Search Results (3,751)

The rapid growth of data and the increasing complexity of modern networks have driven the demand for intelligent solutions in the information and communications technology (ICT) domain. Machine learning (ML) has emerged as a powerful tool, enabling more adaptive, efficient, and scalable systems in this field. This article presents a comprehensive survey on the application of ML techniques in ICT, covering key areas such as network optimization, resource allocation, anomaly detection, and security. Specifically, we review the effectiveness of different ML models across ICT subdomains and assess how ML integration enhances crucial performance metrics, including operational efficiency, scalability, and security. Lastly, we highlight the challenges and future directions that are critical for the continued advancement of ML-driven innovations in ICT. Full article

The effective length factor (ELF) of bridge piers, a critical design parameter, is determined by solving the transcendental equation governing stability. Efficient and accurate solutions to these equations under various constraints are essential for automating bridge design software. In this paper, the bridge pier is simplified as an elastically restrained column based on the Timoshenko beam model, and the pier stability equation under general elastic constraints considering shear deformation is derived. By analyzing the distribution patterns of the solutions to the transcendental equations with and without considering shear deformation, a novel two-stage Adaptive Sequential Root Search Method based on bisection algorithm (ASRSBM2s) is proposed to calculate the ELF. In the first stage, the smallest positive root of the transcendental equation without considering shear deformation is first calculated, and the obtained positive root is used to restrict the solution domain of the transcendental equation considering shear deformation in the second stage. Compared with the results of the finite element method (FEM), the proposed algorithm can accurately determine the correct roots of the transcendental equation for various bridge scenarios, and the maximum relative error of the calculated ELF of bridge piers is below 2.5%. Full article

With the development and widespread application of network information, new technologies led by 5G are emerging, resulting in an increasingly complex network security environment and more diverse attack methods. Unlike traditional networks, 5G networks feature higher connection density, faster data transmission speeds, and lower latency, which are widely applied in scenarios such as smart cities, the Internet of Things, and autonomous driving. The vast amounts of sensitive data generated by these applications become primary targets during the processes of collection and secure sharing, and unauthorized access or tampering could lead to severe data breaches and integrity issues. However, as 5G networks extensively employ encryption technologies to protect data transmission, attackers can hide malicious content within encrypted communication, rendering traditional content-based traffic detection methods ineffective for identifying malicious encrypted traffic. To address this challenge, this paper proposes a malicious encrypted traffic detection method based on reconstructive domain adaptation and adversarial hybrid neural networks. The proposed method integrates generative adversarial networks with ResNet, ResNeXt, and DenseNet to construct an adversarial hybrid neural network, aiming to tackle the challenges of encrypted traffic detection. On this basis, a reconstructive domain adaptation module is introduced to reduce the distribution discrepancy between the source domain and the target domain, thereby enhancing cross-domain detection capabilities. By preprocessing traffic data from public datasets, the proposed method is capable of extracting deep features from encrypted traffic without the need for decryption. The generator utilizes the adversarial hybrid neural network module to generate realistic malicious encrypted traffic samples, while the discriminator achieves sample classification through high-dimensional feature extraction. Additionally, the domain classifier within the reconstructive domain adaptation module further improves the model’s stability and generalization across different network environments and time periods. Experimental results demonstrate that the proposed method significantly improves the accuracy and efficiency of malicious encrypted traffic detection in 5G network environments, effectively enhancing the detection performance of malicious traffic in 5G networks. Full article

Organizations are questioning the effectiveness of one-size-fits-all leadership approaches in managing and developing employees. This article proposes that leaders can support employees in crafting their work experience. By integrating the behavioral domains conducive to job crafting, the Michelangelo model and the leadership for organizational adaptability framework, we introduce the crafting leadership model—a behavioral style where leaders adapt their behaviors to employees’ characteristics to co-construct their fit at work and foster the development of both people and organizations—providing a conceptual foundation for identifying its key behavioral facets and highlighting its unique value compared to existing leadership styles. We developed and validated a questionnaire using structural equation modeling. In Study 1 (N = 2137) and Study 2 (N = 1507), the questionnaire was tested for factor structure, reliability, discriminant, and predictive validity. The results supported a higher-order structure of crafting leadership, underlying three distinct behavioral facets: tailoring, person–organization alignment, and catalyst. Results revealed that crafting leadership (a) was distinct from strength-based, servant, and transformational leadership and (b) correlated with and explained additional variance in employee outcomes, namely needs–supplies fit, meaningful work, job-crafting behaviors, work engagement, and turnover intentions. Implications for research and practice are discussed. Full article

