Search

Proton Exchange Membrane Fuel Cell (PEMFC) systems represent a crucial clean energy component, offering a sustainable alternative to traditional power sources. However, ensuring the dependable and optimal performance of PEMFC systems is essential for their widespread adoption and integration into various applications, ranging from transportation to stationary power generation. To overcome the challenges associated with maintaining the reliability and efficiency of PEMFC systems, there is a growing reliance on Artificial Intelligence (AI)-based diagnosis techniques. AI has emerged as a transformative tool in analyzing complex data patterns, detecting anomalies, and facilitating autonomous decision-making. In the context of PEMFC systems, AI-driven methodologies offer innovative solutions for diagnosing faults, predicting system performance, and optimizing operational parameters. By using AI techniques such as Machine Learning (ML), Neural Networks (NN), expert systems, and data-driven approaches, researchers aim to enhance the reliability, efficiency, and durability of PEMFC systems while minimizing downtime and maintenance costs. The application of AI in PEMFC system diagnosis involves the development of sophisticated algorithms capable of analyzing various data sources, including sensor readings, system parameters, and environmental conditions. These algorithms can detect anomalies, diagnose faults, and provide recommendations for remedial actions in real-time, ensuring continuous and reliable operation of PEMFC systems. While previous papers may have addressed aspects of PEMFC system diagnosis, this comprehensive survey aims to systematically synthesize existing literature to identify shared concepts and research gaps. This extensive survey encompasses a spectrum of AI methodologies, Machine Learning (ML) algorithms, Neural Networks (NN), expert systems, and data-driven approaches associated with diagnosing PEMFC systems. We reviewed over 750 papers to identify shared concepts and real-world implementation issues for future research directions.

Gastrointestinal (GI) diseases are most common worldwide and the death rate can be reduced by early detection. Endoscopy is widely regarded as the gold standard for diagnosing and managing digestive disorders, affecting both the upper and lower GI tracts. Endoscopy is performed to uncover biopsy tissues used to check the presence of cancerous or benign cells, Helicobacter pylori (H. pylori) infection, or perform colonoscopy in case of the removal of polyps. A systematic review was conducted on databases like PubMed, Scopus, Google Scholar, and IEEE Explore, including research papers published up to May 2023, through the systematic search, 33 papers were identified. This review offers valuable insights to physicians and technological guidance to future researchers by examining GI tract diseases. It provides a detailed analysis of Machine learning (ML) techniques like preprocessing, segmentation, feature extraction, and classification. Additionally, Deep Learning (DL) approaches like transfer learning (TL), Convolution Neural Networks (CNN), optimization, transformer, and reinforcement learning have been analyzed for GI diagnosis. The DL approach has increased its use in GI diseases and CNN was the most commonly used architecture. Lastly, the review highlights the research published in the specialized GI fields and provides technological suggestions and insights for future research prospects. Overall, this study broadens the body of knowledge regarding the existing Artificial Intelligence (AI) techniques in gastroenterology as a manual for creating and assessing AI models.

Diabetes, especially type 2 diabetes (T2D), is a chronic disease affecting millions of people worldwide. The increasing prevalence of T2D, coupled with the complex interplay between genetic, environmental, and lifestyle factors, presents a major challenge for effective disease management. The traditional methods for predicting T2D progression and determining appropriate treatment strategies are often subjective and less accurate, resulting in treatment delays. Therefore, artificial intelligence (AI) based prediction models become crucial, as they offer a more objective and data-driven approach to T2D management. By leveraging advanced statistical techniques and machine learning algorithms, AI-based prediction models can better identify patients at high risk for T2D progression and predict responses to different treatment options. This can ultimately lead to improved outcomes for patients suffering from T2D. Therefore, this paper aims to review the existing research articles published from 2018 to 2022 using a systematic literature review (SLR) approach. From 40 selected articles, a taxonomy of the most common techniques for developing a prediction model in diabetes progression is drawn in three approaches: mathematical, machine learning (ML), and deep learning (DL). In addition, the best practices of dataset characteristics, pre-processors, and evaluation metrics of the existing algorithms are also provided, focusing on the context of diabetes progression prediction. The findings found that the majority of the selected papers employed ML, specifically the RF model, proven to have superiority in performance. This review also discusses current challenges faced in building prediction models for diabetes progression and proposes future research directions to overcome these challenges. The promising directions drawn include 1) incorporating feature reduction or importance tools to explore the relationship between variables, 2) developing an interpretable predictive model to provide analytical results that are understandable to clinicians, and 3) validating the model with multiple large-sample size datasets and seeking clinical advice from experts.

This article aims to explore the trend of cultural and creative design combined with artificial intelligence (AI) technology and its modeling of aesthetic preferences. With the rapid development of AI technology, its application in cultural and creative industries is increasingly extensive, which brings new possibilities for cultural and creative design. At first, the paper analyzes the application status of AI technology in cultural and creative design, and focuses on the creative generation model based on Generation Against Network (GAN) and other technologies. Secondly, the paper discusses the modeling methods of aesthetic preference, including descriptive statistical analysis, linear regression, decision tree and cluster analysis. By modeling users’ aesthetic preferences, designers can better understand users’ needs and provide them with more personalized cultural and creative products. Finally, the paper looks forward to the future development trend, including multi-modal creative design and intelligent creative auxiliary tools. This paper aims to provide reference and guidance for the development of cultural and creative industries, and provide new ideas and methods for related research and practice.

Transformer has been adopted to image recognition tasks and shown to outperform CNNs and RNNs while it suffers from high training cost and computational complexity. To address these issues, a hybrid approach has become a recent research trend, which replaces a part of ResNet with an MHSA (Multi-Head Self-Attention). In this paper, we propose a lightweight hybrid model which uses Neural ODE (Ordinary Differential Equation) as a backbone instead of ResNet so that we can increase the number of iterations of building blocks while reusing the same parameters, mitigating the increase in parameter size per iteration. The proposed model is deployed on a modest-sized FPGA device for edge computing. The model is further quantized by QAT (Quantization Aware Training) scheme to reduce FPGA resource utilization while suppressing the accuracy loss. The quantized model achieves 79.68% top-1 accuracy for STL10 dataset that contains $96\times 96$ pixel images. The weights of the feature extraction network are stored on-chip to minimize the memory transfer overhead, allowing faster inference. By eliminating the overhead of memory transfers, inference can be executed seamlessly, leading to accelerated inference. The proposed FPGA implementation accelerates the backbone and MHSA parts by $34.01\times $ , and achieves an overall $9.85\times $ speedup when taking into account the software pre- and post-processing. The FPGA acceleration leads to $7.10\times $ better energy efficiency compared to the ARM Cortex-A53 CPU. The proposed lightweight Transformer model is demonstrated on Xilinx ZCU104 board for the image recognition of $96\times 96$ pixel images in this paper and can be applied to different image sizes by modifying the pre-processing layer.

