriminal tactics. The impact of ransomware extends beyond immediate financial losses, often leading to prolonged operational downtime, reputational damage, and even risks to public safety. In this research paper, we explore the growing threat of crypto-ransomware by examining real-life case studies in key industries, analyzing the countermeasures taken, and proposing additional solutions to mitigate the risk. The goal is to raise awareness and provide actionable insights for organizations to better protect themselves against this pervasive threat.

The rapid acceleration of artificial intelligence (AI) has sparked extensive debate about its impact on the safety and security of society. While AI has shown trans- formative potential, particularly in areas such as healthcare and independent structures where it complements productivity and minimizes human error, accu- racy and protection. However, the misuse of artificial intelligence poses real risks, along with threats such as deep counterfeiting, computer cyber-attacks and the manipulation of social behavior through disinformation. These risks vary from privacy and cyber security breaches to moral dilemmas around liability. The unchecked improvement of AI is expected to threaten the social order, so the relationship between innovation and governance is essential so that AI-related threats do not overshadow its benefits. This article offers a detailed assessment and review of the literature that studies the potential dangers that AI poses to society. The cumulative effects underscore the urgent need for comprehensive regulatory frameworks to mitigate these threats.

This study provides a detailed examination of Natural Language Processing (NLP) for the complexscript of Nepali. We analyze available data resources today and discuss relevant points includingcharacter encoding, advanced tokenization methods and morphological complexity. This allows us tocontrast Nepal’s unique language and technology ecosystem with Hindi and Thai in terms of NLPadvancements. Quantitative assessment of existing tools and resources is offered by this investigationwhich highlights immediate weaknesses as well as areas that need more effort. Various ethicalconcerns are addressed here while potential topics for future research as e-governance, healthcare oreducation with a focus on new domain-specific applications, and cross-lingual transfer learning aresuggested. The objective of this attempt is to enhance understanding of natural language processing(NLP) in Nepali language and beyond aimed at developing NLP technologies that are more efficient,inclusive, culturally appropriate across diverse linguistic communities.

Virtual Reality (VR) is increasingly used in neuropsychological assessments due to its ability to simulate real-world environments. This study aimed to develop and evaluate the Trail Making Test in VR (TMT-VR) and investigate the effects of different interaction modes and gaming skills on cognitive performance. A total of 71 young female and male adults (aged 18-35) with high and low gaming skills participated in this study. Participants completed the TMT-VR using three interaction modes: eye-tracking, head movement, and controller. Performance metrics included task completion time and accuracy. User experience, usability, and acceptability of TMT-VR were also examined. Results showed that both eye-tracking and head movement modes significantly outperformed the controller in terms of task completion time and accuracy. No significant differences were found between eye-tracking and head movement modes. Gaming skills did not significantly influence task performance using any interaction mode. Participants reported high usability, acceptability, and user experience for the TMT-VR. Eye-tracking facilitated higher accuracy, while head movement higher speed. The TMT-VR offers high usability and user experience and is well accepted by the participants. The findings suggest that VR-based assessments can effectively measure cognitive performance without being influenced by prior gaming skills, indicating potential applicability for diverse populations.

With the development of human-computer interaction, the importance of emotion recognition is increasing. Emotion recognition technology provides practical benefits in various industries such as improving user experience, education, and organizational productivity. In education, emotion recognition can enable real-time understanding of students' emotional states and provide tailored feedback, and in the workplace, by monitoring employees' emotional states, it can improve work performance and job satisfaction. Therefore, multimodal-based research that combines text, speech, and video data for emotion recognition is being conducted in various industries. In this study, we propose an emotion recognition method that combines text and speech data, reflecting the characteristics of the Korean language. For text, KoELECTRA is used to perform embedding, and for speech, MFCC and pitch analysis are used to extract features. Finally, a multimodal transformer model is proposed that combines these two data types to perform emotion recognition. The multimodal transformer model processes text and speech data separately, and then learns the interaction between the two modalities through a Cross-Modal Attention mechanism. Through this, the complementary information from text and speech is effectively combined, improving emotion recognition performance. Experimental results show that the proposed model outperforms single-modality models, achieving a high accuracy of 73.13% and an F1-Score of 0.7344 in emotion classification. This study contributes to the advancement of emotion recognition technology by combining various language and modality data, and higher performance can be expected through the integration of additional modalities in the future.

Event detection provides a crucial foundation for intelligent text analysis and supports numerous downstream applications. However, existing detection models often fail to meet the high accuracy requirements and typically require a human–machine collaborative detection mode involving “machine detection followed by manual audit and correction.” Analysis reveals that the recall rate of machine detection is a major factor limiting the efficiency of human–machine collaboration. To address this at its root and ensure high recall, an event trigger recommendation task is introduced, and a span-based recommendation model for Chinese, SpETR (Span-based Event Trigger Recommender), is developed. This model integrates confidence information from both trigger identification and event classification stages to recommend candidate triggers and their event types for each event. To enhance recall, a semantic boundary smoothing method is proposed, which assigns soft labels to spans around gold triggers based on semantic completeness and part-of-speech, combined with a modified focal loss function to make the model predictions smoother. Experiments on DuEE and a self-built dataset show that SpETR is most effective when the number of recommendations is set to 3, achieving recall rates of 97.76% and 98.70%, respectively, comprising improvements of 4.30% and 5.22% over the optimal baseline models. In terms of human–machine collaborative detection, SpETR saved 30.6% and 25.8% of time compared to traditional detection models on two datasets, and the average F1 score of the annotation results was also improved by 5.35% and 3.48%, respectively.

This scoping review explores the intersection of Extended Mind Theory and Extended Reality (XR) technologies, focusing on how Virtual Reality, Augmented Reality, and Mixed Reality reshape human cognition and interaction. XR enables users to offload cognitive tasks and engage in embodied experiences, extending cognition beyond the brain into digital environments. The review highlights a wide range of XR applications, from immersive learning in STEM education and medical training, neuropsychological assessment to therapeutic interventions, arts and entertainment, professional skills development, retail and e-commerce, remote work, sports training, architecture and urban planning, and cultural heritage preservation. XR's integration with modalities like haptics, eye-tracking, face- and body-tracking, and brain-computer interfaces further enhances cognitive extension and user engagement. However, alongside these advancements come significant ethical, psychological, and societal challenges, such as data privacy concerns, the psychological effects of prolonged immersion, and social inequality arising from disparate access to XR technologies. This review emphasizes the need for robust ethical frameworks that address these challenges, ensuring that XR technologies enhance human development while maintaining autonomy, privacy, and mental well-being. As XR continues to evolve and integrate with artificial intelligence and other emerging technologies, its role in expanding human cognition will depend on responsible implementation and governance.

This paper presents a comprehensive exploration of Data Quality terminology, revealing a significant lack of standardisation in the field. We propose a novel approach to aggregating disparate Data Quality terms used to describe the multiple facets of Data Quality, under common umbrella terms, with a focus on the ISO 25012 standard. Our aim is to design a Data Quality Data Model that serves as a universally applicable framework for Data Quality assessment. We introduce four additional Data Quality dimensions: Governance, Usefulness, Quantity, and Semantics, enhancing specificity, complementing the framework established by the ISO 25012 standard, and understanding of Data Quality aspects. The ISO 25012 standard, while tailored for software development, offers a foundation for the development of our proposed Data Quality Data Model. This is due to the prevalent nature of software development across a multitude of domains. In contrast, frameworks like ALCOA+ that are specific to certain domains lack the ability to be generalised. The model we propose can be seen as a "Rosetta Stone" for Data Quality terminology, facilitating a seamless communication of Data Quality between different domains when collaboration is required to tackle cross-domain projects or challenges.