Critical information is frequently lost when individuals with intellectual/developmental disabilities (I/DD) and co-occurring communication challenges transition from one educational/clinical setting to another. To encourage a seamless transition, speech–language pathologists (SLPs) developed This is Me (TiME), a customizable, digital transition tool designed to help students/patients share personal information and advocate for needed support in their new settings. Researchers conducted a content analysis of 92 TiME transcripts to determine how SLPs used the tool across school and inpatient contexts. Findings indicate the most common content domains included in TiME were personal information (e.g., strengths, hobbies, and preferences) and information about communication, learning styles, and behavior/emotion regulation. While school and inpatient units demonstrated similar patterns of domain use, TiME created in an inpatient context contained more information about behavior plans/supports and were almost twice as long on average. They also included more information about safety and diagnoses/medical needs and less information about self-advocacy strategies than TiME created in school contexts, reflecting the very different settings within which they were created. These findings suggest that TiME offers a solution that can readily be adapted to meet the needs of varied groups of individuals with disabilities as well as different audiences. Full article

Parameter tuning based adapter methods have achieved notable success in vision-language models (VLMs). However, they face challenges in scenarios with insufficient training samples or limited resources. While leveraging image modality caching and retrieval techniques can reduce resource requirements, these approaches often overlook the significance of textual modality and cross-modal cues in VLMs. To address this, we propose a Conditional Cross-Modal learning model, which is abbreviated as CoCM. CoCM builds separate cache models for both the text and image modalities and embedding textual knowledge conditioned on image information. It dynamically adjusts the cross-modal fusion affinity ratio and disentangles similarity measures across different modalities. Additionally, CoCM incorporates intra-batch image similarity loss as a regularization term to identify hard samples and enhance fine-grained classification performance. CoCM surpasses existing methods in terms of accuracy, generalization ability, and efficiency, achieving a 0.28% accuracy improvement over XMAdapter across 11 datasets and demonstrating 44.79% generalization performance on four cross-domain datasets. Full article

As an interdisciplinary field of natural language processing and computer vision, Visual Question Answering (VQA) has emerged as a prominent research focus in artificial intelligence. The core of the VQA task is to combine natural language understanding and image analysis to infer answers by extracting meaningful features from textual and visual inputs. However, most current models struggle to fully capture the deep semantic relationships between images and text owing to their limited capacity to comprehend feature interactions, which constrains their performance. To address these challenges, this paper proposes an innovative Trilinear Multigranularity and Multimodal Adaptive Fusion algorithm (TriMMF) that is designed to improve the efficiency of multimodal feature extraction and fusion in VQA tasks. Specifically, the TriMMF consists of three key modules: (1) an Answer Generation Module, which generates candidate answers by extracting fused features and leveraging question features to focus on critical regions within the image; (2) a Fine-grained and Coarse-grained Interaction Module, which achieves multimodal interaction between question and image features at different granularities and incorporates implicit answer information to capture complex multimodal correlations; and (3) an Adaptive Weight Fusion Module, which selectively integrates coarse-grained and fine-grained interaction features based on task requirements, thereby enhancing the model’s robustness and generalization capability. Experimental results demonstrate that the proposed TriMMF significantly outperforms existing methods on the VQA v1.0 and VQA v2.0 datasets, achieving state-of-the-art performance in question–answer accuracy. These findings indicate that the TriMMF effectively captures the deep semantic associations between images and text. The proposed approach provides new insights into multimodal interaction and fusion research, combining domain adaptation techniques to address a broader range of cross-domain visual question answering tasks. Full article

