Search

This paper presents a novel approach to enhancing the security and reliability of drone communications through the integration of Quantum Random Number Generators (QRNG) in Frequency Hopping Spread Spectrum (FHSS) systems. We propose a multi-drone framework that leverages QRNG technology to generate truly random frequency hopping sequences, significantly improving resistance against jamming and interception attempts. Our method introduces a concurrent access protocol for multiple drones to share a QRNG device efficiently, incorporating robust error handling and a shared memory system for random number distribution. The implementation includes secure communication protocols, ensuring data integrity and confidentiality through encryption and Hash-based Message Authentication Code (HMAC) verification. We demonstrate the system’s effectiveness through comprehensive simulations and statistical analyses, including spectral density, frequency distribution, and autocorrelation studies of the generated frequency sequences. The results show a significant enhancement in the unpredictability and uniformity of frequency distributions compared to traditional pseudo-random number generator-based approaches. Specifically, the frequency distributions of the drones exhibited a relatively uniform spread across the available spectrum, with minimal discernible patterns in the frequency sequences, indicating high unpredictability. Autocorrelation analyses revealed a sharp peak at zero lag and linear decrease to zero values for other lags, confirming a general absence of periodicity or predictability in the sequences, which enhances resistance to predictive attacks. Spectral analysis confirmed a relatively flat power spectral density across frequencies, characteristic of truly random sequences, thereby minimizing vulnerabilities to spectral-based jamming. Statistical tests, including Chi-squared and Kolmogorov-Smirnov, further confirm the unpredictability of the frequency sequences generated by QRNG, supporting enhanced security measures against predictive attacks. While some short-term correlations were observed, suggesting areas for improvement in QRNG technology, the overall findings confirm the potential of QRNG-based FHSS systems in significantly improving the security and reliability of drone communications. This work contributes to the growing field of quantum-enhanced wireless communications, offering substantial advancements in security and reliability for drone operations. The proposed system has potential applications in military, emergency response, and secure commercial drone operations, where enhanced communication security is paramount.

This paper introduces an innovative framework for visualisation design ideation, which includes a collection of terms for creative visualisation design, the five-step process, and an implementation called VisAlchemy. Throughout the visualisation ideation process, individuals engage in exploring various concepts, brainstorming, sketching ideas, prototyping, and experimenting with different methods to visually represent data or information. Sometimes, designers feel incapable of sketching, and the ideation process can be quite lengthy. In such cases, generative AI can provide assistance. However, even with AI, it can be difficult to know which vocabulary to use and how to strategically approach the design process. Our strategy prompts imaginative and structured narratives for generative AI use, facilitating the generation and refinement of visualisation design ideas. We aim to inspire fresh and innovative ideas, encouraging creativity and exploring unconventional concepts. VisAlchemy is a five-step framework: a methodical approach to defining, exploring, and refining prompts to enhance the generative AI process. The framework blends design elements and aesthetics with context and application. In addition, we present a vocabulary set of 300 words, underpinned from a corpus of visualisation design and art papers, along with a demonstration tool called VisAlchemy. The interactive interface of the VisAlchemy tool allows users to adhere to the framework and generate innovative visualisation design concepts. It is built using the SDXL Turbo language model. Finally, we demonstrate its use through case studies and examples and show the transformative power of the framework to create inspired and exciting design ideas through refinement, re-ordering, weighting of words and word rephrasing.

In the next decade, the amount of network traffic is estimated to reach Zettabytes. The future International Mobile Telecommunications-2030 (IMT-2030) standard of mobile networks, known as 6G, introduces an important paradigm shift in the context of wireless communication systems thanks to capabilities such as low latency and high data rates. Official documents on 6G standardization have been released by the International Telecommunication Union (ITU). However, other visions and use cases of 6G have been proposed by industrial stakeholders and research institutions, thus generating a multitude of use cases and usage scenarios that are only apparently different from each other. This paper would contribute to providing a holistic vision of the 6G-enabled use cases and potentially impacted vertical market sectors. The differences and similarities between what has been proposed by ITU and other initiatives are identified through a comparison based on the technological characterization of use cases and of the considered vertical market sectors. The main findings presented in this paper demonstrate that many of the use cases proposed by ITU and by the other initiatives are almost identical in many cases.

In software engineering, pattern papers serve the purpose of providing a description of a generalized, reusable solution to recurring design problems, based on practical experience and established best practices. This paper presents an architectural pattern for a Secure Auditable Registry service based on Message-Oriented Middleware to be used in large-scale IoT systems that must provide auditing capabilities to external entities. To prepare the pattern, the direct experience in applying the pattern solution in an industry-funded R&D project has been a key aspect because it has allowed us to gain a deep understanding of the problem and the solution, and it has contributed to the correctness and real-world applicability of the pattern as described. To further improve the quality of the paper, we have followed the commonly accepted practices in pattern development (including peer reviews) to ensure that the core aspects of the solution are correctly represented and that the description allows it to be applicable to similar problems in other domains, such as healthcare, autonomous devices, banking, food tracing or manufacturing to name a few. The work done in applying this pattern confirms that it solves a recurring problem for IoT systems, but also that it can be adopted in other domains, providing an effective solution in order to achieve enhancement of the auditability capabilities of the target systems. This pattern will be part of a pattern language (i.e., a family of related patterns) that we are developing for transitioning from legacy systems to IoT with an emphasis on security.

Maternal mortality (MM) is considered one of the major worldwide concerns. Despite the advances of artificial intelligence (AI) in healthcare, the lack of transparency in AI models leads to reluctance to adopt them. Employing explainable artificial intelligence (XAI) thus helps improve the transparency and effectiveness of AI-driven healthcare solutions. Accordingly, this article proposes a complete framework integrating an Internet of Medical Things (IoMT) architecture with an XAI-based deep learning model. The IoMT system continuously monitors pregnant women’s vital signs, while the XAI model analyzes the collected data to identify risk factors and generate actionable insights. Additionally, an efficient IoMT transmission model is developed to ensure reliable data transfer with the best-required system quality of service (QoS). Further analytics are performed on the data collected from different regions in a country to address high-risk cities. The experiments demonstrate the effectiveness of the proposed framework by achieving an accuracy of 80% for patients and 92.6% for regional risk prediction and providing interpretable explanations. The XAI-generated insights empower healthcare providers to make informed decisions and implement timely interventions. Furthermore, the IoMT transmission model ensures efficient and secure data transfer.