Road Condition Monitoring is a critical task for the management and maintenance of the pavement network infrastructure by the authorities. In recent years, the application of Artificial Intelligence (AI) techniques in this domain has experienced a significant growth, driven by the continuous advancements in AI algorithms. This paper presents a comprehensive review of the latest developments in Road Condition Monitoring approaches using AI methods, with a particular focus on Deep Learning techniques, covering works published from 2020 onwards. It highlights novel approaches that have not been thoroughly explored in previous literature reviews. The literature review categorizes studies based on the type of signal data, distinguishing between acoustic, vibrational, and vision-based approaches. For each data type, the paper examines and discuss the most recent advancements and improvements achieved through AI techniques. Additionally, it provides an overview of future directions and identifying key challenges that remain open in the field. In conclusion, relatively few studies have focused on the analysis of acoustic data, although some studies have reported promising results. Methods based on vibrational data typically integrate feature extraction in frequency and wavelet domain with Convolutional Neural Networks or Long Short-Term Memory Networks. Meanwhile, vision-based methods have experienced significant improvements, driven by the constant evolution of Deep Learning architectures. A total of 173 research articles are summarized across 10 tables.

Fog computing, an extension of cloud computing, enhances capabilities by processing data closer to the source, thereby addressing latency and bandwidth issues inherent in traditional cloud models. However, the integration of Artificial Intelligence (AI) into fog computing introduces challenges, particularly in resource management, security, and privacy. This paper systematically reviews AI applications within fog computing environments, adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to ensure rigorous analysis. The studies were selected based on predefined inclusion criteria, including research published between 2010 and 2024 in peer-reviewed journals and conference papers, with searches conducted in databases like IEEE Xplore, ACM Digital Library, SpringerLink, and Scopus. The review identifies critical issues such as resource constraints, transparency in AI-driven security systems, and the need for adaptable AI models to address evolving security threats. In response, innovative solutions such as lightweight AI models (e.g., Pruned Neural Networks, Quantized Models, Knowledge Distillation), Explainable AI (XAI) (e.g., Model-Agnostic Methods, Feature Importance Analysis, Rule-Based Approaches), and federated learning are proposed. Additionally, a novel taxonomy is introduced, categorizing AI techniques into resource management, security enhancement, and privacy-preserving methods, offering a structured framework for researchers and practitioners. The paper concludes that effective AI integration in fog computing is essential for developing secure, efficient, and adaptable distributed systems, with significant implications for both academia and industry.

The issue of power quality (PQ) has become increasingly critical in modern power systems due to the growing integration of sensitive electronic devices, electric vehicles, and renewable energy sources. Among the various PQ concerns, harmonics have emerged as a significant contributor to the overheating of power system components. This overheating phenomenon can have detrimental effects, including reduced equipment lifespan, increased maintenance costs, and unexpected failures. This comprehensive review paper provides an in-depth examination of the impact of harmonics on power system components, with a focus on the overheating problems they induce. The paper delves into an analysis of PQ indices and standards, underscoring the necessity for efficient mitigation techniques to address harmonic-related overheating and other PQ concerns. The review explores the key PQ devices employed to mitigate harmonics, such as passive power filters, active power filters, and advanced devices like D-STATCOM, unified PQ conditioners, and dynamic voltage restorers. Furthermore, it investigates the various control algorithms and optimization techniques utilized in the design of these power filters, emphasizing their pivotal role in addressing harmonics and preventing overheating. It also discusses the applicability of artificial intelligence techniques in mitigating power harmonics and improving PQ in modern power grid studies.

Vision and Robotic technologies are progressively becoming ubiquitous for automating and digitizing quality control in the food industry. This paper examines the crucial role of advanced automation technologies, including versatile or dedicated robotic systems, specialized end-effectors, machine vision, and efficient material handling systems, which collectively enhance food processing efficiency. This paper aspires to provide a high-level technical review on the crucial role of advanced automation technologies, including versatile or dedicated robotic systems, specialized end-effectors, machine vision, and efficient material handling systems, which collectively enhance food processing efficiency. While the manuscript aims to document the various automation sub-systems utilized generally in food processing, it places a particular emphasis on the primary processing phase of food production. Most food products in the primary processing phase exhibit a plethora of complex physical properties and manipulation conditions, making it difficult to reliably automate the various processes. This research aims to outline the contemporary advances and requirements for integrating various automation technologies, to enhance the efficiency and precision of primary food processing. Furthermore, it aspires to serve as a valuable, up-to-date survey and analysis of the latest advances in automation and vision technologies and their capability to automate a food processing line.

The continuous evolution of autonomous vehicles technologies has significantly elevated the capabilities of intelligent transportation and road safety. Among these advancements, driving automation systems have played a vital role within vehicles, encompassing a diversity of functionality extending from systems assisting the driver called Advanced Driver Assistance Systems to Automated Driving Systems offering full control over various driving functions. Among these systems, Traffic Sign Recognition (TSR) system plays a significant role in terms of functionality and development. This survey focuses on the development of TSR systems including both detection and classification methods considering diverse techniques based on color, shape, machine learning and deep learning algorithms and offers insights into the various approaches. Hence a comparative synthesis is established to discuss thorough of them along. Furthermore, this paper presents a comprehensive study for TSR systems using two hardware platforms: Raspberry Pi and Nano Jetson to analyze their performances and provide insights into the most suitable hardware architectures for deploying efficient and reliable TSR systems. This paper concludes by advocating for a synergistic combination of the two best methods of detection and classification of road signs in terms of accuracy and processing time to build a new real time TSR methodology that effectively address this challenge and ultimately improve TSR performance implemented on the best target.

This review paper examines the transformative role of artificial intelligence (AI) and dynamic ensemble techniques in enhancing healthcare services. By systematically reviewing literature and case studies from the past decade, we explore how these advanced computational methods improve diagnostic accuracy, personalize treatment plans, and optimize patient monitoring. Dynamic ensemble techniques, which leverage multiple predictive models to improve outcome accuracy, offer significant promise in addressing the complexities of patient data and disease manifestations. This paper delves into applications spanning AI-driven diagnostics, personalized medicine, and remote patient monitoring, highlighting both the advancements and challenges faced in integrating these technologies into healthcare. We also address the ethical and computational challenges inherent in deploying dynamic ensemble methods and propose directions for future research. Our findings suggest that while significant progress has been made, multidisciplinary collaboration and continued innovation are crucial for overcoming current limitations and realizing the full potential of AI in healthcare.

Accurate diagnosis and treatment of cardiovascular diseases require the integration of cardiac imaging, which provides crucial information about the structure and function of the heart to improve overall patient care. This review explores the role of Artificial Intelligence (AI) in advancing cardiac imaging analysis, with a focus on unsupervised learning methods. Unlike supervised AI systems, which rely on annotated datasets, the use of unsupervised learning proves to be a game-changer. It effectively tackles issues related to limited datasets and sets the stage for scalable and adaptive solutions in cardiac imaging. This paper gives a comprehensive overview of the limitations of traditional methods and the potential of unsupervised AI in overcoming challenges related to dataset scarcity through an extensive literature review and analysis of unsupervised algorithms, including clustering techniques, dimensionality reduction, and generative models. This review study highlights the contributions of unsupervised techniques for enhancing diagnostic accuracy and efficiency in cardiac imaging. By comparing unsupervised and supervised methods, the paper aims to explain the benefits and limitations of each approach, offering valuable insights for advancing AI integration in cardiac healthcare. The findings are expected to guide future research and development, leading to innovative advancements in cardiovascular diagnostics.

