Search Results (506)

Tillage, cover crops (CC) and nutrient amendments are regenerative agricultural practices (RAPs) which enhance desirable ecosystem services (DESs), including the beneficial nematode community structure (BNCS), soil organic matter (SOM), pH, and available nitrogen, and the Ferris et al. soil food web (SFW) model relates changes in the BNCS to biophysicochemical conditions generating DESs. However, the SFW model’s power to identify soil health conditions influencing DESs’ outcomes has been limited. We tested how tillage, winter rye CC, and 0, 112, or 224 kg N/ha from inorganic and compost sources affected the DESs after four years of corn production. The SOM and NO₃ was much greater in the no-till than the tilled soil, and the SOM in the 224 kg organic source, compared with the rest of the N rates, was significantly increased. The N recovery was not proportional to what was applied. The variable effects of the RAPs on the DESs suggest either changing or continuing treatments until suitable outcomes are achieved, all without knowing the source(s) of variability. The SFW model revealed primarily resource-limited and structured (Quadrant C) conditions, suggesting that (1) nutrient cycling needs biological activities and (2) the presence of a process-limiting factor may have contributed to the variable results. The impacts of the SFW model as a diagnostic tool are outlined. Full article

This paper presents a novel neural network model for the detection of Structured Query Language (SQL) injection attacks for web applications. The model features high detection accuracy, fast inference speed, and low weight size. The model is based on a novel Natural Language Processing (NLP) technique, where a tokenizer for converting SQL queries into tokens is adopted as a pre-processing stage for detection. Only SQL keywords and symbols are considered as tokens for removing noisy information from input queries. Moreover, semantic labels are assigned to tokens for highlighting malicious intentions. For the exploration of correlation among the tokens, a lightweight multi-head self-attention scheme with a position encoder is employed. Experimental results show that the proposed algorithm has high detection performance for SQL injection. In addition, compared to its lightweight NLP counterparts based on self-attention, the proposed algorithm has the lowest weight size and highest inference speed. It consumes only limited computation and storage overhead for web services. In addition, it can even be deployed in the edge devices with low computation capacity for online detection. The proposed algorithm therefore is an effective low-cost solution for SQL injection detection. Full article

This paper addresses the increasing demand for efficient and scalable streaming service applications within the context of edge computing, utilizing NVIDIA Jetson Xavier NX hardware and Docker. The study evaluates the performance of DeepStream and Simple Realtime Server, demonstrating that containerized applications can achieve performance levels comparable to traditional physical machines. The results indicate that WebRTC provides superior low-latency capabilities, achieving delays of around 5 s, while HLS typically experiences delays exceeding 10 s. Performance tests reveal that CPU usage for WebRTC can exceed 40%, which is higher than that of HLS and RTMP, while memory usage remains relatively stable across different streaming protocols. Additionally, load testing shows that the system can support multiple simultaneous connections, but performance degrades significantly with more than three devices, highlighting the limitations of the current hardware setup. Overall, the findings contribute valuable insights into building efficient edge computing architectures that support real-time video processing and streaming. Full article

The main objective of this paper is to illustrate the use of artificial intelligence (AI) in the tourism and air transport industries to improve tourists’ experiences, as well as provide a definition of the AI concept closest to both sectors. In order to examine and demonstrate the body of literature on AI and its application to the travel and tourism industry. This study also presents the findings of a literature review using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) approach in conjunction with a systematic literature review using the Web of Science (WoS) database. This approach enabled us to construct a novel AI concept in the context of tourism. This research found that AI technology offers new and creative opportunities for tourists due to this innovative tool that promotes and empowers travel and tourism organisations’ products and services. AI has helped to outline travel planning for tourists, made it easier to discover new experiences, and streamlined the booking process. The reality is that AI methods and applications are changing and improving passengers and tourists’ experiences in tourism cities and the air transport sector. Moreover, it is necessary to highlight that one of AI technology’s greatest strengths lies in the immediacy of response and advice that swiftly help tourists plan their trips, tours, detailed itineraries, and flight bookings at the same moment. This research is an antecedent attempt to define AI technology in the tourism and air transport context and to illustrate its virtues and shortcomings to improve tourists’ experiences in cities and the operational efficiency of organisations. Full article