Mobile communication is ubiquitous in everyday life. The fifth generation of mobile networks (5G) introduced 5G New Radio as a radio access technology that meets current bandwidth, quality, and application requirements. Network steganographic channels that hide secret message transfers in an innocent carrier communication are a particular threat in mobile communications as these channels are often used for malware, ransomware, and data leakage. We systematically analyze the protocol stack of the 5G–air interface for its susceptibility to network steganography, addressing both storage and timing channels. To ensure large coverage, we apply hiding patterns that collect the essential ideas used to create steganographic channels. Based on the results of this analysis, we design and implement a network covert storage channel, exploiting reserved bits in the header of the Packet Data Convergence Protocol (PDCP). the covert sender and receiver are located in a 5G base station and mobile device, respectively. Furthermore, we sketch a timing channel based on a recent overshadowing attack. We evaluate our steganographic storage channel both in simulation and real-world experiments with respect to steganographic bandwidth, robustness, and stealthiness. Moreover, we discuss countermeasures. Our implementation demonstrates the feasibility of a covert channel in 5G New Radio and the possibility of achieving large steganographic bandwidth for broadband transmissions. We also demonstrate that the detection of the channel by a network analyzer is possible, limiting its scope to application scenarios where operators are unaware or ignorant of this threat.

Mobile communications have experienced exponential growth both in connectivity and multimedia traffic in recent years. To support this tremendous growth, device-to-device (D2D) communications play a significant role in 5G and beyond 5G networks. However, enabling D2D communications in an underlay, heterogeneous cellular network poses two major challenges. First, interference management between D2D and cellular users directly affects a system’s performance. Second, achieving an acceptable level of link quality for both D2D and cellular networks is necessary. An optimum resource allocation is required to mitigate the interference and improve a system’s performance. In this paper, we provide a solution to interference management with an acceptable quality of services (QoS). To this end, we propose a machine learning-based resource allocation method to maximize throughput and achieve minimum QoS requirements for all active D2D pairs and cellular users. We first solve a resource optimization problem by allocating spectrum resources and controlling power transmission on demand. As resource optimization is an integer nonlinear programming problem, we address this problem by proposing a deep Q-network-based reinforcement learning algorithm (DRL) to optimize the resource allocation issue. The proposed DRL algorithm is trained with a decision-making policy to obtain the best solution in terms of spectrum efficiency, computational time, and throughput. The system performance is validated by simulation. The results show that the proposed method outperforms the existing ones.

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.

The healthcare sector has changed dramatically in recent years due to depending more and more on big data to improve patient care, enhance or improve operational effectiveness, and forward medical research. Protecting patient privacy in the era of digital health records is a major challenge, as there could be a chance of privacy leakage during the process of collecting patient data. To overcome this issue, we propose a secure, privacy-preserving scheme for healthcare data to ensure maximum privacy of an individual while also maintaining their utility and allowing for the performance of queries based on sensitive attributes under differential privacy. We implemented differential privacy on two publicly available healthcare datasets, the Breast Cancer Prediction Dataset and the Nursing Home COVID-19 Dataset. Moreover, we examined the impact of varying privacy parameter (ε) values on both the privacy and utility of the data. A significant part of this study involved the selection of ε, which determines the degree of privacy protection. We also conducted a computational time comparison by performing multiple complex queries on these datasets to analyse the computational overhead introduced by differential privacy. The outcomes demonstrate that, despite a slight increase in query processing time, it remains within reasonable bounds, ensuring the practicality of differential privacy for real-time applications.

Phishing email assaults have been a prevalent cybercriminal tactic for many decades. Various detectors have been suggested over time that rely on textual information. However, to address the growing prevalence of phishing emails, more sophisticated techniques are required to use all aspects of emails to improve the detection capabilities of machine learning classifiers. This paper presents a novel approach to detecting phishing emails. The proposed methodology combines ensemble learning techniques with various variables, such as word frequency, the presence of specific keywords or phrases, and email length, to improve detection accuracy. We provide two approaches for the planned task; The first technique employs ensemble learning soft voting, while the second employs weighted ensemble learning. Both strategies use distinct machine learning algorithms to concurrently process the characteristics, reducing their complexity and enhancing the model’s performance. An extensive assessment and analysis are conducted, considering unique criteria designed to minimize biased and inaccurate findings. Our empirical experiments demonstrates that using ensemble learning to merge attributes in the evolution of phishing emails showcases the competitive performance of ensemble learning over other machine learning algorithms. This superiority is underscored by achieving an F1-score of 0.90 in the weighted ensemble method and 0.85 in the soft voting method, showcasing the effectiveness of this approach.

TinyML/DL is a new subfield of ML that allows for the deployment of ML algorithms on low-power devices to process their own data. The lack of resources restricts the aforementioned devices to running only inference tasks (static TinyML), while training is handled by a more computationally efficient system, such as the cloud. In recent literature, the focus has been on conducting real-time on-device training tasks (Reformable TinyML) while being wirelessly connected. With data processing being shift to edge devices, the development of decentralized federated learning (DFL) schemes becomes justified. Within these setups, nodes work together to train a neural network model, eliminating the necessity of a central coordinator. Ensuring secure communication among nodes is of utmost importance for protecting data privacy during edge device training. Swarm Learning (SL) emerges as a DFL paradigm that promotes collaborative learning through peer-to-peer interaction, utilizing edge computing and blockchain technology. While SL provides a robust defense against adversarial attacks, it comes at a high computational expense. In this survey, we emphasize the current literature regarding both DFL and TinyML/DL fields. We explore the obstacles encountered by resource-starved devices in this collaboration and provide a brief overview of the potential of transitioning to Swarm Learning.