The advent of artificial intelligence (AI) has catalyzed transformative changes across diverse domains, establishing itself as a disruptive technology. Traditional methods often fall short in solving intricate information engineering problems, whereas AI methods can offer superior efficiency, speed, and accuracy. This paper provides a comprehensive overview of the research and practical applications of artificial intelligence in addressing information engineering challenges over the past two decades. It focuses on four critical information engineering fields: intelligent control, pattern recognition and intelligent systems, intelligent signal processing and communication, and optimization algorithms. This paper covers the backgrounds, driving forces, technologies, and applications of these fields, as well as the applications of AI in these areas. We believe that this study will be a valuable resource for both novice and seasoned researchers interested in leveraging AI to tackle information engineering challenges, offering a comprehensive understanding of AI integration and its potential in these areas.

The water crisis, global warming and climate changes have become recently prominent world issues. Saving and conserving water have become, therefore, an imperative for water resources’ sustainability. In this context, dramatic innovations have come to light, e.g., Precision Agriculture. Numerous research projects on this subject have been conducted, as illustrated not only by the huge number of research works in this topic, but also by the dozens of surveys dedicated to. Surveys regarding smart agriculture are of two categories, surveys on smart agriculture in general in which smart irrigation is a subtopic among others, and surveys dedicated to smart irrigation. Existing surveys, however, suffer from limitations including low paper numbers, linear description without structural classification, and missing key information. To fill this gap, we propose, in this paper, a survey on SI that classifies the large body of literature into categories in a structured way. To this end, we have employed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to determine the inclusion or exclusion of articles. We have reviewed a total of 610 publications out of which 227 met the inclusion criteria. We have categorized the selected references into three conceptual clusters corresponding to: (1) 41.8% focusing on field measurements, based on IoT sensors, (2) 37% involving Remote Sensing (RS) and (3) 21.1% Artificial Intelligence (AI) methods. Each category is thoroughly described, including the inputs and outputs, along with a description of the various tasks employed in irrigation management. This systematic re-view is expected to serve as a useful reference for research on smart irrigation management methods.

Origin-Destination (OD) traffic flow estimations from traffic sensor data play an important role for transportation planning and management. This paper proposes a novel method to compare OD traffic estimated matrices (using data from traffic sensors). The proposed method uses the estimated OD traffic flow values together with COVID-19 incidence data in order to build a sequence of temporal graphs that are fed into a machine learning (ML) model. The ML model uses the input information to estimate/predict one-week ahead COVID-19 incidence data. A tailored Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) model is designed adapted to the input information. The paper evaluates the proposed method with 3 different OD estimation alternatives and compares the accuracy achieved by different configurations of the ML model with a traffic agnostic baseline model. Data from 44 provinces in Spain during 2021 providing daily COVID-19 incidence data and 635 geo-located traffic sensors providing monthly traffic counts are used to evaluate the results. The 3 traffic-aware OD estimation methods were able to outperform the baseline model, achieving model gains up to 136%. The major application of the results of this paper is a novel mechanism to validate prior OD traffic matrices.

Ovarian cancer (OC) is one of the most common types of cancer in women. Surgery and chemotherapy are still the most common forms of treatment; however, their success depends on lots of factors describing the type of cancer, the size, shape, and its origin, and thus early and accurate detection could bring lots of benefits to increasing survival rate by applying custom/ personalized and effective treatment. This is why many researchers aim to obtain accurate computer-aided diagnosis (CAD) systems to assist in the early detection and diagnosis of such diseases. The current paper presents a systematic review of new trends in designing different deep learning-based intelligent systems for accurate OC detection and diagnosis. The paper presents the advantages of using deep learning approaches for OC diagnosis, the most used methods, and datasets. It performs a detailed analysis concerning the most preferred, effective, and accurate architecture. 95 articles published in journals and impact conferences were investigated between 2018 and 2024, focusing on 2021 and 2024. All included studies are indexed in PubMed, Scopus, or ISI Web of Science. The authors of the analyzed articles used private databases (the majority) and public databases. Neural networks and combined DL systems recently used for ovarian tumor detection, classification, and segmentation were investigated. The performances obtained by the most relevant systems were also presented. Finally, a comparison with other reviews in the field highlighted the advantages of this article.

Reinforcement learning (RL) has seen an uptick in research interest in recent years, with many papers published in a plethora of different fields, topics and applications. A lot of that can be attributed to the recent advancements in machine learning (ML) and deep learning (DL) as a whole, the power of deep neural networks and the incorporation of them into reinforcement learning algorithms and techniques. This marriage of deep neural networks and traditional reinforcement learning methods has enabled reinforcement learning algorithms to achieve incredible results in use-cases that were previously deemed to be too complex. One of these highly complex scenarios is the realm of flight. In the last few years the number of papers published in this field has increased dramatically, but there is a fairly big divide between two major categories (quadcopters vs. fixed-wing aircraft). There is published work focusing on reinforcement learning using quadcopters, also known as drones, and there is published work focusing on fixed-wing aircraft, the more traditional aircraft, commonly referred to as airplanes. This paper focuses on the latter and will give an overview over the current state of reinforcement learning in the field of fixed-wing aviation. It will look into available toolkits usable for research as well as give an overview of different fields and tasks within reinforcement learning for fixed-wing aircraft control tasks. It contributes by providing detailed information about the methodologies used in each paper, while pointing out each paper’s contributions as well. A total of 48 papers on fixed-wing RL and airplane control are discussed. With the main focus lying on papers published post 2015, after the publication of Mnih et al.’s impactful deep RL paper.

The advent of the Artificial Intelligent Internet of Things (AIoT) has sparked a revolution in the deployment of intelligent systems, driving the need for innovative data processing techniques. Due to escalating data privacy concerns and the immense volume of data produced by IoT devices, decentralized and distributed learning methods that are rapidly replacing traditional centralized learning play a pivotal role. As AIoT systems become increasingly ubiquitous, the accompanying computational and storage demands necessitate a departure from conventional paradigms towards more scalable, distributed, and decentralized architectures. This paper delves into the background of AIoT, with a particular focus on the evolution of distributed and decentralized learning mechanisms that operate without the need for centralized data collection, thus aligning with the General Data Protection Regulation (GDPR) for enhanced data privacy. The various distributed and decentralized learning strategies are the focus of this paper that facilitate collaborative model training across multiple AIoT nodes, thereby not only improving the performance of the AIoT system but also mitigating the risks of data concentration. The review further explores the adaptability of AI algorithms in these distributed settings, assessing their potential to optimize system performance and learning efficacy. The paper concludes with some use cases and lessons learned for decentralized and distributed learning in various AIoT areas.