This paper introduces the self-supervised pretext task of rare visual token enhancement: given an image, the model is trained to push the rarest visual tokens far from all the others. This pretext task slightly-but-consistently improves baseline performances for both registration and few-shot change detection on OSCD, LEVIR-CD and S2looking.

Modular inversion on large operands is a time-consuming calculation used in elliptic curve cryptography. Its hardware implementation requires extensive hardware resources such as lookup tables and registers. We investigate state-of-the-art modular inversion algorithms and evaluate the performance and cost of the algorithms and their hardware implementations. We then propose a high-radix modular inversion algorithm aimed at short execution time and low hardware cost. We present a detailed radix-8 hardware implementation based on 256-bit primes in Verilog HDL and compare its cost performance with other implementations. Our implementation on the Altera Cyclone V FPGA chip uses 1227 ALMs (Adaptive logic modules) and 1037 registers. The modular inversion calculation takes 3.67 microseconds. The AT (Area time) factor is 8.30, outperforming other implementations. We also present an implementation of elliptic curve cryptography using the proposed radix-8 modular inversion algorithm. The implementation results also show that our modular inversion algorithm is more efficient in area time than other algorithms.

There is a bifurcation in the academic voice regarding the adoption or rejection of generative AI in the classroom. This division in pedagogy remains ever present as educators struggle to catch up with advancing AI technology and its staunch integration into student’s everyday lives. A resounding concern from educators is for the authenticity of student work and the building of critical thinking skills, both of which become threatened by generative AI tools used without proper guidelines. Educators have a right to these concerns, as studies continue to show how generative AI tools successfully pass assessments and how the AI-coauthored work is challenging to detect or differentiate from student-authored work. In the field of Computer Science, the challenges compound as generative AI technology integrates seamlessly into already approved code-generation tools and development environments. Therefore, an informed and thoughtful decision must be made so that student learning can continue to flourish and evolve in a safe and inclusive setting. This research attempts to go beyond introductory course assessments, where a gap in research currently hangs. As curriculum becomes more challenging and abstract, can generative AI continue to pass assessments and be useful educational assistants? Or will these tools create more confusion for students as prompts become more advanced and prove difficult to interpret? During this empirical study, GitHub Copilot is assessed against the assessments of an advanced CS programming course. The findings present a resounding optimism for generative AI tools, with all assessments passed successfully. The study concludes with recommending an integrated approach of introducing and encouraging the use of generative AI. Collaboration with a partnership mindset will produce the best results.

In this paper, we propose "Synergized Efficiency Optimization for Large Language Models" (SEO-LLM), a groundbreaking approach that integrates advanced data utilization and model compression techniques to significantly enhance the performance, efficiency, and scalability of large language models (LLMs). Our method synergistically combines Adaptive Data Augmentation (ADA), Transfer- Active Learning (TAL), Adaptive Iterative Pruning (AIP), and Synergistic Quantization and Distillation (SQD). These components work together to reduce the training data requirement by 30%, compress model size by 67.6%, and improve inference speed by up to 50%, while preserving or even enhancing model accuracy across various NLP tasks. ADA dynamically adjusts augmentation strategies to optimize model generalization, while TAL leverages pre-trained models to focus learning on the most informative data samples. AIP intelligently prunes less significant weights, and SQD harmonizes quantization with knowledge distillation to achieve high compression rates without significant performance loss. The synergy between these techniques makes SEO-LLM a robust solution for deploying LLMs in resource-constrained environments, maintaining state-of-the-art performance with a fraction of the computational and data resources.

As the adoption of deep learning models continues to surge across various applications, the need for efficient deployment architectures becomes increasingly critical. This paper presents a novel approach to enhance the deployment of deep learning models by leveraging serverless architecture. Serverless computing has been popular for its auto-scaling, cost-effectiveness, and simplified management characteristics. However, the intense resource demands of deep learning models pose challenges in maintaining low response times and effective load balancing within serverless environments. The proposed architecture addresses these challenges by integrating principles from both deep learning model optimization and serverless computing. Through systematic experimentation and analysis, we demonstrate that by appropriately designing and tuning the deployment architecture, significant improvements in response time, performance, resource utilization, and load distribution can be achieved.

It is critical to keep abreast of emerging dangers in the constantly changing field of cyber security. As 2024 approaches, numerous technological developments and trends are changing how businesses handle cyber security. This article explores the cutting edge of cyber security developments that are expected to rule in 2024. The field of cyber security is undergoing a revolution, from the adoption of Zero Trust Architecture (ZTA) as the new paradigm to the integration of AI and ML for real-time threat detection. Solutions for Extended Detection and Response (XDR) are becoming the mainstay for thorough threat detection and response in a variety of contexts, including networks, endpoints, and cloud environments. The use of biometric authentication techniques is growing in popularity because they provide better access control and identity verification. Concurrently, Deception Technologies are altering defensive tactics by using fictitious assets to trick and identify attackers at an early stage. Quantum-resistant cryptography, which aims to protect sensitive data from future quantum attacks, is on the horizon given the threat posed by quantum computing. Furthermore, the growing number of linked devices emphasizes how critical it is to strengthen IoT security protocols. Moreover, as long as companies are using cloud computing, they must make sure that strong cloud security protocols are in place. Simultaneously, the emergence of containerization technologies demands a targeted strategy for containerized environment security. Organizations must adopt these practices and strengthen their defenses against new threats as the cyber security landscape changes. Businesses may confidently and resiliently traverse the complex cybersecurity landscape of 2024 by remaining aware and implementing proactive security measures.

Meta-heuristic algorithms are methods that try to solve problems by imitating events and systems existing in nature. It can be very difficult to solve nonlinear problems with the help of known classical algorithms. In this study, a new meta-heuristic method, the Pi algorithm, is proposed. Pi is a special number that is not periodic and contains many different number combinations in its digits calculated so far. The most important part of meta-heuristic methods is the equations and parameters used to ensure the diversity of the created population. In this study, a specific Pi coefficient for each attribute was calculated with the help of the Monte-Carlo method. These coefficients were used in the Pi algorithm in other parts of the study. In the application for data clustering, experiments were made on 5 different data sets. The best accuracy rate of 95.5% was achieved. In this respect, it has been seen that the Pi algorithm works successfully as a meta-heuristic method. It can be studied on a population-based data clustering, classification, prediction, etc. It can be easily applied in all areas.

In conventional Federated Learning (FL), clients work together to train a model managed by a central server, intending to speed up the learning process. However, this approach imposes significant computational and communication burdens on clients, particularly with complex models. Additionally, while FL strives to protect client privacy, the server's access to local and global models raises security concerns. To address these challenges, Split Learning (SL) separates the model into parts handled by the client and the server, though it suffers from inefficiencies due to sequential client participation. To overcome these issues, SplitFed Learning (SFL) was proposed, which combines the parallelism of FL with the model-splitting strategy of SL, enabling simultaneous training by multiple clients. Our main contribution is the theoretical analysis of SFL, which, for the first time, includes non-i.i.d. datasets, non-convex loss functions, and both full and partial client participation. We provide convergence proofs for a state-of-the-art SFL algorithm based on conventional convergence analysis assumptions for FL. Our results prove that we can recover the linear convergence rate of conventional FL for the SFL algorithm with the distinction that increasing the number of local steps or clients may not speed up the convergence in SFL.