When developing a distributed application, several issues need to be handled, and software components should include some mechanisms to make their execution resilient when network faults, delays, or tampering occur. For example, synchronous calls represent a too-tight connection between a client requesting a service and the service itself, whereby potential network delays or temporary server overloads would keep the client side hanging, exposing it to a domino effect. The proposed approach assists developers in dealing with such issues by providing an automatic tool that enhances a distributed application using simple blocking calls and makes it robust in the face of adverse events. The proposed devised solution consists in automatically identifying the parts of the application that connect to remote services using simple synchronous calls and substituting them with a generated customized snippet of code that handles potential network delays or faults. To accurately perform the proposed transformation, the devised tool finds application code statements that are data-dependent on the results of the original synchronous calls. Then, for the dependent statements, a solution involving guarding code, proper synchronization, and timeouts is injected. We experimented with the analysis and transformation of several applications and report a meaningful example, together with the analysis of the results achieved.

With the increasing use of online meetings, there is a growing need for efficient tools that can automatically generate meeting minutes from recorded sessions. Current solutions often rely on proprietary systems, limiting adaptability and flexibility. This paper investigates whether various open-source models and methods such as audio-to-text conversion, summarization, keyword extraction, and optical character recognition (OCR) can be integrated to create a meeting minutes generation tool for recorded video presentations. For this purpose, a series of evaluations are conducted to identify suitable models. Then, the models are integrated into a system that is modular yet accurate. The utilization of an open-source approach ensures that the tool remains accessible and adaptable to the latest innovations, thereby ensuring continuous improvement over time. Furthermore, this approach also benefits organizations and individuals by providing a cost-effective and flexible alternative. This work contributes to creating a modular and easily extensible open-source framework that integrates several advanced technologies and future new models into a cohesive system. The system was evaluated on ten videos created under controlled conditions, which may not fully represent typical online presentation recordings. It showed strong performance in audio-to-text conversion with a low word-error rate. Summarization and keyword extraction were functional but showed room for improvement in terms of precision and relevance, as gathered from the users’ feedback. These results confirm the system’s effectiveness and efficiency in generating usable meeting minutes from recorded presentation videos, with room for improvement in future works.

Federated learning (FL) is creating a paradigm shift in machine learning by directing the focus of model training to where the data actually exist. Instead of drawing all data into a central location, which raises concerns about privacy, costs, and delays, FL allows learning to take place directly on the device, keeping the data safe and minimizing the need for transfer. This approach is especially important in areas like healthcare, where protecting patient privacy is critical, and in industrial IoT settings, where moving large numbers of data is not practical. What makes FL even more compelling is its ability to reduce the bias that can occur when all data are centralized, leading to fairer and more inclusive machine learning outcomes. However, it is not without its challenges—particularly with regard to keeping the models secure from attacks. Nonetheless, the potential benefits are clear: FL can lower the costs associated with data storage and processing, while also helping organizations to meet strict privacy regulations like GDPR. As edge computing continues to grow, FL’s decentralized approach could play a key role in shaping how we handle data in the future, moving toward a more privacy-conscious world. This study identifies ongoing challenges in ensuring model security against adversarial attacks, pointing to the need for further research in this area.

With the increasing demand for expected data volume daily, current telecommunications infrastructure can not meet requirements without using enhanced technologies adopted by 5G and beyond networks. Due to their diverse features, 5G technologies and services will be phenomenal in the coming days. Proper planning procedures are to be adopted to provide cost-effective and quality telecommunication services. In this paper, we planned 5G network deployment in two frequency ranges, 3.5 GHz and 28 GHz, using a mixed cell structure. We used metaheuristic approaches such as Grey Wolf Optimization (GWO), Sparrow Search Algorithm (SSA), Whale Optimization Algorithm (WOA), Marine Predator Algorithm (MPA), Particle Swarm Optimization (PSO), and Ant Lion Optimization (ALO) for optimizing the locations of remote radio units. The comparative analysis of metaheuristic algorithms shows that the proposed network is efficient in providing an average data rate of 50 Mbps, can meet the coverage requirements of at least 98%, and meets quality-of-service requirements. We carried out the case study for an urban area and another suburban area of Kathmandu Valley, Nepal. We analyzed the outcomes of 5G greenfield deployment and 5G deployment using existing 4G infrastructure. Deploying 5G networks using existing 4G infrastructure, resources can be saved up to 33.7% and 54.2% in urban and suburban areas, respectively.

The Future Internet aims to revolutionize digital interaction by integrating advanced technologies like AI and IoT, enabling a dynamic and resilient network. It envisions emotionally intelligent systems that can interpret and respond to human feelings, creating immersive, empathy-driven learning experiences. This evolution aspires to form a responsive digital ecosystem that seamlessly connects technology and human emotion. This paper presents a computational model aimed at enhancing the emotional aspect of learning experiences within museum environments. The model is designed to represent and manage affective and emotional feedback, with a focus on how emotions can significantly impact the learning process in a museum context. The proposed model seeks to identify and quantify emotions during a visitor’s engagement with museum exhibits. To achieve this goal, we primarily explored the following: (i) methods and techniques for assessing and recognizing emotional responses in museum visitors, (ii) feedback management strategies based on the detection of visitors’ emotional states. Then, the methodology was tested on 1000 cases via specific questionnaire forms, along with the presentation of images and short videos, and the results of data analysis are reported. The findings contribute toward establishing a comprehensive methodology for the identification and quantification of the emotional state of museum visitors.