The power grids nowadays are facing increasing complexity and uncertainty due to the continuously growing penetration of renewable energy sources, such as photovoltaic (PV) and wind power, as well as the emerging uncertain and dynamic nature of demand-side factors such as electric vehicles, portable energy storage, etc. To effectively manage these challenges, artificial intelligence (AI) technologies, particularly model-free deep reinforcement learning (DRL), have risen as a powerful tool for power system control. This paper presents an in-depth review of the state-of-the-art applications of model-free DRL in power system control. The review is focused on various model-free DRL approaches utilized in addressing uncertainty caused by stochastic factors from renewable generations, demand-side dynamics, and power system contingencies. Specifically, it investigates how model-free DRL techniques are employed to facilitate decision-making in the frequency control, voltage control, and optimal power flow control in the grid. The benefits, challenges, and limitations of these technologies are revealed, shedding light on recent advancements in the field and showcasing the performance of these methods across diverse power system scenarios. By synthesizing the findings from extensive research, this paper also highlights the limitations, key future research directions, and recommendations for deploying model-free DRL in power system control.

The usage of artificial intelligence and machine learning in wireless communications is the stepping stone towards a technological breakthrough in the current limitations of wireless communication systems. The trend of future coding schemes towards 6G appears to be based on rateless schemes and machine learning. Channel coding is important when transmitting data or information reliably as it provides error-correcting purposes. However, there is still a demand for more research regarding machine learning for channel coding. There is also a lack of a specific term or classification for existing machine learning applications for channel coding. This paper explores and compiles current trending machine learning techniques for channel coding. We are also introducing and proposing a new type of machine learning classification for channel coding purposes, as well as surveying some of the papers that fall under the respective class. This paper also discusses current challenges and future machine learning trends for channel coding, which are expected to impact future wireless communications development, especially in channel coding advancements.

Situation Awareness (SA) is a process of sensing, understanding and predicting the environment and is an important component in complex systems. The reception of information from the environment tends to be continuous and of a multimodal nature. AI technologies provide a more efficient and robust support by subdividing the different stages of SA objectives into tasks such as data fusion, representation, classification, and prediction. This paper provides an overview of AI and multimodal methods used to build, enhance and evaluate SA in a variety of environments and applications. Emphasis is placed on enhancing perceptual integrity and persistence. Research indicates that the integration of artificial intelligence and multimodal approaches has significantly enhanced perception and comprehension in complex systems. However, there remains a research gap in projecting future situations and effectively fusing multimodal information. This paper summarizes some of the use cases and lessons learned where AI and multimodal techniques have been used to deliver SA. Future perspectives and challenges are proposed, including more comprehensive predictions, greater interpretability, and more advanced visual information.

Human Digital Twins (HDTs) have emerged as a key technology in digitalizing human-centered applications, able to enhance decision-making, personalize healthcare, and optimize workplace environments. However, despite a growing research body, there exists a critical lack of guidance for designing sophisticated, user-centric HDTs. In addressing this gap, this paper reports a systematic literature review of 44 papers in the field of HDTs (published between 2022 and 2023) to distill key design process insights and identify gaps in the current understanding and approaches to HDT design. Based on insights from this review, we introduce ETHICA, a systematic methodology that advocates for an iterative development process, emphasizing stakeholder collaboration and focusing on ethical and user-centric principles throughout the design life cycle. The resulting ETHICA methodology offers a robust blueprint for constructing sophisticated HDTs that harmonizes technological advancements with human-centered design and ethical considerations, encouraging a shift towards more holistic and human-centric approaches in the emerging field of Digital Twin technologies.

This paper lays the foundations for Physical Layer Security (PLS) as a native 6G communication operation mode. 6G mobile network will enable intelligent applications, automated services, and low-latency connectivity to data networks. Security performance improvements become vital as 6G ubiquitously integrates with critical infrastructure. This paper presents 6G PLS frameworks that combine a Deep Neural Network (DNN) with a shared key-based PLS scheme at the decoding stage to achieve higher security performance. The paper analyzes and models an Artificial Intelligence (AI)/Machine Learning (ML) PLS Layer-1 security detection scheme that achieves an impressive approximately $10-15$ dB of improvement in Signal to Noise Ratio (SNR) performance over the linear PLS detection model in multiple fading environments modelled in COST 259 channel model and accompanying AWGN noise prior to error correction coding (ECC). An analysis of raw BER versus SNR is presented for multiple MIMO antenna sizes and codebook modulation orders. An analysis of the scheme shows that eavesdroppers cannot perfectly decode the secret information even under significantly improved SNR case scenarios. In contrast, legitimate receivers achieve nearly perfect secrecy at lower SNR cases by adopting the ML-based PLS model. In addition, the paper develops the theory and analysis, for the first time to our knowledge, of Alamouti Space-Time Coding (STC) over adjacent periods within a shared key-based PLS scheme with 2M transmit and 2M receive antennas. New modes of STC-based PLS show vast gains of approximately 15 dB over existing linear shared key-based PLS for multi-codebook modulation order in COST 259 environments and noise. Finally, the paper also proposes an operational overview of AI/ML integrated PLS with shared key-agreement protocol in an Open Radio Access Network (O-RAN) architecture model. The paper illustrates a secure, low latency, Layer-1 security O-RAN architecture scheme for 6G communication based upon “security Apps” for latency mitigation.

Nowadays, the advancements of wearable consumer devices have become a predominant role in healthcare gadgets. There is always a demand to obtain robust recognition of heterogeneous human activities in complicated IoT environments. The knowledge attained using these recognition models will be then combined with healthcare applications. In this way, the paper proposed a novel deep learning framework to recognize heterogeneous human activities using multimodal sensor data. The proposed framework is composed of four phases: employing dataset and processing, implementation of deep learning model, performance analysis, and application development. The paper utilized the recent KU-HAR database with eighteen different activities of 90 individuals. After preprocessing, the hybrid model integrating Extreme Learning Machine (ELM) and Gated Recurrent Unit (GRU) architecture is used. An attention mechanism is then included for further enhancing the robustness of human activity recognition in the IoT environment. Finally, the performance of the proposed model is evaluated and comparatively analyzed with conventional CNN, LSTM, GRU, ELM, Transformer and Ensemble algorithms. To the end, an application is developed using the Qt framework which can be deployed on any consumer device. In this way, the research sheds light on monitoring the activities of critical patients by healthcare professionals remotely. The proposed ELM-GRUaM model achieved supreme performance in recognizing multimodal human activities with an overall accuracy of 96.71% as compared with existing models.

Proton Exchange Membrane Fuel Cells (PEMFCs) play a crucial role in the advancement of clean hydrogen vehicles. Their ability to convert hydrogen into electricity makes them promising candidates to replace conventional engines. However, optimizing their performance and efficiency necessitates accurate modeling techniques capable of simulating their behavior. In this context, this paper proposes an advanced approach for precise parameter estimation in PEMFC models. Employing an Enhanced Walrus Optimization (EWO) algorithm integrated with Lévy flight exploration, the approach tackles the inherent nonlinearity of PEMFC systems. The technique aims to minimize the squared error between measured and simulated terminal voltage, thereby ensuring superior accuracy and robustness compared to established algorithms. The effectiveness of the proposed model is validated through comparisons between theoretical simulations and experimental measurements. The findings demonstrate the efficacy of the EWO algorithm, consistently outperforming previously published algorithms and achieving notably lower errors. Moreover, the incorporation of Lévy flights enhances the algorithm’s capabilities, leading to expedited convergence and more accurate parameter estimations. Beyond facilitating precise parameter estimation, this enhanced modeling strategy opens avenues for refining design and optimization strategies in fuel cell research and development. The major contributions of this paper include the enhancement of the WO algorithm, evaluation of theoretical model accuracy, and robustness assessment of the EWO in optimizing the PEMFC model. By furnishing accurate models validated through experimental evidence, this enhanced modeling strategy paves the way for refining design and optimization strategies in fuel cell research and development.