Background/Objectives: Drug development involves multiple stages, spanning from initial discovery to clinical trials. This intricate process entails understanding disease mechanisms, identifying potential drug targets, and evaluating the efficacy and safety of candidate drugs. Clinical trials are designed to assess the effects of drugs on humans, focusing on determining safety profiles, appropriate modes of administration, and comparative efficacy against placebos. Notably, neuroscience drug development encounters distinct challenges, including the complex nature of diseases, limitations imposed by the blood–brain barrier, the absence of reliable predictive preclinical models, and regulatory hurdles. Ethical and safety considerations are pivotal due to the potential cognitive and motor effects of CNS-active drugs. Methods: Our manuscript outlines the procedures for CNS clinical trials and highlights the key elements of study design, methodological considerations, and ethical frameworks. To achieve our objectives, we considered the official websites of regulatory authorities, the EQUATOR network, and recent publications in the field. The paper includes key elements such as criteria for subject selection, methods of evaluation, variable analysis, and statistical methodology approaches. Results: We want to furnish a concise and comprehensive guide tailored to individuals new to CNS clinical trials, providing foundational elements necessary for the design and execution of such trials. The manuscript seeks to outline sources of relevant materials and elucidate adaptability, particularly in instances where sponsors may be absent. Conclusions: By meeting the needs of less-experienced researchers or those with limited resources, the intention is to facilitate an understanding of the intricate nature of the process and offer guidance on appropriately navigating its complexities. It is essential to note that this manuscript does not aim to be exhaustive but endeavors to serve as a structured checklist. Through its approach, the manuscript aspires to offer guidance and support to individuals navigating the challenges inherent in this intricate domain. Full article

Unmanned Aerial Vehicles (UAVs) have transformed the process of data collection and analysis in a variety of research disciplines, delivering unparalleled adaptability and efficacy. This paper presents a thorough examination of UAV datasets, emphasizing their wide range of applications and progress. UAV datasets consist of various types of data, such as satellite imagery, images captured by drones, and videos. These datasets can be categorized as either unimodal or multimodal, offering a wide range of detailed and comprehensive information. These datasets play a crucial role in disaster damage assessment, aerial surveillance, object recognition, and tracking. They facilitate the development of sophisticated models for tasks like semantic segmentation, pose estimation, vehicle re-identification, and gesture recognition. By leveraging UAV datasets, researchers can significantly enhance the capabilities of computer vision models, thereby advancing technology and improving our understanding of complex, dynamic environments from an aerial perspective. This review aims to encapsulate the multifaceted utility of UAV datasets, emphasizing their pivotal role in driving innovation and practical applications in multiple domains. Full article

The global pursuit of carbon neutrality requires the reduction of carbon emissions in logistics and distribution. The integration of electric vehicles (EVs) and drones in a collaborative delivery model revolutionizes last-mile delivery by significantly reducing operating costs and enhancing delivery efficiency while supporting environmental objectives. This paper presents a cost-minimization model that addresses transportation, energy, and carbon trade costs within a cap-and-trade framework. We develop a multi-depot mixed fleet, including electric and fuel vehicles, and a drone collaborative delivery routing optimization model. This model incorporates key factors such as nonlinear EV charging times, time-dependent travel conditions, and energy consumption. We propose an adaptive large neighborhood search algorithm integrating spatiotemporal distance (ALNS-STD) to solve this complex model. This algorithm introduces five domain-specific operators and an adaptive adjustment mechanism to improve solution quality and efficiency. Our computational experiments demonstrate the effectiveness of the ALNS-STD, showing its ability to optimize routes by accounting for both spatial and temporal factors. Furthermore, we analyze the influence of charging station distribution and carbon trading mechanisms on overall delivery costs and route planning, underscoring the global significance of our findings. Full article

Building on a previously developed partially synthetic data generation algorithm utilizing data visualization techniques, this study extends the novel algorithm to generate fully synthetic tabular healthcare data. In this enhanced form, the algorithm serves as an alternative to conventional methods based on Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). By iteratively applying the original methodology, the adapted algorithm employs UMAP (Uniform Manifold Approximation and Projection), a dimensionality reduction technique, to validate generated samples through low-dimensional clustering. This approach has been successfully applied to three healthcare domains: prostate cancer, breast cancer, and cardiovascular disease. The generated synthetic data have been rigorously evaluated for fidelity and utility. Results show that the UMAP-based algorithm outperforms GAN- and VAE-based generation methods across different scenarios. In fidelity assessments, it achieved smaller maximum distances between the cumulative distribution functions of real and synthetic data for different attributes. In utility evaluations, the UMAP-based synthetic datasets enhanced machine learning model performance, particularly in classification tasks. In conclusion, this method represents a robust solution for generating secure, high-quality synthetic healthcare data, effectively addressing data scarcity challenges. Full article