Leak detection in oil and gas pipeline networks is a climacteric and frequent issue in the oil and gas field. Many establishments have long depended on stationary hardware or traditional assessments to monitor and detect abnormalities. Rapid technological progress; innovation in engineering; and advanced technologies providing cost-effective, rapidly executed, and easy to implement solutions lead to building an efficient oil pipeline leak detection and real-time monitoring system. In this area, wireless sensor networks (WSNs) are increasingly required to enhance the reliability of checkups and improve the accuracy of real-time oil pipeline monitoring systems with limited hardware resources. The real-time transient model (RTTM) is a leak detection method integrated with LoRaWAN technology, which is proposed in this study to implement a wireless oil pipeline network for long distances. This study will focus on enhancing the LoRa network parameters, e.g., node power consumption, average packet loss, and delay, by applying several machine learning techniques in order to optimize the durability of individual nodes’ lifetimes and enhance total system performance. The proposed system is implemented in an OMNeT++ network simulator with several frameworks, such as Flora and Inet, to cover the LoRa network, which is used as the system’s network infrastructure. In order to implement artificial intelligence over the FLoRa network, the LoRa network was integrated with several programming tools and libraries, such as Python script and the TensorFlow libraries. Several machine learning algorithms have been applied, such as the random forest (RF) algorithm and the deep extreme learning machine (DELM) technique, to develop the proposed model and improve the LoRa network’s performance. They improved the LoRa network’s output performance, e.g., its power consumption, packet loss, and packet delay, with different enhancement ratios. Finally, a hybrid deep extreme learning machine model was built and selected as the proposed model due to its ability to improve the LoRa network’s performance, with perfect prediction accuracy, a mean square error of 0.75, and an exceptional enhancement ratio of 39% for LoRa node power consumption.

Modern ICT infrastructures, i.e., cyber-physical systems and critical infrastructures relying on interconnected IT (Information Technology)- and OT (Operational Technology)-based components and (sub-)systems, raise complex challenges in tackling security and safety issues. Nowadays, many security controls and mechanisms have been made available and exploitable to solve specific security needs, but, when dealing with very complex and multifaceted heterogeneous systems, a methodology is needed on top of the selection of each security control that will allow the designer/maintainer to drive her/his choices to build and keep the system secure as a whole, leaving the choice of the security controls to the last step of the system design/development. This paper aims at providing a comprehensive methodological approach to design and preliminarily implement an Open Platform Architecture (OPA) to secure the cyber-physical systems of critical infrastructures. Here, the Open Platform Architecture (OPA) depicts how an already existing or under-design target system (TS) can be equipped with technologies that are modern or currently under development, to monitor and timely detect possibly dangerous situations and to react in an automatic way by putting in place suitable countermeasures. A multifaceted use case (UC) that is able to show the OPA, starting from the security and safety requirements to the fully designed system, will be developed step by step to show the feasibility and the effectiveness of the proposed methodology.

Mobile gaming accounts for more than 50% of global online gaming revenue, surpassing console and browser-based gaming. The success of mobile gaming titles depends on optimizing applications for the specific hardware constraints of mobile devices, such as smaller displays and lower computational power, to maximize battery life. Additionally, these applications must dynamically adapt to the variations in network speed inherent in mobile environments. Ultimately, user engagement and satisfaction are critical, necessitating a favorable comparison to browser and console-based gaming experiences. While Quality of Experience (QoE) subjective evaluations through user surveys are the most reliable method for assessing user perception, various factors, termed influence factors (IFs), can affect user ratings of stimulus quality. This study examines human influence factors in mobile gaming, specifically analyzing the impact of user delight towards displayed content and the effect of gaze tracking. Using Pupil Core eye-tracking hardware, we captured user interactions with mobile devices and measured visual attention. Video stimuli from eight popular games were selected, with resolutions of 720p and 1080p and frame rates of 30 and 60 fps. Our results indicate a statistically significant impact of user delight on the MOS for most video stimuli across all games. Additionally, a trend favoring higher frame rates over screen resolution emerged in user ratings. These findings underscore the significance of optimizing mobile gaming experiences by incorporating models that estimate human influence factors to enhance user satisfaction and engagement.

Nowadays, Edge Intelligence has seen unprecedented growth in most of our daily life applications. Traditionally, most applications required significant efforts into data collection for data-driven analytics, raising privacy concerns. The proliferation of specialized hardware on sensors, wearable, mobile, and IoT devices has led to the growth of Edge Intelligence, which has become an integral part of the development cycle of most modern applications. However, scalability issues hinder their wide-scale adoption. We aim to focus on these challenges and propose a scalable decentralized edge intelligence framework. Therefore, we analyze and empirically evaluate the challenges of existing methods, and design an architecture that overcomes these challenges. The proposed approach is client-driven and model-centric, allowing models to be shared between entities in a scalable fashion. We conduct experiments over various benchmarks to show that the proposed approach presents an efficient alternative to the existing baseline method, and it can be a viable solution to scale edge intelligence.

In the fourth industrial revolution, artificial intelligence and machine learning (ML) have increasingly been applied to manufacturing, particularly additive manufacturing (AM), to enhance processes and production. This study provides a comprehensive review of the state-of-the-art achievements in this domain, highlighting not only the widely discussed supervised learning but also the emerging applications of semi-supervised learning and reinforcement learning. These advanced ML techniques have recently gained significant attention for their potential to further optimize and automate AM processes. The review aims to offer insights into various ML technologies employed in current research projects and to promote the diverse applications of ML in AM. By exploring the latest advancements and trends, this study seeks to foster a deeper understanding of ML’s transformative role in AM, paving the way for future innovations and improvements in manufacturing practices.