Living beings as open systems depend on climate and weather to survive. However, changes in the Earth’s climatology, which have become more frequent since the industrial period, have affected different territories of the planet, limiting access to ecosystem services and causing imbalances in health and well-being. The first purpose of this study is to conduct a literature review on academic production regarding climate change and its impact on health, in the context of education, using international academic production condensed in the Web of Science (WOS) database over the last 10 years as a reference. The second purpose focuses on identifying the environmental attitudes of science teachers in initial training regarding aspects related to climate change. The study results show three categories emerging from the literature review: Climate Change and Health, Nature and Risks, and Environment and Energy. For the analysis of environmental attitudes, a survey was conducted with 51 pre-service teachers, consisting of 59 items distributed in five categories: (a) environment, (b) climate change, (c) health, (d) education, and (e) lifestyle. Although the results reveal a positive attitude towards all analyzed categories, it is important to advance effective mitigation and adaptation strategies from the teacher training processes themselves. Full article

Massive image datasets are often required for the proper functioning of Machine Learning (ML) and Computer Vision (CV) applications. This paper offers a solution to computational challenges in the Image Processing of satellite imagery, by proposing an optimization procedure. The presented approach is verified by an exemplary Python implementation, constituting a standalone tool for automating the dataset creation and labeling, including the extraction of road network data from the national satellite cartography provider. The collected data include detailed road maps along with the parcel information obtained via WebMapService endpoints. The method presented in this paper involves three basic steps: road segmentation (using the Shapely module) to facilitate handling high-resolution orthoimagery, and then a modified Region-of-Interest approach, i.e., removing irrelevant areas, with only roads remaining. This results in obtaining file sizes that are significantly smaller. The presented algorithm also involves asynchronous tile downloading, which, combined with the masking of irrelevant areas, improves not only the efficiency but surprisingly also the accuracy of subsequent ML/CV procedures. The research results of the paper reveal substantial file size reduction, and improved processing efficiency, thus making the optimized geospatial graphical data more practical for ML/CV applications, while still maintaining the original data quality and relevance of the analyzed parcels or infrastructure. Full article

This paper proposes using a web crawler to organize website content as a dialogue tree in some domains. We build an intelligent customer service agent based on this dialogue tree for general usage. The encoder-decoder architecture Seq2Seq is used to understand natural language and then modified as a bi-directional LSTM to increase the accuracy of the polysemy cases. The attention mechanism is added in the decoder to improve the problem of accuracy decreasing as the sentence grows in length. We conducted four experiments. The first is an ablation experiment demonstrating that the Seq2Seq + Bi-directional LSTM + Attention mechanism is superior to LSTM, Seq2Seq, Seq2Seq + Attention mechanism in natural language processing. Using an open-source Chinese corpus for testing, the accuracy was 82.1%, 63.4%, 69.2%, and 76.1%, respectively. The second experiment uses knowledge of the target domain to ask questions. Five thousand data from Taiwan Water Supply Company were used as the target training data, and a thousand questions that differed from the training data but related to water were used for testing. The accuracy of RasaNLU and this study were 86.4% and 87.1%, respectively. The third experiment uses knowledge from non-target domains to ask questions and compares answers from RasaNLU with the proposed neural network model. Five thousand questions were extracted as the training data, including chat databases from eight public sources such as Weibo, Tieba, Douban, and other well-known social networking sites in mainland China and PTT in Taiwan. Then, 1000 questions from the same corpus that differed from the training data for testing were extracted. The accuracy of this study was 83.2%, which is far better than RasaNLU. It is confirmed that the proposed model is more accurate in the general field. The last experiment compares this study with voice assistants like Xiao Ai, Google Assistant, Siri, and Samsung Bixby. Although this study cannot answer vague questions accurately, it is more accurate in the trained application fields. Full article