Ransomware, a combination of "ransom" and "malware," is a type of malicious software designed to encrypt or block access to a victim's data or system, demanding a ransom for its release Initially targeting individuals, ransomware has evolved to attack businesses for greater financial gain. It mainly exists in two forms: encrypting ransomware, which holds data hostage, and non-encrypting ransomware, which blocks system access and displays a ransom note. The energy sector has been notably targeted by ransomware, exemplified by the 2021 attack on Colonial Pipeline by the DarkSide group, which led to a temporary shutdown and a significant fuel shortage on the US East Coast. Similarly, in 2023, Russian hackers using LockBit ransomware disrupted Royal Mail, halting international deliveries and incurring millions in recovery costs despite no ransom payment. These incidents underscore the need for comprehensive cybersecurity strategies that combine human vigilance with advanced technologies like AI and machine learning. By adopting a multi-layered protection approach, organizations can better prepare for and mitigate the risks posed by ransomware attacks safeguarding sensitive data and ensuring business continuity.

Background: Accurate sales forecasting in the mobile phone industry is critical to informed decision making by both the government and corporations. This study seeks to enhance mobile phone sales predictions by incorporating brand exposure as a predictive factor, hence addressing the gap left by the existing forecasting models that do not consider the impact of brand awareness. Method: This study thereby indicates a quantification method for brand exposure that merges word-of-mouth reviews with online search data. Word2Vec is used to extract initial keywords from a word-of-mouth corpus, whereas time-lag correlation analysis refines the core keywords. Later, PCA synthesizes brand exposure. The attention-LSTM framework hereby develops a forecasting model of mobile phone sales, effectively combining long short-term memory networks with the ability to capture time series dependencies and an attention mechanism to reduce data redundancy. Results: By considering brand exposure, the experiments demonstrate that the attention-LSTM model decreases the RMSE and MAPE indicators by 2.02% and 0.96%, respectively. In addition, compared with the ARIMA, SVR, BP neural network, and LSTM models, the attention-LSTM model decreases the average percentage errors by 6.52%, 3.42%, 2.56%, and 0.81%, respectively. Conclusion: Attention-LSTM captures dynamic sales trends very well and holds great significance over traditional models. Overall, including brand exposure, this model is very strong for the interpretation of mobile phone sales predictions, which has important implications in terms of policy as well as corporate strategies.

Dead reckoning is a promising yet often overlooked smartphone-based indoor localization technology that relies on phone-mounted sensors for counting steps and estimating walking directions, without the need for extensive sensor or landmark deployment. However, misalignment between the phone’s direction and the user’s actual movement direction can lead to unreliable direction estimates and inaccurate location tracking. To address this issue, this paper introduces SWiLoc, an enhanced direction correction system that integrates passive WiFi sensing with smartphone-based sensing to form Correction Zones. Our two-phase approach accurately measures the user’s walking directions when passing through a Correction Zone and further refines successive direction estimates outside the zones, enabling continuous and reliable tracking. In addition to direction correction, SWiLoc extends its capabilities by incorporating a localization technique that leverages corrected directions to achieve precise user localization. This extension significantly enhances the system’s applicability for high-accuracy localization tasks. Additionally, our innovative Fresnel zone-based approach, which utilizes unique hardware configurations and a fundamental geometric model, ensures accurate and robust direction estimation, even in scenarios with unreliable walking directions. We evaluate SWiLoc across two real-world environments, assessing its performance under varying conditions such as environmental changes, phone orientations, walking directions, and distances. Our comprehensive experiments demonstrate that SWiLoc achieves an average 75th percentile error of 8.89 degrees in walking direction estimation and an 80th percentile error of 1.12 meters in location estimation. These figures represent reductions of 64% and 49%, respectively for direction and location estimation error, over existing state-of-the-art approaches.

The current era in which we live is centered on information technology because we live in the renaissance of information and its expansion on multiple scales and fields. People who have a high knowledge of technology and a passion for it seek to disseminate this information and process it correctly, and computers have now become one of the most essential devices for government operations. Large companies have already begun to use it in most businesses, and it has helped direct some government procedures for joint e-government, which allows people to access government services from home from their computers. It is also not hidden that with the increase in computer use, electronic crimes increased, and this contributed to the formation of laws. In various countries to deal with them. As technology evolves, the sophistication and impact of these cyber threats continue to grow, posing significant challenges to cybersecurity. This research discusses the role against cybercrime, the regulations, and the allowable behavior of using technology in Saudi Arabia. It analyzes cybercrime in the Kingdom and the system for combating cybercrime.

With the fast growth of smartphones and digital cameras, massive images are generated every day in the world. They are easily transmitted on the insecure channel-Internet. It has been a hot spot for protecting sensitive images during communication. A new cryptosystem is proposed using a six dimensional (6D) hyperchaotic system and DNA computing. The hash value is obtained with the function of SHA-512. It keeps the encrypted result closely connected with the original image. The initial values of the cryptosystem are produced with the hash value and the secret key. The pixel is divided into four parts, and a large matrix is formed. Scrambling is performed on the new image. DNA coding, modern DNA complementary rules, DNA computing, and DNA decoding are performed on the new image. Diffusion is also executed, and ciphered image is achieved finally. The experimental result reveals the outcome of the proposed algorithm. Security analysis shows that the designed algorithm has a huge secret key space, low correlation, and high sensitivity. It also signifies that the designed algorithm could protect against common attacks and is more secure than some existing methods.

In this paper, the P versus NP problem is studied based on a six-dimensional space-time perspective. The gap between the P-class and NP-class arises from the relationship between time and the solution, as well as the answer that is independent of time. The complexity of solving a problem depends on the time dependence of the answer. Solving problems whose answers do not depend on the passage of time is very difficult and impossible. Like the description of the gravitational factor in Newtonian physics, NP class problems require different mathematical tools. Based on the generalization of physical facts in mathematics, based on six-dimensional space-time, a method to solve problem P versus NP problem has been stated. The results of this study offer a fresh insight into information processing that occurs independent of the passage of time.

With the large-scale application of Internet of Things (IoT) in the medical field, eHealthcare has attracted wide attention. With the help of IoT devices, eHealthcare allows doctors to monitor patients’ health conditions and make recommendations accordingly. The addition of cloud computing greatly saves Healthcare Center’s (HC) computing resources. In order to provide privacy and fine-grained access control, Attribute-b ased encryption (ABE) is widely favored. HC usually operates multiple medical institutions in different regions, and each medical institution can be regarded as a attribute authority. Therefor, multi-authority (MA) ABE is usually concerned to encrypt the patient data. However for existing MA-ABE algorithms, the ciphertext is long and the efficiency of encryption and decryption is low. These problems will greatly increase the computing burden of patients and seriously affect the efficiency of data transmission. Hence we propose a decentralized key-policy MA-ABE in eHealthcare. The proposed algorithm can achieve decentralization, that is, it does not need central authority. Meanwhile, compared with existing MA-ABE algorithms, the length of ciphertext generated by our algorithm is shorter, and the efficiency of encryption and decryption is significantly improved. With the help of Java Pairing Based Cryptography, we carried out the experiments which show that our algorithm can effectively reduce the time required for encryption and decryption.