Schizophrenia is a complex neuropsychiatric disorder characterized by disruptions in brain connectivity and cognitive functioning. Continuous monitoring of neural activity is essential, as it allows for the detection of subtle changes in brain connectivity patterns, which could provide early warnings of cognitive decline or symptom exacerbation, ultimately facilitating timely therapeutic interventions. This paper proposes a novel approach for detecting schizophrenia-related abnormalities using deep learning (DL) techniques applied to electroencephalogram (EEG) data. Using an openly available EEG dataset on schizophrenia, the focus is on preprocessed event-related potentials (ERPs) from key electrode sites and applied transfer entropy (TE) analysis to quantify the directional flow of information between brain regions. TE matrices were generated to capture neural connectivity patterns, which were then used as input for a hybrid DL model, combining convolutional neural networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The model achieved a performant accuracy of 99.94% in classifying schizophrenia-related abnormalities, demonstrating its potential for real-time mental health monitoring. The generated TE matrices revealed significant differences in connectivity between the two groups, particularly in frontal and central brain regions, which are critical for cognitive processing. These findings were further validated by correlating the results with EEG data obtained from the Muse 2 headband, emphasizing the potential for portable, non-invasive monitoring of schizophrenia in real-world settings. The final model, integrated into the NeuroPredict platform, offers a scalable solution for continuous mental health monitoring. By incorporating EEG data, heart rate, sleep patterns, and environmental metrics, NeuroPredict facilitates early detection and personalized interventions for schizophrenia patients.

The field of digital forensics relies on expertise from multiple domains, including computer science, criminology, and law. It also relies on different toolsets and an analyst’s expertise to parse enormous amounts of user-generated data to find clues that help crack a case. This process of investigative analysis is often done manually. Artificial Intelligence (AI) can provide practical solutions to efficiently mine enormous amounts of data to find useful patterns that can be leveraged to investigate crimes. Natural Language Processing (NLP) is a subdomain of research under AI that deals with problems involving unstructured data, specifically language. The domain of NLP includes several tools to parse text, including topic modeling, pairwise correlation, word vector cosine distance measurement, and sentiment analysis. In this research, we propose a digital forensic investigative technique that uses an ensemble of NLP tools to identify a person of interest list based on a corpus of text. Our proposed method serves as a type of human feature reduction, where a total pool of suspects is filtered down to a short list of candidates who possess a higher correlation with the crime being investigated.

Small datasets are frequent in some scientific fields. Such datasets are usually created due to the difficulty or cost of producing laboratory and experimental data. On the other hand, researchers are interested in using machine learning methods to analyze this scale of data. For this reason, in some cases, low-performance, overfitting models are developed for small-scale data. As a result, it appears necessary to develop methods for dealing with this type of data. In this research, we provide a new and innovative framework for regression problems with a small sample size. The base of our proposed method is the K-nearest neighbors (KNN) algorithm. For feature selection, instance selection, and hyperparameter tuning, we use the bat optimization algorithm (BA). Generative Adversarial Networks (GANs) are employed to generate synthetic data, effectively addressing the challenges associated with data sparsity. Concurrently, Deep Neural Networks (DNNs), as a deep learning approach, are utilized for feature extraction from both synthetic and real datasets. This hybrid framework integrates KNN, DNN, and GAN as foundational components and is optimized in multiple aspects (features, instances, and hyperparameters) using BA. The outcomes exhibit an enhancement of up to 5% in the coefficient of determination (R2 score) using the proposed method compared to the standard KNN method optimized through grid search.

The Internet of Medical Things (IoMT), an extension of the Internet of Things (IoT), is still in its early stages of development. Challenges that are inherent to IoT, persist in IoMT as well. The major focus is on data transmission within the healthcare domain due to its profound impact on health and public well-being. Issues such as latency, bandwidth constraints, and concerns regarding security and privacy are critical in IoMT owing to the sensitive nature of patient data, including patient identity and health status. Numerous forms of cyber-attacks pose threats to IoMT networks, making the reliable and secure transmission of critical medical data a challenging task. Several other situations, such as natural disasters, war, construction works, etc., can cause IoMT networks to become unavailable and fail to transmit the data. The first step in these situations is to recover from failure as quickly as possible, resume the data transfer, and detect the cause of faults, failures, and errors. Several solutions exist in the literature to make the IoMT resilient to failure. However, no single approach proposed in the literature can simultaneously protect the IoMT networks from various attacks, failures, and faults. This paper begins with a detailed description of IoMT and its applications. It considers the underlying requirements of resilience for IoMT networks, such as monitoring, control, diagnosis, and recovery. This paper comprehensively analyzes existing research efforts to provide IoMT network resilience against diverse causes. After investigating several research proposals, we identify that the combination of software-defined networks (SDNs), machine learning (ML), and microservices architecture (MSA) has the capabilities to fulfill the requirements for achieving resilience in the IoMT networks. It mainly focuses on the analysis of technologies, such as SDN, ML, and MSA, separately, for meeting the resilience requirements in the IoMT networks. SDN can be used for monitoring and control, and ML can be used for anomaly detection and diagnosis, whereas MSA can be used for bringing distributed functionality and recovery into the IoMT networks. This paper provides a case study that describes the remote patient monitoring (RPM) of a heart patient in IoMT networks. It covers the different failure scenarios in IoMT infrastructure. Finally, we provide a proposed methodology that elaborates how distributed functionality can be achieved during these failures using machine learning, software-defined networks, and microservices technologies.

This paper presents the design and development of a flexible hyper-distributed IoT–Edge–Cloud computing platform for real-time Digital Twins in real logistics and industrial environments, intended as a novel living lab and testbed for future 6G applications. It expands the limited capabilities of IoT devices with extended Cloud and Edge computing functionalities, creating an IoT–Edge–Cloud continuum platform composed of multiple stakeholder solutions, in which vertical application developers can take full advantage of the computing resources of the infrastructure. The platform is built together with a private 5G network to connect machines and sensors on a large scale. Artificial intelligence and machine learning are used to allocate computing resources for real-time services by an end-to-end intelligent orchestrator, and real-time distributed analytic tools leverage Edge computing platforms to support different types of Digital Twin applications for logistics and industry, such as immersive remote driving, with specific characteristics and features. Performance evaluations demonstrated the platform’s capability to support the high-throughput communications required for Digital Twins, achieving user-experienced rates close to the maximum theoretical values, up to 552 Mb/s for the downlink and 87.3 Mb/s for the uplink in the n78 frequency band. Moreover, the platform’s support for Digital Twins was validated via QoE assessments conducted on an immersive remote driving prototype, which demonstrated high levels of user satisfaction in key dimensions such as presence, engagement, control, sensory integration, and cognitive load.