One of the most visible manifestations of the changes brought about by the digitization of everyday life is undoubtedly the spread of electronic commerce. It is difficult to think of the digital economy without considering transactions through electronic channels. In turn, the user interface (UI) is the key to e-commerce, as it is usually the first and primary point of contact between business and consumer. A key trend in e-commerce is the personalization of communications, which can improve the user experience, increase customer satisfaction and deliver tangible business benefits. Today, it is technically possible to base this personalization on an analysis of user behavior using artificial intelligence and machine learning techniques. A common form of personalization in e-commerce is the use of product recommendation systems, but the user interface can be tailored much more extensively. The approach described and discussed in this paper is a multivariant user interface that allows the layout to be tailored to the characteristics, attributes, and behaviors of customer groups generated using machine learning techniques. The results of the research carried out make it possible to verify the practicality of the proposed solution and provide an opportunity to identify development directions that take into account the potential of artificial intelligence. The application of the concept described in the paper is broad, covering all aspects of e-commerce design that require compromises when serving a single UI variant, but allow flexibility and customization for different users when serving a multivariant UI.

This paper delineates the contemporary landscape, challenges, and prospective developments in human-centred artificial intelligence (AI) within the ambit of smart farming, a pivotal element of the emergent Agriculture 5.0, supplanting Agriculture 4.0. Analogous to Industry 4.0, agriculture has witnessed a trend towards comprehensive automation, often marginalizing human involvement. However, this approach has encountered limitations in agricultural contexts for various reasons. While AI’s capacity to assume human tasks is acknowledged, the inclusion of human expertise and experiential knowledge (human-in-the-loop) often proves indispensable, corroborated by the Moravec’s Paradox: tasks simple for humans are complex for AI. Furthermore, social, ethical, and legal imperatives necessitate human oversight of AI, a stance strongly reflected in the European Union’s regulatory framework. Consequently, this paper explores the advancements in human-centred AI focusing on their application in agricultural processes. These technological strides aim to enhance crop yields, minimize labor and resource wastage, and optimize the farm-to-consumer supply chain. The potential of AI to augment human decision-making, thereby fostering a sustainable, efficient, and resilient agri-food sector, is a focal point of this discussion - motivated by the current worldwide extreme weather events. Finally, a framework for Agriculture 5.0 is presented, which balances technological prowess with the needs, capabilities, and contexts of human stakeholders. Such an approach, emphasizing accessible, intuitive AI systems that meaningfully complement human activities, is crucial for the successful realization of future Agriculture 5.0.

This research paper intends to provide real-life applications of Generative AI (GAI) in the cybersecurity domain. The frequency, sophistication and impact of cyber threats have continued to rise in today’s world. This ever-evolving threat landscape poses challenges for organizations and security professionals who continue looking for better solutions to tackle these threats. GAI technology provides an effective way for them to address these issues in an automated manner with increasing efficiency. It enables them to work on more critical security aspects which require human intervention, while GAI systems deal with general threat situations. Further, GAI systems can better detect novel malware and threatening situations than humans. This feature of GAI, when leveraged, can lead to higher robustness of the security system. Many tech giants like Google, Microsoft etc., are motivated by this idea and are incorporating elements of GAI in their cybersecurity systems to make them more efficient in dealing with ever-evolving threats. Many cybersecurity tools like Google Cloud Security AI Workbench, Microsoft Security Copilot, SentinelOne Purple AI etc., have come into the picture, which leverage GAI to develop more straightforward and robust ways to deal with emerging cybersecurity perils. With the advent of GAI in the cybersecurity domain, one also needs to take into account the limitations and drawbacks that such systems have. This paper also provides some of the limitations of GAI, like periodically giving wrong results, costly training, the potential of GAI being used by malicious actors for illicit activities etc.

Rare event detection (RED) involves the identification and detection of events characterized by low frequency of occurrences, but of high importance or impact. This paper presents a Systematic Review (SR) of rare event detection across various modalities using Machine Learning (ML) and Deep Learning (DL) techniques. This review comprehensively outlines techniques and methods best suited for rare event detection across various modalities, while also highlighting future research prospects. To the extent of our knowledge, this paper is a pioneering SR dedicated to exploring this specific research domain. This SR identifies the employed methods and techniques, the datasets utilized, and the effectiveness of these methods in detecting rare events. Four modalities concerning RED are reviewed in this SR: video, sound, image, and time series. The corresponding performances for the different ML and DL techniques for RED are discussed comprehensively, together with the associated RED challenges and limitations as well as the directions for future research are highlighted. This SR aims to offer a comprehensive overview of the existing methods in RED, serving as a valuable resource for researchers and practitioners working in the respective field.

This paper presents a systematic bibliometric analysis of the artificial intelligence (AI) domain to explore privacy protection research as AI technologies integrate and data privacy concerns rise. Understanding evolutionary patterns and current trends in this research is crucial. Leveraging bibliometric techniques, the authors analyze 8,322 papers from the Web of Science (WoS) database, spanning 1990 to 2023. The analysis highlights IEEE Transactions on Knowledge and Data Engineering and IEEE Access journals as highly influential, the former being an early contributor and the latter emerging as a pivotal source. The study demonstrates substantial disparities in scientific productivity across countries. Specifically, the top 10 countries collectively accounted for 74.8% of the articles, with China and the USA making up nearly half of the total contribution (46.1%). In contrast, regions in Africa and South America exhibited lower scientific production. The evolution of privacy preservation research is reflected, shifting from an algorithm-oriented approach to a focus on data orientation, and subsequently, to privacy solutions centered around Cloud Computing. In recent years, there has been a shift towards embracing Federated Learning and Differential Privacy. The analysis brings to light emerging themes and identifies research gaps, notably a global disparity in research output and a lag in ethical and legal inquiry. It asserts that enhanced interdisciplinary collaboration is imperative to formulate comprehensive privacy solutions for AI. Specifically, the paper imparts invaluable insights that are pivotal for effectively addressing the evolving privacy concerns in the era of AI and big data.

Artificial intelligence (AI) systems are trained to solve complex problems and learn to perform specific tasks by using large volumes of data, such as prediction, classification, recognition, decision-making, etc. In the past three decades, AI research has focused mostly on the model-centric approach compared to the data-centric approach. In the model-centric approach, the focus is to improve the code or model architecture to enhance performance, whereas in data-centric AI, the focus is to improve the dataset to enhance performance. Data is food for AI. As a result, there has been a recent push in the AI community toward data-centric AI from model-centric AI. This paper provides a comprehensive and critical analysis of the current state of research in data-centric AI, presenting insights into the latest developments in this rapidly evolving field. By emphasizing the importance of data in AI, the paper identifies the key challenges and opportunities that must be addressed to improve the effectiveness of AI systems. Finally, this paper gives some recommendations for research opportunities in data-centric AI.