Public transportation systems play a vital role in modern cities, but they face growing security challenges, particularly related to incidents of violence. Detecting and responding to violence in real time is crucial for ensuring passenger safety and the smooth operation of these transport networks. To address this issue, we propose an advanced artificial intelligence (AI) solution for identifying unsafe behaviours in public transport. The proposed approach employs deep learning action recognition models and utilises technologies like NVIDIA DeepStream SDK, Amazon Web Services (AWS) DirectConnect, local edge computing server, ONNXRuntime and MQTT to accelerate the end-to-end pipeline. The solution captures video streams from remote train stations closed circuit television (CCTV) networks, processes the data in the cloud, applies the action recognition model, and transmits the results to a live web application. A temporal pyramid network (TPN) action recognition model was trained on a newly curated video dataset mixing open-source resources and live simulated trials to identify the unsafe behaviours. The base model was able to achieve a validation accuracy of 93% when trained using open-source dataset samples and was improved to 97% when live simulated dataset was included during the training. The developed AI system was deployed at Wollongong Train Station (NSW, Australia) and showcased impressive accuracy in detecting violence incidents during an 8-week test period, achieving a reliable false-positive (FP) rate of 23%. While the AI correctly identified 30 true-positive incidents, there were 6 cases of false negatives (FNs) where violence incidents were missed during the rainy weather suggesting more data in the training dataset related to bad weather. The AI model’s continuous retraining capability ensures its adaptability to various real-world scenarios, making it a valuable tool for enhancing safety and the overall passenger experience in public transport settings. Full article

The majority of the global population now resides in cities, and this trend continues to grow. In this context, the Internet of Things (IoT) is crucial in transforming existing urban areas into Smart Cities. However, IoT architectures mainly focus on machine-to-machine interactions, leaving human involvement aside. The Internet of Everything (IoE) includes human-to-human and human–machine collaboration, but the specifics of these interactions are still under-explored. As urban populations grow and IoT integrates into city infrastructure, efficient, collaborative architectures become crucial. In this work, we use the Rapid Review methodology to analyze collaboration in four prevalent computing architectures in the IoE paradigm, namely Edge Computing, Cloud Computing, Blockchain/Web Services, and Fog Computing. To analyze the collaboration, we use the 3C collaboration model, comprising communication, cooperation, and coordination. Our findings highlight the importance of Edge and Cloud Computing for enhancing collaborative coordination, focusing on efficiency and network optimization. Edge Computing supports real-time, low-latency processing at data sources, while Cloud Computing offers scalable resources for diverse workloads, optimizing coordination and productivity. Effective resource allocation and network configuration in these architectures are essential for cohesive IoT ecosystems. Therefore, this work offers a comparative analysis of four computing architectures, clarifying their capabilities and limitations. Smart Cities are a major beneficiary of these insights. This knowledge can help researchers and practitioners choose the best architecture for IoT and IoE environments. Additionally, by applying the 3C collaboration model, the article provides a framework for improving collaboration in IoT and IoE systems. Full article

As machine learning (ML) transforms industries, the need for efficient model development tools using high-performance computing (HPC) and ensuring interpretability is crucial. This paper presents SIBILA, an AutoML approach designed for HPC environments, focusing on the interpretation of ML models. SIBILA simplifies model development by allowing users to set objectives and preferences before automating the search for optimal ML pipelines. Unlike traditional AutoML frameworks, SIBILA is specifically designed to exploit the computational capabilities of HPC platforms, thereby accelerating the model search and evaluation phases. The emphasis on interpretability is particularly crucial when model transparency is mandated by regulations or desired for stakeholder understanding. SIBILA has been validated in different tasks with public datasets. The results demonstrate that SIBILA consistently produces models with competitive accuracy while significantly reducing computational overhead. This makes it an ideal choice for practitioners seeking efficient and transparent ML solutions on HPC infrastructures. SIBILA is a major advancement in AutoML, addressing the rising demand for explainable ML models on HPC platforms. Its integration of interpretability constraints alongside automated model development processes marks a substantial step forward in bridging the gap between computational efficiency and model transparency in ML applications. The tool is available as a web service at no charge. Full article