Smart grids (SGs) are essential for the efficient and distributed management of electrical distribution networks. A key task in SG management is fault detection and subsequently, network reconfiguration to minimize power losses and balance loads. This process should minimize power losses while optimizing distribution by balancing loads across the grid. However, the current literature yields a lack of methods for efficient fault prediction and fast reconfiguration. To achieve this goal, this paper builds on DEN2DE, an adaptable routing and reconfiguration solution potentially applicable to SGs, and investigates its potential extension with AI-based fault prediction using real-world datasets and randomly generated topologies based on the IEEE 123 Node Test Feeder. The study applies models based on Machine Learning (ML) and Deep Learning (DL) techniques, specifically evaluating Random Forest (RF) and Support Vector Machine (SVM) as ML methods, and Artificial Neural Network (ANN) as a DL method, evaluating each for accuracy, precision, and recall. Results indicate that the RF model with Recursive Feature Elimination (RFECV) achieves 94.28% precision and 81.05% recall, surpassing SVM (precision 89.32%, recall 6.95%) and ANN (precision 72.17%, recall 13.49%) in fault detection accuracy and reliability.

With the emergence of containerization 10 years ago, we saw a compact, convenient and portable way of running apps directly concurrently with virtualization. The major difference is in the architecture. Containers share the same kernel as the guest and then do not virtualize low-layer components like the Central Processing Unit (CPU). On the one hand, they are lighter and more flexible than virtual machines (VMs). On the other hand, VMs can more precisely meet the low-layer needs and are completely autonomous systems. Nowadays, what is the best architecture to use to develop an application? In this paper, we will study the two main virtual methods of deploying this. We will compare both methods on several criteria: compatibility based on user experience and the ease of installation/deployment, scalability based on the automatic elasticity facing the workload and energy efficiency in terms of energy and computer resources. After the tests, we conclude that the containerization option is the most ecologically advantageous option in terms of energy consumption.

Background/Objectives: The healthcare sector is rapidly growing, aiming to promote health, provide treatment, and enhance well-being. This paper focuses on the organ donation and transplantation system, a vital aspect of healthcare. It offers a comprehensive review of challenges in global organ donation and transplantation, highlighting issues of fairness and transparency, and compares centralized architecture-based models and blockchain-based decentralized models. Methods: This work reviews 370 publications from 2016 to 2023 on organ donation management systems. Out of these, 85 publications met the inclusion criteria, including 67 journal articles, 2 doctoral theses, and 16 conference papers. About 50.6% of these publications focus on global challenges in the system. Additionally, 12.9% of the publications examine centralized architecture-based models, and 36.5% of the publications explore blockchain-based decentralized models. Results: Concerns about organ trafficking, illicit trade, system distrust, and unethical allocation are highlighted, with a lack of transparency as the primary catalyst in organ donation and transplantation. It has been observed that centralized architecture-based models use technologies such as Python, Java, SQL, and Android Technology but face data storage issues. In contrast, blockchain-based decentralized models, mainly using Ethereum and a subset on Hyperledger Fabric, benefit from decentralized data storage, ensure transparency, and address these concerns efficiently. Conclusions: It has been observed that blockchain technology-based models are the better option for organ donation management systems. Further, suggestions for future directions for researchers in the field of organ donation management systems have been presented.

Social media platforms play a significant role in facilitating business decision making, especially in the context of emerging technologies. Such platforms offer a rich source of data from a global audience, which can provide organisations with insights into market trends, consumer behaviour, and attitudes towards specific technologies, as well as monitoring competitor activity. In the context of social media, such insights are conceptualised as immediate and real-time behavioural responses measured by likes, comments, and shares. To monitor such metrics, social media platforms have introduced tools that allow users to analyse and track the performance of their posts and understand their audience. However, the existing tools often overlook the impact of contextual features such as sentiment, URL inclusion, and specific word use. This paper presents a data-driven framework to identify and quantify the influence of such features on the visibility and impact of technology-related tweets. The quantitative analysis from statistical modelling reveals that certain content-based features, like the number of words and pronouns used, positively correlate with the impressions of tweets, with increases of up to 2.8%. Conversely, features such as the excessive use of hashtags, verbs, and complex sentences were found to decrease impressions significantly, with a notable reduction of 8.6% associated with tweets containing numerous trailing characters. Moreover, the study shows that tweets expressing negative sentiments tend to be more impressionable, likely due to a negativity bias that elicits stronger emotional responses and drives higher engagement and virality. Additionally, the sentiment associated with specific technologies also played a crucial role; positive sentiments linked to beneficial technologies like data science or machine learning significantly boosted impressions, while similar sentiments towards negatively viewed technologies like cyber threats reduced them. The inclusion of URLs in tweets also had a mixed impact on impressions—enhancing engagement for general technology topics, but reducing it for sensitive subjects due to potential concerns over link safety. These findings underscore the importance of a strategic approach to social media content creation, emphasising the need for businesses to align their communication strategies, such as responding to shifts in user behaviours, new demands, and emerging uncertainties, with dynamic user engagement patterns.