ChatGPT has been acknowledged as a powerful tool that can radically boost productivity across a wide range of industries. It reveals potential in cybersecurity-related tasks such as social engineering. Nevertheless, this possibility raises important concerns regarding the thin line separating moral use of this technology from its harmful usage. It is imperative to address the challenges of distinguishing between legitimate and malevolent use of ChatGPT. This research paper investigates the many concerns of ChatGPT in cybersecurity, privacy and enterprise settings. It covers harmful attacker uses such as injecting malicious prompts, testing brute force attacks, preparing and developing ransomware attacks, etc. Defenders’ proactive activities are also addressed, highlighting ChatGPT’s significance in security operations and threat intelligence. These defensive operations are classified based on the National Institute of Standards and Technology cybersecurity framework. They involve analyzing configuration files, inquiring about authoritative server, improving security in various systems, etc. Moreover, secure enterprise practices and mitigations spread through five classes are proposed, with an emphasis on clear usage standards and guidelines establishment, personally identifiable information protection, adversarial attack prevention, watermarking generated content, etc. An integrated discussion digs into the interaction of offensive and defensive applications, covering ethical and practical concerns. Future attacks are also discussed, along with potential solutions such as content filtering and collaboration. Finally, a comparative analysis with recent research on ChatGPT security concerns is directed. The paper provides a thorough framework to comprehend the range of implications associated with ChatGPT, enabling the navigation of cybersecurity and privacy challenges.

With the rapid development of artificial intelligence (AI), especially in machine learning and deep learning technologies, the particle and impurity detection and removal processes employed in many industries have been improved. Particles and impurities of any size, shape and in any condition can be detected using advanced technology in both areas. This paper presents a comprehensive overview of research papers that discuss the application of AI techniques for the detection and removal of particles and impurities. The publications featured in this review were mainly retrieved from the Web of Science (WoS) database, covering the timeframe from 2000 to 2023. This paper also covers the review on the impurity detection and removal specifically in edible bird’s nest (EBN). The aim of this paper is to provide a valuable resource for the future development of AI applications in particle and impurity detection and removal technologies that have not been addressed in this study. Through the review and analysis of AI for particle and impurity detection and removal techniques in recent years, this paper includes the following parts: research trend in particle and impurity detection in general and AI methods in particle and impurity detection, applications of AI in particle and impurity detection in related industries including in EBN and AI applications in particle and impurity removal. This review study will offer advantages to researchers engaged in the field of AI with regards to the detection and removal of particles and impurities.

Large Language Models (LLMs) recently demonstrated extraordinary capability in various natural language processing (NLP) tasks including language translation, text generation, question answering, etc. Moreover, LLMs are new and essential part of computerized language processing, having the ability to understand complex verbal patterns and generate coherent and appropriate replies in a given context. Though this success of LLMs has prompted a substantial increase in research contributions, rapid growth has made it difficult to understand the overall impact of these improvements. Since a plethora of research on LLMs have been appeared within a short time, it is quite impossible to track all of these and get an overview of the current state of research in this area. Consequently, the research community would benefit from a short but thorough review of the recent changes in this area. This article thoroughly overviews LLMs, including their history, architectures, transformers, resources, training methods, applications, impacts, challenges, etc. This paper begins by discussing the fundamental concepts of LLMs with its traditional pipeline of the LLMs training phase. Then the paper provides an overview of the existing works, the history of LLMs, their evolution over time, the architecture of transformers in LLMs, the different resources of LLMs, and the different training methods that have been used to train them. The paper also demonstrates the datasets utilized in the studies. After that, the paper discusses the wide range of applications of LLMs, including biomedical and healthcare, education, social, business, and agriculture. The study also illustrates how LLMs create an impact on society and shape the future of AI and how they can be used to solve real-world problems. Finally, the paper also explores open issues and challenges to deploy LLMs in real-world scenario. Our review paper aims to help practitioners, researchers, and experts thoroughly understand the evolution of LLMs, pre-trained architectures, applications, challenges, and future goals.

Millimeter-wave and Terahertz communications consist of complex analog and mixed-signal transceivers where overall system performance is often limited by the weakest performing subsystem. While analog and mixed-signal integrated circuits have significantly advanced, the future of 5G and 6G transceiver design could be accelerated by including artificial intelligence. In this combination, analog integrated circuit design and operation would harness machine learning to identify, characterize, and act upon variations and anomalies in system performance. Focusing on 5G and 6G, this paper investigates solutions for a unified intelligent integrated transceiver: a conceptual combination of a traditional analog subsystem, a supporting digital subsystem that enables artificial intelligence, and dedicated feedback circuitry or sensors that monitor performance, efficiency, or reliability. Active and passive components and propagation channels are reviewed based on their merits of introducing intelligence. Holistically and for broader applicability, the paper conceptualizes and coins the notion of an “intelligent integrated system (IIS)”, which brings forward a novel unified vision and approach toward context-aware subsystems that dynamically interact with ambient and varying operating conditions. To demonstrate viability, the paper concatenates a select set of measurement results.

Detecting respiratory diseases is of utmost importance, considering that respiratory ailments represent one of the most prevalent categories of diseases globally. The initial stage of lung disease detection involves auscultation conducted by specialists, relying significantly on their expertise. Therefore, automating the auscultation process for the detection of lung diseases can yield enhanced efficiency. Artificial intelligence (AI) has shown promise in improving the accuracy of lung sound classification by extracting features from lung sounds that are relevant to the classification task and learning the relationships between these features and the different pulmonary diseases. This paper utilizes two publicly available respiratory sound recordings namely, ICBHI 2017 challenge dataset and another lung sound dataset available at Mendeley Data. Foremost in this paper, we provide a detailed exposition about employing a Convolutional Neural Network (CNN) that utilizes feature extraction from Mel spectrograms, Mel frequency cepstral coefficients (MFCCs), and Chromagram. The highest accuracy achieved in the developed classification is 91.04% for 10 classes. Extending the contribution, this paper elaborates on the explanation of the classification model prediction by employing Explainable Artificial Intelligence (XAI). The novel contribution of this study is a CNN model that classifies lung sounds into 10 classes by combining audio-specific features to enhance the classification process.

With the development of artificial intelligence, there have been many attempts to incorporate artificial intelligence into algorithmic trading. In particular, reinforcement learning, which aims to solve dynamic decision-making problems, is attracting attention because of its high utilization in algorithmic trading. In this paper, we will implement a simple Deep Reinforcement Learning (DRL) trading robot to check the performance of DRL. In addition, we tried to find out how much performance improvement can be achieved by comparing a robot that learned a single stock data with a robot that learned stock data, market index, and interest rate data. This paper aims to develop a stock investment robot using a Proximal Policy Optimization (PPO) reinforcement learning algorithm and analyze the performance of the robot. The first robot used only the stock data of APPL INC, a single stock, as input, and the second robot used stock data of APPL INC and the S&P 500 index together with US interest rate data as input data. Afterward, the stock investment performance of the two robots for APPL INC was comparatively analyzed using the test data.