The Mixture of Experts (MoE) architecture has evolved as a powerful and versatile approach for improving the performance and efficiency of deep learning models. This survey aims to provide the fundamental principles of MoE in details, a paradigm that harnesses the collective power of multiple specialized "expert" models working in concert to tackle complex tasks.Our exploration is a thorough analysis of the core components that constitute the MoE framework. We begin by dissecting the routing mechanism, a crucial element responsible for dynamically assigning input data to the most appropriate expert models. This routing process is pivotal in ensuring that each expert's specialized knowledge is optimally utilized. The survey places significant emphasis on expert specialization, a key feature that sets MoE apart from traditional architectures. We examine various strategies for developing and training specialized experts, exploring how this specialization enables MoE models to effectively handle diverse and multifaceted problems.Load balancing, another critical aspect of MoE systems, receives thorough attention. We discuss techniques for efficiently distributing computational resources among experts, ensuring optimal model performance while managing hardware constraints. This section provides insights into the delicate balance between model capacity and computational efficiency. Furthermore, we provide an in-depth discussion of the expert models themselves, examining their architectural designs, training methodologies, and how they interact within the larger MoE framework. This includes an analysis of different types of experts, from simple neural networks to more complex, task-specific architectures. The survey also navigates through diverse research avenues within the MoE landscape, highlighting recent advancements and innovative applications across various domains of machine learning. We pay particular attention to the burgeoning use of MoE in two rapidly evolving fields: computer vision and large language model (LLM) scaling. By providing this comprehensive overview, our survey aims to offer researchers and practitioners a deep understanding of MoE's capabilities, current applications, and potential future directions in the ever-evolving landscape of deep learning.The Mixture of Experts (MoE) architecture has evolved as a powerful and versatile approach for improving the performance and efficiency of deep learning models. This survey aims to provide the fundamental principles of MoE in details, a paradigm that harnesses the collective power of multiple specialized "expert" models working in concert to tackle complex tasks.Our exploration is a thorough analysis of the core components that constitute the MoE framework. We begin by dissecting the routing mechanism, a crucial element responsible for dynamically assigning input data to the most appropriate expert models. This routing process is pivotal in ensuring that each expert's specialized knowledge is optimally utilized. The survey places significant emphasis on expert specialization, a key feature that sets MoE apart from traditional architectures. We examine various strategies for developing and training specialized experts, exploring how this specialization enables MoE models to effectively handle diverse and multifaceted problems.Load balancing, another critical aspect of MoE systems, receives thorough attention. We discuss techniques for efficiently distributing computational resources among experts, ensuring optimal model performance while managing hardware constraints. This section provides insights into the delicate balance between model capacity and computational efficiency. Furthermore, we provide an in-depth discussion of the expert models themselves, examining their architectural designs, training methodologies, and how they interact within the larger MoE framework. This includes an analysis of different types of experts, from simple neural networks to more complex, task-specific architectures. The survey also navigates through diverse research avenues within the MoE landscape, highlighting recent advancements and innovative applications across various domains of machine learning. We pay particular attention to the burgeoning use of MoE in two rapidly evolving fields: computer vision and large language model (LLM) scaling. By providing this comprehensive overview, our survey aims to offer researchers and practitioners a deep understanding of MoE's capabilities, current applications, and potential future directions in the ever-evolving landscape of deep learning.

The Mining Industry has changed significantly in recent decades with the introduction of advanced technologies such as Artificial Intelligence (AI) and Machine Learning (ML). These innovations contribute to the creation of expert systems that help in optimizing processes, increasing the safety and sustainability of operations. This article is a literature review of modern AI and ML methods and technologies used in the Mining Industry. Discusses various intelligent and expert systems used to improve productivity, reduce operating costs, improve occupational safety, environmental sustainability, machine automation, predictive analytics, quality monitoring and control, and inventory and logistics management. The advantages and disadvantages of different approaches are analyzed, as well as their potential impact on the future of the Mining Industry. The review highlights the importance of integrating AI and ML into mining processes to achieve more efficient and safer solutions.

In modern times, technology has become more than just a tool; it is a vital component of our lives, driving society and humanity towards new horizons, better living standards, and solu-tions for complex, global challenges. This article explores the world of dependable systems, specifically focusing on system design, software solutions, and architectural decisions that fa-cilitate collaborative work. It aims to dive into the intricacies of designing robust and effective document collaboration software. Throughout this paper, readers will gain insights into the proposed design process, enabling them to understand, learn from, and critically evaluate the examined methodologies and outcomes. Like everything else in the software technology field, there are multiple solutions to any given problem, and this work is no exception to this rule. The objective of this study is to provide a detailed architectural overview of the microservices pattern in an orchestrated cloud environment based on independent containers. To examine the pros and cons of such a system, the paper will detail how a real-time document collaboration system can benefit from such an architecture regarding availability, elasticity, scaling, and disaster recovery. Moreover, the paper will analyze how cloud-native technologies can be used to create a scalable platform solution, capable of handling traffic, dynamic resource storage, asynchronous com-munication, and application scaling. The intricate nature of this system renders this paper a valuable resource for prospective investigations within the domain of dependable systems, cloud computing, and distributed systems. This paper not only showcases the design and implementation process but also sets a founda-tion for future research and innovation in dependable systems, collaborative technologies, sustainable solutions, and distributed system architecture.

In the modern days the data is coming from various devices like mobiles, tabs, laptops, computers, IOT devices e.tc and is stored in the electronics form in the systems using the concept of files or data bases. Clustering Technique is used to extract data from these sources. Improving the accuracy of the model is improved using the feature selection or feature engineering or both. The feature engineering is used to add a new feature based on the global mean. Along with that new feature in addition to the feature selection increase the overall accuracy of the model.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

In the era of DevOps, developing new toolsets and frameworks that leverage DevOps principles is crucial. This paper demonstrates how Ansible’s powerful automation capabilities can be harnessed to manage the complexity of Kubernetes environments. This paper evaluates efficiency across various CNI (Container Network Interface) plugins by orchestrating performance analysis tools across multiple power profiles. Our methodology, which involves managing numerous components, dependencies, and configurations, requires high expertise and precision. Our performance evaluations across network interfaces with different theoretical bandwidths gave us a comprehensive understanding of CNI performance and overall efficiency. Our research confirms that certain CNIs are better suited for specific use cases, mainly when tuning our environment for smaller or larger network packages and workload types, but also that there are configuration changes we can make to mitigate that. This paper also provides research into how to use performance tuning to optimize the performance and efficiency of our CNI infrastructure, with practical implications for improving the performance of Kubernetes environments in real-world scenarios, particularly in more demanding scenarios such as High-Performance Computing (HPC) and Artificial Intelligence (AI).

Honeypots are vital security tools that enable cybersecurity specialists to scrutinize the tactics employed by attackers. By doing so, they can get valuable insights into existing and upcoming internet dangers. Cyber-attacks are in a perpetual evolution, increasingly sophisticated and tailored to exploit specific vulnerabilities. Hence, it is imperative for both organizations and individuals not only to consider but also implement methods to safeguard themselves against cyberattacks and malware. This paper assesses a specific group of honeypot systems by considering detection range, emulation accuracy, data quality, dependability, scalability, performance, extensibility, installation options, setup difficulty, and maintenance requirements. Furthermore, it provides conclusions regarding the relative effectiveness of diverse honeypot systems in different situations. As a part of the research, it analyzes the latest progress and innovations in honeypot development, including enhancements in machine learning, heightened automation, integration with other security tools, cloud-based honeypots, and deception technology by using simulated assaults to showcase the logging and recording capabilities of these honeypots in capturing attack information. After carefully analyzing each honeypot, each has unique advantages, disadvantages, and special characteristics.