With the rapid expansion of cloud computing and the pervasive growth of IoT across industries and educational sectors, the need for efficient remote data management and service orchestration has become paramount. Web services, facilitated by APIs, offer a modular approach to integrating and streamlining complex business processes. However, real-time monitoring and optimal service selection within large-scale, cloud-based repositories remain significant challenges. This study introduces the novel Improved Eagle Strategy (IES) hybrid model, which uniquely integrates bio-inspired optimization with clustering techniques to drastically reduce computation time while ensuring highly accurate service selection tailored to specific user requirements. Through comprehensive NetLogo simulations, the IES model demonstrates superior efficiency in service selection compared to existing methodologies. Additionally, the IES model’s application through a web dashboard system highlights its capability to manage both functional and non-functional service attributes effectively. When deployed on real-time IoT devices, the IES model not only enhances computation speed but also ensures a more responsive and user-centric service environment. This research underscores the transformative potential of the IES model, marking a significant advancement in optimizing cloud computing processes, particularly within the IoT ecosystem. Full article

Seasonal vertical ground movement (SVGM), which refers to the periodic vertical displacement of the Earth’s surface, has significant implications for infrastructure stability, agricultural productivity, and environmental sustainability. Understanding how SVGM correlates with climatic conditions—such as temperatures and drought—is essential in managing risks posed by land subsidence or uplift, particularly in regions prone to extreme weather events and climate variability. The correlation of periodic SVGM with climatic data from Earth observation was investigated in this work. The European Ground Motion Service (EGMS) vertical ground movement measurements, provided from 2018 to 2022, were compared with temperature and precipitation data from MODIS and CHIRP datasets, respectively. Measurement points (MP) from the EGMS over Italy provided a value for ground vertical movement approximately every 6 days. The precipitation and temperature datasets were processed to provide drought code (DC) maps calculated ad hoc for this study at a 1 km spatial resolution and daily temporal resolution. Seasonal patterns were analyzed to assess correlations with Spearman’s rank correlation coefficient ($\rho$) between this measure and the DCs from the Copernicus Emergency Management Service ($D{C}_{CEMS}$), from MODIS + CHIRP ($D{C}_{1\mathrm{km}}$) and from the temperature. The results over the considered area (Italy) showed that 0.46% of all MPs (32,826 MPs out of 7,193,676 MPs) had a $\rho$ greater than 0.7; 12,142 of these had a positive correlation, and 20,684 had a negative correlation. $D{C}_{1\mathrm{km}}$ was the climatic factor that provided the highest number of correlated MPs, roughly giving +59% more correlated MPs than $D{C}_{CEMS}$ and +300% than the temperature data. If a $\rho$ greater than 0.8 was considered, the number of MPs dropped by a factor of 10: from 12,142 to 1275 for positive correlations and from 20,684 to 2594 for negative correlations between the $D{C}_{1\mathrm{km}}$ values and SVGM measurements. Correlations that lagged in time resulted in most of the correlated MPs being within a window of ±6 days (a single satellite overpass time). Because the DC and temperature are strongly co-linear, further analysis to assess which was superior in explaining the seasonality of the MPs was carried out, resulting in $D{C}_{1\mathrm{km}}$ significantly explaining more variance in the SVGM than the temperature for the inversely correlated points rather than the directly correlated points. The spatial distribution of the correlated MPs showed that they were unevenly distributed in clusters across the Italian territory. This work will lead to further investigation both at a local scale and at a pan-European scale. An interactive WebGIS application that is open to the public is available for data consultation. This article is a revised and expanded version of a paper entitled “Detection and correlation analysis of seasonal vertical ground movement measured from SAR and drought condition” which was accepted and presented at the ISPRS Mid-Term Symposium, Belem, Brasil, 8–12 November 2024. Data are shared in a public repository for the replication of the method. Full article