Advances in deep reinforcement learning have made it possible to create artificial intelligence-based agents for games that use visual information to make decisions as accurately as humans. Novel procedures are often evaluated in two-dimensional games. However, they are relatively easy compared to three-dimensional games, which have a significantly larger state and action space and, more prominently, contain partially observable states. Thus, this paper trains agents with different reinforcement learning algorithms that work fine in contradiction of human players and in-built agents by evaluating them in the first-person shooter (FPS) game Doom using the VizDoom platform. The agents learned in three different scenarios (maps): ’ Defend the Center,’ ‘Deadly Corridor,’ and ‘Health gathering.’ C51-DDQN, DFP, and REINFORCE algorithms have been proven effective in this study. To assess how well the trained agents performed using various reinforcement learning algorithms, we compared the results of our research with other findings in the literature. Finally, this paper presents a comparative analysis and future research directions.

This paper aims to measure the level of artificial intelligence (AI) support to project management (PM) in selected service sector activities. The exploratory factor analysis was employed based on the extensive survey on AI in Slovenian companies and the multi-criteria measurement with an emphasis on value functions and pairwise comparisons in the analytic hierarchy process. The synthesis and performance sensitivity analysis results show that in the service sector, concerning all criteria, PM is with the level 0.276 best supported with AI in services of professional, scientific, and technical activities, which also stand out concerning the first-level goals in using AI solutions in a project with the value 0.284, and in successful project implementation using AI with the value 0.301. Although the lowest level of AI support to PM, which is 0.220, is in services of wholesale and retail trade and repair of motor vehicles and motorcycles, these services excel in adopting AI technologies in a project with a value of 0.277. Services of financial and insurance activities, with the level 0.257 second-ranked concerning all criteria, have the highest value of 0.269 concerning the first-level goal of improving the work of project leaders using AI. The paper, therefore, contributes to the comparison of AI support to PM in service sector activities. The results can help AI development policymakers determine which activities need to be supported and which should be set as an example. The presented methodological frame can serve to perform measurements and benchmarking in various research fields.

The rapid expansion of artificial intelligence (AI) technologies presents novel technical solutions to traditional accounting and finance problems. Despite this, scholars in accounting and finance frequently encounter difficulties navigating the extensive and intricate domain knowledge of AI and its continuously evolving literature. To address this gap, this paper conducts a qualitative survey of the implementation of AI methods in accounting and finance. The paper is structured into four sections. Firstly, we examine the conventional accounting and finance issues and their requirement for AI techniques. Secondly, to inform accounting and finance researchers about the potential of AI, we present broad categories of AI applications. Thirdly, we explore recent research on AI solutions to conventional problems. Finally, we highlight emerging trends and possible research directions.

Smart Energy (SE) has emerged as a critical technology in tackling global challenges like climate change while addressing the rising energy demands driven by today’s data-intensive industrial revolution. SE integrates information and communication technologies into energy systems, optimizing them to meet these challenges effectively. At the core of SE operations are smart meters, playing a fundamental role in ensuring efficient functionality. These devices collect data, which is then leveraged to derive Business Intelligence (BI) for operations across the entire spectrum, from the sensing infrastructure to the cloud, primarily utilizing the Internet of Things (IoT) technology framework. With the increasing complexity of operations and the growing demand for optimization and enhanced functionality, the SE technology stack is evolving to integrate across all layers and domains. This integration has led to the stratification of computational load across IoT layers, intensifying the dependence on smart meter data for BI. Consequently, smart meters themselves have evolved to become more functional and complex. This paper’s novelty lies in its comprehensive exploration of the integration of BI with smart meter data. It delves into various aspects, including the different layers of intelligent operations within SE systems, the current state of the art, and diverse implementations of smart meters and their applications across operational locations, ranging from consumers to fog computing. The paper concludes by identifying research gaps and future directions, offering insights into the evolving requirements for the next generation of SE systems and the necessary adaptations in smart metering infrastructure to support these roles. This work contributes to a better understanding of the evolving landscape of data and computation in the context of SE, facilitating more efficient and effective energy management solutions.

Technology’s fast growth has profoundly impacted myriad areas, including healthcare. Implementing 5G networks offering high-speed and low-latency communication capabilities is one of the most promising technical developments. Parallel to this, artificial intelligence (AI) has become a robust data analysis and decision-making tool. This paper examines how 5G and AI are combined in the context of intelligent healthcare systems. T5G green communication systems must overcome several challenges to satisfy the need for more user capacity, faster network speeds, cheaper pricing, and less resource use. By applying 5G standards, data rates, and device dependability for Industry 4.0 applications may be significantly increased. Advanced security and decreased unauthenticated assaults from various platforms are also covered in the paper. An outline of prospective new technologies and security improvements was provided to safeguard 5G-based intelligent healthcare networks. This paper identifies several research issues and potential future directions for secure 5G-based smart healthcare. This article discusses Industry 4.0, 5G standards, and new research in future wireless communications to explore current research concerns related to 5G technology. A brand-new architecture is also suggested in the paper for Industry 4.0 and 5G-enabled intelligent healthcare systems. Our method achieves an average improvement of 25% compared to existing techniques. Furthermore, we observe a 20% reduction in computational costs, making it a more efficient solution for real-world applications. These findings underscore the practical value of our research and pave the way for improved healthcare applications in 5G communication.

Over the past few decades, Industrial Control Systems (ICS) have been targeted by cyberattacks and are becoming increasingly vulnerable as more ICSs are connected to the internet. Using Machine Learning (ML) for Intrusion Detection Systems (IDS) is a promising approach for ICS cyber protection, but the lack of suitable datasets for evaluating ML algorithms is a challenge. Although a few commonly used datasets may not reflect realistic ICS network data, lack necessary features for effective anomaly detection, or be outdated. This paper introduces the ‘ICS-Flow’ dataset, which offers network data and process state variables logs for supervised and unsupervised ML-based IDS assessment. The network data includes normal and anomalous network packets and flows captured from simulated ICS components and emulated networks, where the anomalies were applied to the system through various cyberattacks. We also proposed an open-source tool, “ICSFlowGenerator,” for generating network flow parameters from Raw network packets. The final dataset comprises over 25,000,000 raw network packets, network flow records, and process variable logs. The paper describes the methodology used to collect and label the dataset and provides a detailed data analysis. Finally, we implement several ML models, including the decision tree, random forest, and artificial neural network to detect anomalies and attacks, demonstrating that our dataset can be used effectively for training intrusion detection ML models.