Image generation optimization is an important research direction in the field of deep learning, which aims to improve the performance of image generation models and the quality of generated images. In recent years, researchers have made significant progress in image generation optimization with the development of deep generative models such as generative adversarial networks (GANs) and variational autoencoders (VAEs). These models are able to generate high-quality, realistic images by learning the distribution of image data. In this study, a deep learning-based image generation optimization model was adopted, which combined the advantages of GAN and VAE. The model architecture consists of a generator and a discriminator, where the generator is responsible for generating the image and the discriminator is used to judge the authenticity of the image. In addition, the model also introduces attention mechanism and self-supervised learning strategy to further improve the quality and diversity of generated images. In the training process, a large-scale image dataset is used, and a variety of optimization algorithms are used to improve the stability and efficiency of the model. By evaluating various indicators of the generative model, including image quality, generation speed and model convergence, it was found that the introduced attention mechanism and self-supervised learning strategy significantly improved the performance of the model.

This paper thoroughly assesses the ARM and RISC-V architectures in the context of High-Performance Computing (HPC). It includes an analysis of Docker, Kubernetes, and KVM virtualization integration. Our study aims to evaluate and compare these systems' performance, scalability, and practicality in a general context and then assess the impact that might have on special use cases, like HPC. ARM-based systems exhibited better performance and seamless integration with Docker and Kubernetes, underscoring their advanced development and effectiveness in managing high-performance computing workloads. On the other hand, despite their open-source architecture, RISC-V platforms presented considerable intricacy and difficulties in coordinating with Kubernetes, which hurt their overall effectiveness and ease of management. The results of our study offer valuable insights into the practical consequences of implementing these architectures for HPC, highlighting ARM's preparedness and the potential of RISC-V while acknowledging the increased complexity involved and significant trade-offs at this point.

Gaussian mixture models (GMMs) are powerful tools specifically suited for problems where data distributions are multi-modal. Inspired by Fourier expansion, we propose a concept called GMM expansion to approximate arbitrary densities. A simple learning method is introduced under this framework. Theoretical and numerical analyses are provided to show that densities under GMM expansion are able to approximate arbitrary densities with certain accuracy. The proposed learning algorithm demonstrates better accuracy and time efficiency compared to classic density approximation methods such as the Expectation Maximization (EM) algorithm and Bayesian variational inference (BVI) for Gaussian mixture models. The proposed framework also shows better accommodation of neural networks. Three neural network applications are built to demonstrate its usability. The accuracy of density estimation in neural networks is reported to be significantly improved in one of the applications. Another application shows that latent variables can be easily turned into random variables. This user-friendly method opens up more possibilities in terms of latent manipulation, embedding techniques, and many other potential uses.

In this study, a novel method is proposed to estimate surface-spectral reflectance from camera responses that combines model-based and training-based approaches. An imaging system is modeled using the spectral sensitivity functions of an RGB camera, spectral power distributions of multiple light sources, unknown surface-spectral reflectance, additive noise, and a gain parameter. The estimation procedure comprises two main stages: (1) selecting the local optimal reflectance dataset from a reflectance database and (2) determining the best estimate by applying a neural network to the local optimal dataset only. In stage (1), the camera responses are predicted for the respective reflectances in the database, and the optimal candidates are selected in the order of lowest prediction error. In stage (2), most reflectance training data are obtained by a convex linear combination of local optimal data using weighting coefficients based on random numbers. A feed-forward neural network with one hidden layer is used to map the observation space onto the spectral reflectance space. In addition, the reflectance estimation is repeated by generating multiple sets of random numbers, and the median of a set of estimated reflectances is determined as the final estimate of the reflectance. Experimental results show that the estimation accuracies exceed those of other methods.

This study investigates the effectiveness of a text summarization method applied to open-ended student evaluations at the Hellenic Open University, aiming to improve the analysis of qualitative feedback from online educational surveys. To address the challenges of processing large volumes of student feedback, an automated summarization technique utilizing advancements in Natural Language Processing (NLP) and text mining is proposed. Using the TextRank and the Walktrap algorithms, student comments on positive aspects, study challenges, and improvement suggestions were analyzed. The analysis revealed that while some students expressed satisfaction with tutor-student interactions and the organization of educational material, there were also negative comments about outdated content in some modules and scheduling issues. The findings highlight the importance of qualitative feedback for education quality, providing actionable insights for improving curricula and teaching effectiveness. This research responds to the growing need for effective qualitative data analysis in higher education and contributes to ongoing discussions about student satisfaction in distance learning environments. By effectively summarizing open-ended responses, university staff can better understand student experiences and make informed decisions to enhance the educational process.

Modern search engines encounter a significant challenge when it comes to handling duplicate and nearly identical web pages, particularly during the indexing process for vast amounts of web content. This issue can lead to slow search results and increased costs due to the accumulation of storage space necessary for storing indexes. To tackle this issue, different techniques have been proposed to find similar websites. However, it has long been a challenge in research to distinguish between web pages. In the current study, sentence-level features i.e., hashcode and thresholding are used to determine the nearly identical web pages. We employ an adaptive threshold that enables the application of our model in both large- and small-scale settings. The benchmark datasets consisting of Shakespeare’s collections, free text, job descriptions, and Reuters-21578 are used to test the proposed approach. With an accuracy of 0.99 and an F1-score of 0.97, the proposed technique outperforms existing methods.

This study explores the optimization of the admission process at the Escuela Colombiana de Ingeniería Julio Garavito through data anal- ysis. By integrating advanced tools like Power BI, Python Flask, and data mining techniques, a model has been developed to improve student selection and retention, enabling more informed and effective decisions. The results indicate that applying data science not only facilitates efficient data management but also promotes more inclusive and equitable educational poli- cies. This pioneering approach in the field of higher education in Colombia offers a frame- work for future research and technological de- velopments, highlighting the vital importance of data science in improving educational and administrative processes.

This study examines a new approach to hybdrid neuromorphic devices by studying the impact of omeprazole-proteinoid complexes on Izhikevich neurone models. We investigate the influence of these metabolic structures on five specific patterns of neuronal firing: accommodation, chattering, triggered spiking, phasic spiking, and tonic spiking. By combining omeprazole, a proton pump inhibitor, with proteinoids, we create a unique substrate that interfaces with neuromorphic models. The Izhikevich neurone model is used because it is computationally efficient and can accurately simulate various behaviours of cortical neurones. The results of our simulations show that omeprazole-proteinoid complexes have the ability to affect neuronal dynamics in different ways. This suggests that they could be used as adjustable components in bio-inspired computer systems. We have noticed a notable alteration in the frequency of spikes, patterns of bursts, and rates of adaptation, especially in chattering and triggered spiking behaviours. The findings indicate that omeprazole-proteinoid complexes have the potential to serve as adaptable elements in neuromorphic systems, presenting novel opportunities for information processing and computation that have origins in neurobiological principles. This study makes a valuable contribution to the expanding field of biochemical neuromorphic devices and establishes a basis for the development of hybrid bio-synthetic computational systems.

The current surge in the deployment of web applications underscores the need to consider users' individual preferences in order to enhance their experience. In response to this, an innovative approach is emerging that focuses on the detailed analysis of interaction data captured by web browsers. This data, which includes metrics such as the number of mouse clicks, keystrokes, and navigation patterns, offers insights into user behaviour and preferences. By leveraging this information, developers can achieve a higher degree of personalization in web applications, particularly in the context of interactive elements such as online games. This paper presents the WebTraceSense project, which aims to pioneer this approach by developing a framework that encompasses a backend and frontend, advanced visualization modules, a DevOps cycle, and the integration of AI and statistical methods. The backend of this framework will be responsible for securely collecting, storing, and processing vast amounts of interaction data from various websites. The frontend will provide a user-friendly interface that allows developers to easily access and utilize the platform’s capabilities. One of the key components of this framework is the visualization modules, which will enable developers to monitor, analyse, and interpret user interactions in real-time, facilitating more informed decisions about user interface design and functionality. Furthermore, the WebTraceSense framework incorporates a DevOps cycle to ensure continuous integration and delivery, thereby promoting agile development practices and enhancing the overall efficiency of the development process. Moreover, the integration of AI methods and statistical techniques will be a cornerstone of this framework. By applying machine learning algorithms and statistical analysis, the platform will not only personalize user experiences based on historical interaction data but also infer new user behaviours and predict future preferences. In order to validate the proposed components, a case study was conducted which demonstrated the usefulness of the WebTraceSense framework in the creation of visualizations based on an existing dataset.