There have been several catastrophic events that have impacted multiple economies and resulted in thousands of fatalities, and violence has generated a severe political and financial crisis. Multiple studies have been centered around the artificial intelligence (AI) and machine learning (ML) approaches that are most widely used in practice to detect or forecast violent activities. However, machine learning algorithms become less accurate in identifying and forecasting violent activity as data volume and complexity increase. For the prediction of future events, we propose a hybrid deep learning (DL)-based model that is composed of a convolutional neural network (CNN), long short-term memory (LSTM), and an attention layer to learn temporal features from the benchmark the Global Terrorism Database (GTD). The GTD is an internationally recognized database that includes around 190,000 violent events and occurrences worldwide from 1970 to 2020. We took into account two factors for this experimental work: the type of event and the type of object used. The LSTM model takes these complex feature extractions from the CNN first to determine the chronological link between data points, whereas the attention model is used for the time series prediction of an event. The results show that the proposed model achieved good accuracies for both cases—type of event and type of object—compared to benchmark studies using the same dataset (98.1% and 97.6%, respectively).

This study examines the level of implementation of artificial intelligence (AI) in the personalization of hotel services and its impact on guest satisfaction through an analysis of tourists’ attitudes and behaviors The focus of the research is on how personalized recommendations for food and beverages, activities, and room services, delivered by trustworthy AI systems, digital experience, and the perception of privacy and data security, influence overall guest satisfaction. The research was conducted in Serbia and Hungary, using structural models to assess and analyze direct and indirect effects. The results show that AI personalization significantly contributes to guest satisfaction, with mediating variables such as trust in AI systems and technological experience playing a key role. A comparative analysis highlights differences between Hungary, a member of the European Union, and Serbia, a country in transition, shedding light on specific regulatory frameworks and cultural preferences in these countries.

To ensure the operational safety of oil transportation stations, it is crucial to predict the impact of pressure and temperature before crude oil enters the pipeline network. Accurate predictions enable the assessment of the pipeline’s load-bearing capacity and the prevention of potential safety incidents. Most existing studies primarily focus on describing and modeling the mechanisms of the oil flow process. However, monitoring data can be skewed by factors such as instrument aging and pipeline friction, leading to inaccurate predictions when relying solely on mechanistic or data-driven approaches. To address these limitations, this paper proposes a Temporal-Spatial Three-stream Temporal Convolutional Network (TS-TTCN) model that integrates mechanistic knowledge with data-driven methods. Building upon Temporal Convolutional Networks (TCN), the TS-TTCN model synthesizes mechanistic insights into the oil transport process to establish a hybrid driving mechanism. In the temporal dimension, it incorporates real-time operating parameters and applies temporal convolution techniques to capture the time-series characteristics of the oil transportation pipeline network. In the spatial dimension, it constructs a directed topological map based on the pipeline network’s node structure to characterize spatial features. Data analysis and experimental results show that the Three-stream Temporal Convolutional Network (TTCN) model, which uses a Tanh activation function, achieves an error rate below 5%. By analyzing and validating real-time data from the Dongying oil transportation station, the proposed hybrid model proves to be more stable, reliable, and accurate under varying operating conditions.

Presidential elections are an important political event that often trigger intense debate. With more than 139 million users, YouTube serves as a significant platform for understanding public opinion through sentiment analysis. This study aimed to implement deep learning techniques for a multi-label sentiment analysis of comments on YouTube videos related to the 2024 Indonesian presidential election. Offering a fresh perspective compared to previous research that primarily employed traditional classification methods, this study classifies comments into eight emotional labels: anger, anticipation, disgust, joy, fear, sadness, surprise, and trust. By focusing on the emotional spectrum, this study provides a more nuanced understanding of public sentiment towards presidential candidates. The CRISP-DM method is applied, encompassing stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment, ensuring a systematic and comprehensive approach. This study employs a dataset comprising 32,000 comments, obtained via YouTube Data API, from the KPU and Najwa Shihab channels. The analysis is specifically centered on comments related to presidential candidate debates. Three deep learning models—Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), and a hybrid model combining CNN and Bi-LSTM—are assessed using confusion matrix, Area Under the Curve (AUC), and Hamming loss metrics. The evaluation results demonstrate that the Bi-LSTM model achieved the highest accuracy with an AUC value of 0.91 and a Hamming loss of 0.08, indicating an excellent ability to classify sentiment with high precision and a low error rate. This innovative approach to multi-label sentiment analysis in the context of the 2024 Indonesian presidential election expands the insights into public sentiment towards candidates, offering valuable implications for political campaign strategies. Additionally, this research contributes to the fields of natural language processing and data mining by addressing the challenges associated with multi-label sentiment analysis.

This paper advances real-time cursor control for individuals with motor impairments through a novel brain–computer interface (BCI) system based solely on motor imagery. We introduce an enhanced deep neural network (DNN) classifier integrated with a Four-Class Iterative Filtering (FCIF) technique for efficient preprocessing of neural signals. The underlying approach is the Four-Class Filter Bank Common Spatial Pattern (FCFBCSP) and it utilizes a customized filter bank for robust feature extraction, thereby significantly improving signal quality and cursor control responsiveness. Extensive testing under varied conditions demonstrates that our system achieves an average classification accuracy of 89.1% and response times of 663 milliseconds, illustrating high precision in feature discrimination. Evaluations using metrics such as Recall, Precision, and F1-Score confirm the system’s effectiveness and accuracy in practical applications, making it a valuable tool for enhancing accessibility for individuals with motor disabilities.

It is well-believed that most trading activities tend to herd. Herding is an important topic in finance. It implies a violation of efficient markets and hence, suggests possibly predictable trading profits. However, it is hard to test such a hypothesis using aggregated data (as in the literature). In this paper, we obtain a proprietary data set that contains detailed trading information, and as a result, for the first time it allows us to validate this hypothesis. The data set contains all trades transacted in 2019 by all the brokers/dealers across all locations in Taiwan of all the equities (stocks, warrants, and ETFs). Given such data, in this paper, we use swarm intelligence to identify such herding behavior. In particular, we use two versions of swarm intelligence—Boids and PSO (particle swarm optimization)—to study the herding behavior. Our results indicate weak swarm among brokers/dealers.