Despite following standard practices of well-known project management methodologies, some projects fail to achieve expected results, incurring unexplained cost overruns or delays. These problems occur regardless of the type of project, the environment, or the project manager’s experience and are characteristic of complex projects. Such projects require special control using a multidimensional network approach that includes contractual aspects, supply and resource considerations, and information exchange between stakeholders. By modelling project elements as nodes and their interrelations as links within a network, we can analyze how components evolve and influence each other, a phenomenon known as coevolution. This network analysis allows us to observe not only the evolution of individual nodes but also the impact of their interrelations on the overall dynamics of the project. Two metrics are proposed to address the inherent complexity of these projects: one to assess Structural Complexity (SC) and the other to measure Dynamic Complexity (DC). These metrics are based on Boonstra and Reezigt’s studies on the dimensions and domains of complex projects. These two metrics have been combined to create a Global Complexity Index (GCI) for measuring project complexity under uncertainty using fuzzy logic. These concepts are applied to a case of study, the construction of a wastewater treatment plant, a complex project due to the intense interrelations, the integration of new technologies that require R&D, and its location next to a natural park. The application of the GCI allows constant monitoring of dynamic complexity, thus providing a tool for risk anticipation and decision support. Also, the integration of fuzzy logic in the model facilitates the incorporation of imprecise or partially defined information. It makes it possible to deal efficiently with the dynamic variation of complexity parameters in the project, adapting to the inherent uncertainties of the environment. Full article

This paper investigates socioeconomic variation in motivations for ritual practices among Mauritian Hindus. Using cultural domain analysis, we explore individuals’ reported reasons for engaging in a variety of religious rituals. Our findings demonstrate significant intra-cultural diversity driven by social stratification. Specifically, we observe that those of lower social standing appear primarily motivated by existential concerns related to material security and safety, while higher-status individuals view these practices as platforms for personal and social enrichment, as they are more preoccupied with self-actualization, spiritual connection, and social affirmation, reflecting a more abstract engagement with religious practices. Our findings reveal the adaptability of ritual practices to meet a wide range of human needs across varying life circumstances, as rituals can be differentially negotiated by individuals within the same cultural context depending on the specific socioecological niches they occupy. Moreover, they highlight the role of culture as a dynamic and distributed system with important implications for anthropological theory and practice. Full article

Automatic pavement distress detection using deep learning has revolutionized maintenance efficiency, but deploying models in new, unseen scenarios presents significant challenges due to shifts in data distribution. Traditional transfer learning requires extensive labeled data from the new domain, which is both time-consuming and costly. This paper proposes a test-time adaptation (TTA) framework that addresses feature distribution biases across different scenes, including differences in background, perspective, and environmental conditions. It adapts models at inference time without requiring additional labeled data, making it a promising solution for cross-scenario applications. The framework dynamically adapts the model to these biases by generating domain-specific prior knowledge, applying perspective correction, and generating global attention maps to reduce focus on irrelevant elements. We evaluate the framework on a cross-scene dataset that includes pavement images from three countries and four perspectives. In unsupervised settings, the TTA framework improves detection accuracy by 20.6%, achieving 93.09% of the accuracy obtained through transfer learning with 10,000 labeled images. Compared to traditional transfer learning, our framework reduces the reliance on high-quality labeled data while achieving similar performance gains. Experimental results also demonstrate the framework’s adaptability across various deep learning detection models, offering a scalable solution for rapid deployment and cross-scenario application of pavement distress detection systems. Full article

Remote sensing imagery (RSI) segmentation plays a crucial role in environmental monitoring and geospatial analysis. However, in real-world practical applications, the domain shift problem between the source domain and target domain often leads to severe degradation of model performance. Most existing unsupervised domain adaptation methods focus on aligning global-local domain features or category features, neglecting the variations of ground object categories within local scenes. To capture these variations, we propose the scene covariance alignment (SCA) approach to guide the learning of scene-level features in the domain. Specifically, we propose a scene covariance alignment model to address the domain adaptation challenge in RSI segmentation. Unlike traditional global feature alignment methods, SCA incorporates a scene feature pooling (SFP) module and a covariance regularization (CR) mechanism to extract and align scene-level features effectively and focuses on aligning local regions with different scene characteristics between source and target domains. Experiments on both the LoveDA and Yanqing land cover datasets demonstrate that SCA exhibits excellent performance in cross-domain RSI segmentation tasks, particularly outperforming state-of-the-art baselines across various scenarios, including different noise levels, spatial resolutions, and environmental conditions. Full article