The exponential growth of multimodal content across social media platforms, comprising text, images, audio, and video, has catalyzed substantial interest in artificial intelligence, particularly in multi-modal sentiment analysis (MSA). This study presents a comprehensive survey of 30 research papers published between 2020 and 2024 by eminent publishers such as Elsevier, ACM, IEEE, Springer, and others indexed in Google Scholar. Our analysis primarily focuses on exploring multimodal fusion techniques and features, with specific emphasis on the integration of text and image data. Additionally, the article offers an overview of the evolution, definition, and historical context of MSA. It delves into the current challenges and potential advantages of MSA, investigating recent datasets and sophisticated models. Furthermore, the study provides insights into prospective research directions. Notably, this review offers valuable recommendations for advancing research and developing more robust MSA models, thus serving as a valuable resource for both academic and industry researchers engaged in this burgeoning field.

Real-time image processing is crucial in applications such as video surveillance, diagnostic medicine, and autonomous vehicle systems. Parallel computing is essential to address the demands of real-time processing, but challenges persist in its practical implementation. This review analyzes parallel computing techniques applied to real-time image processing, examining parallel architectures and algorithms, identifying effective applications, and evaluating challenges and limitations. The results of this study will contribute to the development of more efficient solutions for real-time image processing. Keywords: Parallel computing, real-time image processing, video surveillance, diagnostic medicine, autonomous vehicle systems.

With the rapid development of Intelligent Transportation Systems (ITS), vehicle type classification, as a key link in Automatic Toll Collection systems (ATC), is of great significance in improving traffic efficiency and reducing economic losses. This study proposes an intelligent vehicle classification system based on deep learning and multi-sensor data fusion to address the accuracy issues existing in vehicle classification methods based on optical sensors (OS) and human observers. The system significantly improves the accuracy and robustness of vehicle classification by combining deep Convolutional Neural Networks (CNN), LiDAR sensors, and machine learning algorithms. We first constructed a large-scale annotated dataset containing multiple vehicle types and complex traffic scenes to improve our model's capability to identify different vehicle characteristics. Next, CNN models based on different architectures were designed to extract global and local features of the vehicle, respectively. In addition, the LiDAR sensor was used to achieve the spatial structure architectures of the vehicle and combined with the output of the CNN model to improve classification performance under occlusion and complex scenes.

With the emergence of the Internet and WWW has become a comprehensive source of information for the extraction of meaningful information has become a significant challenge in the past decade. Furthermore, the available information is classified in unstructured, structured, and semi-structured forms. Numerous amount of information on the web is also characterized in an unstructured or semi-structured format. This usually extracts the potential useful information from these multiple forms and has been considered a leading area of research in this modern era. The authors presented web content mining as a subcategory of web mining that focuses on important extracting patterns from the contexts available in the documents on the web. Hence, this paper focuses on the multiple content mining concepts, tools, and techniques implemented on the documents available on WWW.

In order to reduce the environmental impact of energy enterprises, it is important to promptly identify cases of possible changes in the quality of wastewater generated at power plants, that is cases of exceeding the maximum permissible concentrations of pollutants in wastewater. The goal of the method for detecting complex anomalies in multidimensional time series obtained from smart energy station’s sensor channels is to increase the accuracy of detecting pollution levels in industrial wastewater. To achieve this goal, the following tasks were solved: methods for detecting time series anomalies were analyzed, the method for detecting complex anomalies was developed, software implementation of the algorithm was carried out and experiments were conducted. The developed method is proposed to be used in an smart energy monitoring system.

Nowadays and in the web era, there is a huge amount of information available due to automatically and easily generated websites. This information has many shared opinions from people toward different entities. Over the last decade there was a significant huge interest to determine the sentiment of any type of text especially on twitter. Twitter provides unstructured text that has many misspelling words, slang words and shortened forms. More complexity and challenges have come to the sentiment analysis researchers in the context of twitter. In this paper we conducted a literature review of the recent research of Twitter sentiment analysis on different languages. After that, we investigated challenges related to twitter sentiment analysis of Arabic language. Then we found a new solution for Sentiment analysis of Arabic twitter. So, we designed the main component of the proposed system and presented its algorithm. Finally, we performed many experiments under two kinds of datasets. The system achieves highest accuracy and shows many important results..

Big Data and blockchain technology are coming together to revolutionize how decisions are made in a decentralized way across various industries. This review looks at how these technologies, along with distributed systems, can improve data security, transparency, and real-time processing, making decision-making more efficient and informed. The integration enhances data security with unchangeable records, increases transparency and traceability, and supports real-time data analysis. However, there are challenges to overcome, including scalability, data privacy, interoperability, regulatory compliance, and high costs. By examining case studies such as Estonia's healthcare system, IBM and Walmart's Food Trust, and the Brooklyn Microgrid project, we explore the practical applications and benefits of combining Big Data with blockchain. Despite these hurdles, the review finds that the ongoing advancements and innovative solutions in these technologies offer significant promise. They are set to drive the adoption and effectiveness of decentralized decision-making, ultimately leading to better efficiency and outcomes across multiple sectors.

In the future, smart cities will provide key services including seamless communication, intelligent transport systems, advanced healthcare platforms, urban and infrastructure management, and digital services for local and regional government. Therefore, a new service and networking paradigm, called the Intelligent Edge Environment, has been specified. and is known as the Intelligent Edge Environment. As a key part of this system, a new secure service ecosystem must be developed to provide the secure realtime movement of services on different High-Performance Edge Cloud Systems. This paper explores these issues by introducing the following mechanisms: the Resource Allocation Algorithm, the Resource Allocation Secure Protocol and finally the Secure Service Protocols. These systems were integrated into the Basic Capabilities System Library and a multithreaded FUSE client connected to the Service Management Framework. Docker was used as a migration mechanism. A prototype was developed and implemented using a FUSE-Network Memory System in which the Network Memory Server was migrated as users move around. The result shows that this approach was safe and could be used to develop new applications and services for smart cities.

The concept of Digital Twins has been in the field for a long time, constantly challenging the specification, modeling, design, implementation, and exploitation of complex cyber-physical systems. Despite the various foundations, standards, and platforms in Systems Engineering, there are ongoing challenges with Verification and Validation methodology. This study aims to establish a generic framework that addresses the various aspects of Digital Twinning. The multifaceted nature of the problem requires raising the abstraction level in both the Real (Actual) and Virtual domains, effective dissemination of information resources, and a design inspired by verification and validation. The proposed framework combines the Quintuple Helix model with the Problem and Operational Domains of a Real (Actual) Twin, the Solution and Implementation Domains of a Virtual Twin, and the Execution Domain as the bridge that links them. Verification and Validation dimensions follow the Meta Object Facility abstraction layers (Instance, Model, Meta-model, and Meta-meta-model) mapping over five Helices. Embedding the complexity reduction mechanisms in the proposed framework builds a suite for extendible and verifiable digital twinning in simulation and real-time scenarios.