The sharing economy (SE) is a nascent phenomenon representing a socio-economic process to optimise underutilised resources through digital platforms. This process facilitates the shared consumption of resources to maximise resource utilisation while supporting the circularity of resources. However, the successful operation of SE practices is hindered by the lack of identification of effective strategies for enhancing the SE implications, which are essential to comprehending SE practices and developing more sophisticated applications. Therefore, this research aims to provide the first insights into the strategies that enhance SE practices across diverse industries and identify knowledge gaps and future research directions. A systematic literature review (SLR) was conducted by selecting articles published in the 2014–2023 period in Scopus and Web of Science databases. Selected articles were subjected to descriptive and NVivo 14-supported thematic analyses. The descriptive analysis showed that, despite considering articles published in the last 10 years, all relevant articles were published in the last 5 years. Developed and developing countries showed almost equal contributions, while China was recognised as the country with the highest number of publications. Accommodation and transportation sectors were reported as the sectors with the highest number of publications. A cross-analysis was conducted to recognise the varying utilisation of different strategies across diverse industries and sectors. Ten different categories were identified through the thematic analysis that enhance SE practices: economic; environmental; geographic; governance; health, safety, and security; marketing; people; product/services; research, training, education; and technology-related strategies. Each category was discussed along with its relevant strategies, resulting in identifying a total of 84 strategies. These strategies were then presented alongside the responsible parties tasked with their implementation. The study contributes to the SE literature by providing an SLR for contemporary strategies utilised to enhance SE practices, specifically focusing on elucidating the most appropriate categorisation of these strategies. Moreover, this comprehensive SLR provides the first insights into the effective strategies that enhance SE practices across diverse industries. Full article

Nonprofit Organizations (NPOs) are adopting technology to improve their quality of services, scale up, or reduce operation costs. However, due to the heterogeneity of systems they use, NPOs face system-integration challenges when collaborating with other organizations. Middleware is an intermediary software that assists dissimilar systems in working together. This paper explores middleware applications, opportunities, and challenges within the sector. It extensively reviewed the current state of research on middleware usage in the nonprofit sector for all papers published in Scopus and Web of Science (WoS) until 2023. Out of 127 papers returned, only 31 remained after removing duplicates, invalid entries, and out-of-scope publications. Then, we synthesized insights from a thorough survey of these selected papers. In light of the survey results, we observed that NPOs primarily use middleware in a few of the Sustainable Development Goals (SDGs), namely, health (SDG 3), NPO operations (SDG 8 and 9), NPO collaborations (SDG 17), development of sustainable cities (SDG 11), security and disaster management (SDG 16), and education (SDG 4). We also identified several challenges related to using middleware in the nonprofit sector, which include privacy, security, system development and performance, data processing and transfer, and volunteer attrition. Full article

The motivation for this work arose when noticing that definitions of honeypots’ interaction level are mainly based on the information technology environment and do not reflect operational technology even if several honeypot projects approach this field. Within operational technology, programmable logic controllers (PLCs) have a main role, resulting in several honeypot researchers choosing to mimic this device at a certain interaction level. However, searching for an interaction level definition that approaches PLCs results in few studies. In this context, this work aims to explore how to adapt the information technology definition of the interaction level in order to encompass PLCs and their specific features. The method chosen to obtain inputs was a literature review where, in attempting to keep the connection with information technology, the features were based in terms of honey system, honey service, and honey token. The findings of this review provide a means to translate these terms when developing a PLC honeypot for a desired interaction level, resulting in a metrics proposal for low and high interaction. Summarizing the proposed metrics, the system of a PLC can be considered as the vendor specific firmware, its unique device banner, and a realistic network topology. For services, a PLC honeypot reflects the tasks performed by the real device, thus resulting in industrial communication protocols, network management protocols, appropriate response times, code-related interactions, dynamic input and output data processing, physical process simulation, and web interface. Lastly, a PLC honey token can be approached with the PLC program file, MIB file, and software license, among other elements. Based on these metrics, researchers can better evaluate how to design a programmable logic controller honeypot or select tools that match their target interaction level. Full article