In recent years, Generative Adversarial Networks (GANs) have gained worldwide interest and have marked a breakthrough in deep learning, encouraging detailed studies in generating artificial images. A new Generative Adversarial Networks (GAN) is proposed to unveil how Human visual perception takes place, focusing on how human beings perceive images, firstly, coarse structures and then their details. The network called 3G-AN consists of three generation stages and a single Discriminator. In this paper, a novel three-branch generator is proposed, which takes into account Coarse, Medium, and Fine structure of a given image. Coarse RGB decomposition image provides the general structure, while Medium RGB stage provides general-fine structure. Finally, Fine RGB decomposition provides fine details of the image. The proposal is tested on MNIST, CIFAR10, and Celebrity faces databases, generating realistic images with almost no anomalies. The RGB decomposition into coarse, medium, and fine, allows to understand the composition of an image from a structural point of view. The qualitative analysis carried out in this research paper outperforms the six most competitive models existing in the literature.

Domestic violence is an issue of great importance that exceeds socioeconomic backgrounds and cultural boundaries. It stems from factors such as power struggle, mental health issue, financial hardship, substance abuse, among others. Technology can play a vital role in not only detecting and mitigating instances of domestic violence, but also providing essential support and resources to its victims. This review paper examines the latest technological innovations for tackling domestic violence. It describes a range of technology platforms and tools, and discusses their capabilities and shortcomings. Firstly, the review methodology is given including the aims and objectives of the review, the search strategy, and the selection of sources. Next, the technological innovations in the context of domestic violence are defined. Then, the paper presents the technological approaches developed to tackle domestic violence through: (i) analysis of data shared through digital platforms, (ii) analysis of data captured by ambient sensors, (iii) analysis of data collected by smartphones, (iv) analysis of data obtained by wearable sensors, (v) protection of online activities, (vi) prevention of non-contact harassment, (vii) deployment of anti-stalking and anti-monitoring measures, and (viii) use of virtual reality techniques. Next, discussions on the capabilities and applications of these technological innovations across different aspects of domestic violence are presented. The paper also addresses the challenges and limitations associated with these innovations, and gives future directions and recommendations for further research and development.

Cybersecurity, as a crucial aspect of the information society, requires significant attention. Fortunately, the concept of trust, originating from the field of sociology, has been under extensive research in order to enhance cybersecurity by evaluating the trustworthiness of nodes with artificial intelligence (AI) techniques in distributed networks (DNs). However, the scalability issues faced by AI-enabled trust hinder its integration with the DNs. Currently, there is a lack of a comprehensive review article that explores the current state of AI-enabled trust development applications. This paper aims to address this gap by providing a review of the state-of-the-art AI-enabled trust in DNs. This review focuses on the concept of trust and how it can be facilitated through AI, particularly utilizing machine learning and deep learning methods. Additionally, the paper provides a comprehensive comparison and analysis of three key domains in the field of AI-enabled trust: trust management (TM), intrusion detection system (IDS), and recommender systems (RS). Some open problems and challenges that currently exist in the field are manifested, and some suggestions for future work are presented.

Body language is a nonverbal communication process consisting of movements, postures, gestures, and expressions of the body or body parts. Body language expresses human feelings, thoughts, and intentions. It also reveals physical and psychological health conditions: abnormal activities inform peoples’ health conditions, facial expressions indicate their emotional states and abnormal body actions convey specific diseases’ external signs and symptoms. We can observe the importance of studying the body language of people with health conditions through many reports in literature written by healthcare (medical) and artificial intelligence researchers. This paper comprehensively reviews artificial intelligence-based articles that have studied patients’ body language. We also conduct different descriptive and exploratory examinations of the findings using data analysis techniques, which provide more authentic domain knowledge of abnormal activities, abnormal body actions, and more precise analysis of methodologies used in machine learning tasks for studying these abnormalities. The paper’s results are essential for developing intelligent automated systems that accurately evaluate patients’ physical and psychological conditions, precisely identify external signs and symptoms of diseases, and adequately monitor patients’ health conditions.

Facial expression recognition is an important research direction of emotion computing and has broad application prospects in human-computer interaction. However, noise such as illumination and occlusion in natural environment brings many challenges to facial expression recognition. In order to solve the problems such as low recognition rate of facial expression in natural environment, unable to highlight the characteristics of facial expression in global facial research, and misclassification caused by the similarity between negative expressions. In this paper, a multi-region coordinate attentional residual expression recognition model (MrCAR) is proposed. The model is mainly composed of the following three parts: 1) multi-region input: MTCNN is used for face detection and alignment processing, and the eyes and mouth parts are further cropped to obtain multi-region pictures. Through multi-region input, local details and global features are more easily obtained, which reduces the influence of complex environmental noise and highlights the facial features. 2) Feature extraction module: On the basis of residual element, CA-Net and multi-scale convolution were added to obtain coordinate residual attention module, through which the model’s ability to distinguish subtle changes of expression and the utilization rate of key features were improved; 3) Classifier: Arcface Loss is used to enhance intra-class tightness and inter-class difference at the same time, thus reducing the wrong classification of negative expressions by the model. Finally, the accuracy rates of CK+, JAFFE, FER2013 and RAF-DB were 98.78%, 99.09%, 74.50% and 88.26%, respectively. The experimental results show that compared with many advanced models, the MrCAR model in this paper is more competent for the task of expression classification.

Image matting is an important computer vision problem. Many existing matting methods leverage a hand-made trimap to provide auxiliary information, which is expensive and time-consuming for real-world applications. In recent years, some trimap-free methods have been proposed, which completely get rid of any user input. However, their performance lag far behind trimap-based methods due to the ambiguity problem. This paper proposes a matting method that uses flexible interactive guidance as user hints, which means the proposed method can use trimap, scribblemap, clickmap, and bounding box as guidance information or can even work without any guidance input. Our goal is to maintain accuracy while simplifying input. To achieve this, we propose Progressive Trimap Deformation (PTD) scheme that gradually transforms the input trimaps into scribblemaps during training. To enable bounding box input, based on the same network, this paper proposes Progressive Bounding Box Deformation (PBD) scheme that gradually turns trimaps into bounding box masks during training. To further ensure the stability of training and enhance performance, this paper also introduces the Random Deformation Degree scheme. Experiments show that the proposed method can achieve competitive results compared with existing trimap-based and trimap-free methods.

The Reinforcement Learning (RL) paradigm is showing promising results as a generic purpose framework for solving decision-making problems (e.g., robotics, games, finance). The aim of this work is to reduce the learning barriers and inspire young students, researchers and educators to use RL as an obvious tool to solve robotics problems. This paper provides an intelligible step-by-step RL problem formulation and the availability of an easy-to-use interactive simulator for students at various levels (e.g., undergraduate, bachelor, master, doctorate), researchers and educators. The interactive tool facilitates the familiarization with the key concepts of RL, its problem formulation and implementation. In this work, RL is used for solving a robotics 2D navigational problem where the robot needs to avoid collisions with obstacles while aiming to reach a goal point. A navigational problem is simple and convenient for educational purposes, since the outcome is unambiguous (e.g., the goal is reached or not, a collision happened or not). Due to a lack of open-source graphical interactive simulators concerning the field of RL, this paper combines theoretical exposition with an accessible practical tool to facilitate the apprehension. The results demonstrated are produced by a Python script that is released as open-source to reduce the learning barriers in such innovative research topic in robotics.