The 6TiSCH protocol (IEEE 802.15.4e) is crucial for the Industrial Internet of Things (IIoT), utilizing a time-slotted channel hopping (TSCH) mode based on node distribution. In our experiment, we explored node position clustering and adjusted the capacity of existing cells in congested areas to understand traffic patterns and optimize cell selection for TSCH resource allocation, particularly in slot frames. Efficient cell allocation prevents packet loss, manages congestion, and enhances data transmission reliability. Node clustering increases cell usage efficiency and reduces communication latency between nodes, with each cell allocation tailored to its traffic needs through the sink node from the clustering result. We evaluated the clustering method using the K-means algorithm through experiments using the 6TiSCH simulator. Additionally, we considered using the routing protocol for low power and lossy networks (RPL) as a comparison, such as OF0 and MRHOF, as the objective function to assess clustering results and their impact on throughput and packet delivery. Our method significantly improved average performance metrics: under the OF0 routing protocol, we achieved a 30.01% latency reduction, 15.95% faster joining time, 8% higher packet delivery ratio, and 13.82% throughput increase. Similarly, with the MRHOF routing protocol, we observed a 12.34% improvement in packet delivery ratio, 21.06% latency reduction, 12.68% faster joining time, and 25.97% higher throughput speed.

The study of Internet of Vehicle (IoV) based on Fog Computing (FC) and Artificial Intelligent (AI) has attracted more and more attention. However, there are still many problems require to investigate such as time-critical, scalability, load-balancing, energy consumption, and so on. Focusing on these problems, we proposed an AI-based Vehicle-to-Everything (V2X) model for tasks and resource offloading model for IoVs network, which ensures reliable low-latency communication efficient tasks offloading in IoV network by using Software Defined Vehicular based FC (SDV-F) architecture. To fit to time-critical data transmission task distribution, the proposed model reduces unnecessary task allocation at the fog computing layer by proposing an AI-based task-allocation algorithm in IoV layer to implement task allocation of each vehicle. By applying AI technologies of Reinforcement Learning (RL), Markov decision process, and Deep Learning (DL), the proposed model intelligently makes decision on maximizing resource utilization at the fog layer, and minimizing the average end-to-end delay of time-critical IoV applications. The experiment demonstrates the proposed model can efficiently distribute the fog layer tasks while minimizing the delay.

In the dynamic realm of HPC (High-performance computing) and cloud-native applications, ensuring optimal network performance for Kubernetes Container Network Interfaces (CNIs) is critical. Traditional manual methods for evaluating network bandwidth and latency are prone to errors, time-consuming, and lack consistency. This paper introduces a novel approach that leverages Ansible to automate and coordinate network performance tests across diverse CNIs, performance profiles, and configurations. By automating these processes, we eliminate the potential for human errors, ensure the ability to replicate the process, and significantly reduce the time required for comprehensive testing. The use of Ansible playbooks facilitates the efficient and scalable deployment, configuration, and execution of performance tests, enabling comprehensive and standardized benchmarking across various environments. The set of Ansible playbooks, which we will make available online, has a significant real-world impact by providing DevOps teams with robust and reliable tools for consistently monitoring and enhancing network performance. This, in turn, enhances the stability and efficiency of cloud-native applications, accelerates the development cycle, and ensures that Kubernetes-based infrastructures can meet the demanding performance requirements of modern applications.

The digital age has ushered in unprecedented connectivity and convenience, but it has also given rise to escalating cyber threats and privacy concerns. This study examines the intricate balance between technological advancement and personal privacy in the face of evolving cyber risks. A comprehensive literature review was conducted, analyzing peer-reviewed articles, government reports, and industry white papers from the past decade. Additionally, case studies of major data breaches and privacy violations were examined. Surveys and interviews with cybersecurity experts, policymakers, and privacy advocates were conducted to gather diverse perspectives. The research reveals a significant increase in both the frequency and sophistication of cyber-attacks, coupled with a growing public awareness of privacy issues. However, there is a notable disconnect between individuals' stated privacy concerns and their online behaviors. Regulatory efforts to protect privacy often lag behind technological advancements and cyber threats. Maintaining equilibrium between technological progress and privacy protection requires a multifaceted approach involving enhanced cybersecurity measures, updated regulations, and improved digital literacy. The study underscores the need for ongoing collaboration between government, industry, and academia to address this complex challenge.

This study develops a hybrid machine learning (ML) algorithm integrated with IoT technology to improve the accuracy and efficiency of soil monitoring and tomato crop disease prediction in Anakapalle, a south Indian station. An IoT device collected one-minute and critical soil parameters—humidity, temperature, pH values, nitrogen (N), phosphorus (P), and potassium (K)—essential for assessing soil health and optimizing crop growth. Kendall's correlations were computed to rank these parameters for utilization in hybrid ML techniques. Various ML algorithms including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Tree (DT), Random Forest (RF), and Logistic Regression (LR) were evaluated. A novel hybrid algorithm, 'Bayesian Optimization with KNN', was introduced to combine multiple ML techniques and enhance predictive performance. The hybrid algorithm demonstrated superior results with 95% accuracy, precision, and recall, and an F1 score of 94%, while individual ML algorithms achieved varying results: KNN (80% accuracy), SVM (82%), DT (77%), RF (80%), and LR (81%) with differing precision, recall, and F1 scores. This hybrid ML approach proved highly effective in predicting tomato crop diseases in natural environments, underscoring the synergistic benefits of IoT and advanced ML techniques in optimizing agricultural practices.

The exponential growth and widespread adoption of Internet of Things (IoT) devices have introduced many vulnerabilities. Attackers frequently exploit these flaws, necessitating advanced technological approaches to protect against emerging cyber threats. This study introduces a novel approach utilizing hardware honeypots as an additional defensive layer against hardware vulnerabilities, particularly hardware trojans (HTs). HTs pose significant risks to the security of modern integrated circuits (ICs), potentially causing operational failures, denial of service, or data leakage through intentional modifications. The proposed system was implemented on a Raspberry Pi and tested on an emulated HT circuit using a Field-Programmable Gate Array (FPGA). This approach leverages hardware honeypots to detect and mitigate HTs in IoT devices. The results demonstrate that the system effectively detects and mitigates HTs without imposing additional complexity on the IoT devices. The trojan-agnostic solution offers full customization to meet specific security needs, providing a flexible and robust layer of security. The findings provide valuable insights into enhancing the security of IoT devices against hardware-based cyber threats, thereby contributing to the overall resilience of IoT networks. This innovative approach offers a promising solution to address the growing security challenges in IoT environments.

This study delves into the impact of artificial intelligence on students’ learning.The paper pioneers the use of kmeans classification to reduce the dimensionality of features before the classification process, which minimizes redundant information and computational overhead. This step is not commonly found in prior research.Firstly, a random forest model is established with “whether AI assistance was used to complete the paper” as the output, and various features as inputs. The analysis of the predictive accuracy when changing input features reveals the degree of influence of each feature on using AI to complete the paper. After feature selection, the remaining 6 features can still effectively predict the use of AI to complete the paper, indicating the representativeness of the extracted indicators. Subsequently, the PCA-K-means algorithm is employed to classify the use of artificial intelligence. PCA algorithm is used for dimensionality reduction of the extracted features to better characterize students’ use of AI. Three representative variables are selected, and the contribution of each feature is computed based on the factor loading matrix. Finally, the K-means algorithm is used to classify students based on the three dimensional features, showing that students can be effectively classified into 2 categories. The results indicate that the majority of students support the use of AI technology to enhance their abilities, although some students may only intend to use AI to cope with exams and similar tasks.

Globalization is a basic feature of contemporary digital society related to increasing level of informatization, electroniztion and communications through the global network and share different information. Regardless of the many advantages of the digital age, related to the intellectualization of various activities and objects (e-governance, e-health, social computing, smart home, smart city, etc.), the need for secure protection of users' privacy should not be overlooked. In this reason, the goal of the article is to determine the specific features of the main components of the globalization and the impact on the privacy and data protection. Based on the analysis of possible impacts the main recommendation for adequate data security and privacy protection are determined.

The digital world is increasingly invading our reality, which leads to the formation of a significant reflection of the processes and activities taking place in the smart city. Such activities include well-known urban events, celebrations, and those with a very local character. Due to the mass occurrence, events have a comparable influence on the formation of the spirit and the urban atmosphere. This work presents an enhanced semantic version of the ConvTree algorithm - SemConvTree. It allows considering the semantic component of the data obtained by using semi-supervised learning of topic modeling ensemble (consisting of improved models BERTopic, TSB-ARTM, SBert-Zero-Shot). We also present an improved event search algorithm based on both statistical evaluations and semantic analysis of posts. This algorithm allows fine-tuning the mechanism of discovering the required entities with the specified particularity (such as a particular topic). Experimental studies were conducted within the area of New York City. They showed an improvement in the detection of posts devoted to events (about 40% higher f1-score) due to the accurate handling of events of different scales. These results lead in the long term to talk about the potential perspective in creating a semantic platform for the analysis and monitoring of urban events in the future.

The growing interest in environmental sustainability issues and, at the same time, the advantages offered by blockchain technology have strong connections between these two topics. This study explores the application of blockchain technology across various environmental domains, such as air quality, climate change impacts, and resource management. The research utilised a dual approach, combining a bibliometric analysis with VOSviewer and a topic analysis using BERT models to assess the discourse within both scientific literature extracted from Scopus and practical blockchain projects obtained from GitHub. The findings reveal that food security, energy, and sustainable agriculture are predominant topics in academic discussions, with a noticeable increase in focus from 2017 onwards. Practical projects are focused on transparent tracking and decentralised management. The overlap between academic and practical spheres is evident in the shared focus on energy and environmental management, demonstrating blockchain’s growing role in addressing global environmental challenges. The study underscores the importance of integrating theoretical research with practical implementations to harness blockchain’s full potential in promoting sustainable environmental practices.

This study explores advanced feature engineering and semantic enrichment methods to enhance text classification, focusing on detecting figurative language in tweets. The novel features introduced, Syno\_Lower\_Mean and Syn\_Mean, measure the use of uncommon synonyms and the mean frequency of synonyms, capturing semantic richness crucial for detecting figurative expressions. Using resources like SenticNet and Framester, we enrich our feature set with sentiment and frame semantic information. Our approach includes extensive data preprocessing, sophisticated feature selection, and implementing various classification models, such as SVM, KNN, Logistic Regression, Decision Trees, Random Forest, BERT, and LSTM networks. We rigorously evaluate each model's performance to assess the effectiveness of our features and enrichment methods. Putting emphasis on model explainability, we use decision tree analysis, feature importance analysis, and the TREPAN algorithm to approximate SVM decisions. Although we focus on figurative language detection, our methods have broader implications for various NLP text classification tasks. Our findings demonstrate significant improvements in classification accuracy and interpretability through innovative feature design and dataset enrichment.

This paper examines the use of multisensory virtual reality (VR) as a novel approach in psychological therapy for autobiographical memory retrieval with benefits for cognitive enhancement, stress reduction etc. The research in this paper was done under Romanian Arut Research Grant no. 27/09/10/2023 ”Intelligent VR system for treating autobiographical/episodic memory deficits".  By simulating realistic multisensory experiences, VR technology offers an immersive environment that surpasses traditional therapeutic methods in effectiveness. Previous studies demonstrate improved outcomes in treating various psychological conditions (affective disorders and PTSD, specific phobias and age-related cognitive decline). Technological advancements in VR, such as olfactory integration cand contribute to the realism and therapeutic potential of these environments, the integration of various physical stimuli with VR holds promising potential psychological therapies and highlighting the need for further interdisciplinary research. In this pilot study we tested the efficacy of a new system for triggering autobiographical memory retrieval. For this we used images combined with odors in a congruent manner and offering participants the chance to interact with the VR environment by using 2 virtual hands. We evaluated the efficacy of this system using qualitative methods with emphasis on the evaluation of the emotions associated with memory recollection and the ease of triggering memories. All participants in our pilot study experienced intense emotions related to childhood or adolescence and the pleasant feelings they had during the experiment persisted even after it ended. This is an advancement to what exists currently and original research elements for our paper.

This paper presents an innovative approach to dimensionality reduction and feature extraction in high-dimensional datasets, with a specific application focus on wood surface defect detection. The proposed framework integrates sparse modeling techniques, particularly Lasso and proximal gradient methods, into a comprehensive pipeline for efficient and interpretable feature selection. Leveraging pre-trained models such as VGG19 and incorporating anomaly detection methods like Isolation Forest and Local Outlier Factor, our methodology addresses the challenge of extracting meaningful features from complex datasets. Evaluation metrics such as accuracy and F1 score, alongside visualizations, are employed to assess the performance of the sparse modeling techniques. Through this work, we aim to advance the understanding and application of sparse modeling in machine learning, particularly in the context of wood surface defect detection.

For the first time, mathematical models were obtained for evaluating biomedical images using fuzzy set methods on the basis of expert knowledge bases, which made it possible to carry out complex qualitative diagnostics and increase the reliability and efficiency of diagnosis, to form a methodology for analyzing biomedical images based on the fuzzy set apparatus, which allowed to more fully assess the level of the disease for glaucoma. Aspects of practical implementation of the optical-electronic system of biomedical information processing are considered. An algorithm and an optical-electronic system of biomedical image analysis are proposed, which are used to increase the informativeness and reliability of diagnosing eye pathologies, in particular, glaucoma.

The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the complexity and volume of this data present substantial challenges in data modeling and analysis, which have been tamed with approaches spanning time series modeling to deep learning techniques. The latest frontier in this domain is the adoption of Large Language Models (LLMs), such as GPT-4 and Llama, for data analysis, modeling, understanding, and generation of human behavior through the lens of wearable sensor data. This survey explores current trends and challenges in applying LLMs for sensor-based human activity recognition and behavior modeling. We discuss the nature of wearable sensors data, the capabilities and limitations of LLMs to model them and their integration with traditional machine learning techniques. We also identify key challenges, including data quality, computational requirements, interpretability, and privacy concerns. By examining case studies and successful applications, we highlight the potential of LLMs in enhancing the analysis and interpretation of wearable sensors data. Finally, we propose future directions for research, emphasizing the need for improved preprocessing techniques, more efficient and scalable models, and interdisciplinary collaboration. This survey aims to provide a comprehensive overview of the intersection between wearable sensors data and LLMs, offering insights into the current state and future prospects of this emerging field.

In this article, we propose a machine learning based fine-grained vehicle classification method VehiClassNet, which effectively solves the challenges of precise vehicle recognition and classification in intelligent transportation systems by combining multi-scale feature extraction, cross modal fusion, and attention mechanisms. Our model demonstrated excellent performance on the Stanford Cars-196 dataset. The innovation of this study lies in its advanced multi-scale feature extraction, cross modal fusion, and attention mechanism. It not only improves classification accuracy, but also lays the foundation for further research on intelligent transportation systems and autonomous vehicle technology.