The maritime industry is constantly evolving and posing new challenges, especially with increasing digitalization, which has raised concerns about cyber-attacks on maritime supply chain agents. Although scholars have proposed various methods and classification models to counter these cyber threats, a comprehensive cyber-attack taxonomy for maritime supply chain actors based on a systematic literature review is still lacking. This review aims to provide a clear picture of common cyber-attacks and develop a taxonomy for their categorization. In addition, it outlines best practices derived from academic research in maritime cybersecurity using PRISMA principles for a systematic literature review, which identified 110 relevant journal papers. This study highlights that distributed denial of service (DDoS) attacks and malware are top concerns for all maritime supply chain stakeholders. In particular, shipping companies are urged to prioritize defenses against hijacking, spoofing, and jamming. The report identifies 18 practices to combat cyber-attacks, categorized into information security management solutions, information security policies, and cybersecurity awareness and training. Finally, this paper explores how emerging technologies can address cyber-attacks in the maritime supply chain network (MSCN). While Industry 4.0 technologies are highlighted as significant trends in the literature, this study aims to equip MSCN stakeholders with the knowledge to effectively leverage a broader range of emerging technologies. In doing so, it provides forward-looking solutions to prevent and mitigate cyber-attacks, emphasizing that Industry 4.0 is part of a larger landscape of technological innovation.

Birthweight (BW) is a widely used indicator of neonatal health, with low birthweight (LBW) being linked to higher risks of morbidity and mortality. Timely and precise prediction of LBW is crucial for ensuring newborn health and well-being. Despite recent machine learning advancements in BW classification based on physiological traits in the mother and ultrasound outcomes, maternal status in essential micronutrients for fetal development is yet to be fully exploited for BW prediction. This study aims to evaluate the impact of maternal nutritional factors, specifically mid-pregnancy plasma concentrations of vitamin B12, folate, and anemia on BW prediction. This study analyzed data from 729 pregnant women in Tarragona, Spain, for early BW prediction and analyzed each factor’s impact and contribution using a partial dependency plot and feature importance. Using a super learner ensemble method with tenfold cross-validation, the model achieved a prediction accuracy of 96.19% and an AUC-ROC of 0.96, outperforming single-model approaches. Vitamin B12 and folate status were identified as significant predictors, underscoring their importance in reducing LBW risk. The findings highlight the critical role of maternal nutritional factors in BW prediction and suggest that monitoring vitamin B12 and folate levels during pregnancy could enhance prenatal care and mitigate neonatal complications associated with LBW.

Educational Data Mining (EDM) applies advanced data mining techniques to analyse data from educational settings, traditionally aimed at improving student performance. However, EDM’s potential extends to enhancing administrative functions in educational organisations. This systematisation of knowledge (SoK) explores the use of EDM in organisational administration, examining peer-reviewed and non-peer-reviewed studies to provide a comprehensive understanding of its impact. This review highlights how EDM can revolutionise decision-making processes, supporting data-driven strategies that enhance administrative efficiency. It outlines key data mining techniques used in tasks like resource allocation, staff evaluation, and institutional planning. Challenges related to EDM implementation, such as data privacy, system integration, and the need for specialised skills, are also discussed. While EDM offers benefits like increased efficiency and informed decision-making, this review notes potential risks, including over-reliance on data and misinterpretation. The role of EDM in developing robust administrative frameworks that align with organisational goals is also explored. This study provides a critical overview of the existing literature and identifies areas for future research, offering insights to optimise educational administration through effective EDM use and highlighting its growing significance in shaping the future of educational organisations.

Database engineered applications cover a broad range of topics including various design and maintenance methods, as well as data analytics and data mining algorithms and learning strategies for enterprise, distributed, or federated data stores [...]

The outbreak of epidemiological diseases creates a major impact on humanity as well as on the world’s economy. The consequence of such infectious diseases affects the survival of mankind. The government has to stand up to the negative influence of these epidemiological diseases and facilitate society with medical resources and economical support. In recent times, COVID-19 has been one of the epidemiological diseases that created lethal effects and a greater slump in the economy. Therefore, the prediction of outbreaks is essential for epidemiological diseases. It may be either frequent or sudden infections in society. The unexpected raise in the application of prediction models in recent years is outstanding. A study on these epidemiological prediction models and their usage from the year 2018 onwards is highlighted in this article. The popularity of various prediction approaches is emphasized and summarized in this article.

We propose an enhanced privacy-preserving method for image classification using ConvMixer, which is an extremely simple model that is similar in spirit to the Vision Transformer (ViT). Most privacy-preserving methods using encrypted images cause the performance of models to degrade due to the influence of encryption, but a state-of-the-art method was demonstrated to have the same classification accuracy as that of models without any encryption under the use of ViT. However, the method, in which a common secret key is assigned to each patch, is not robust enough against ciphertext-only attacks (COAs) including jigsaw puzzle solver attacks if compressible encrypted images are used. In addition, ConvMixer is less robust than ViT because there is no position embedding. To overcome this issue, we propose a novel block-wise encryption method that allows us to assign an independent key to each patch to enhance robustness against attacks. In experiments, the effectiveness of the method is verified in terms of image classification accuracy and robustness, and it is compared with conventional privacy-preserving methods using image encryption.

This study investigates the factors influencing the acceptance and implementation of smart city solutions, with a particular focus on smart mobility and digital services in Novi Sad, one of the leading urban centers in Serbia. Employing a quantitative methodology, the research encompasses citizens’ perceptions of the benefits of smart technologies, their level of awareness regarding smart solutions, the degree of engagement in using digital services, and their interest in smart mobility. The results indicate that these factors are crucial for the successful integration of smart technologies. Notably, awareness of smart city initiatives and the perceived benefits, such as improved mobility, reduced traffic congestion, increased energy efficiency, and enhanced quality of life, are highlighted as key prerequisites for the adoption of these solutions. Novi Sad, as the European Capital of Culture in 2022, presents a unique opportunity for the implementation of these technologies. Our findings point to the need for strategic campaigns aimed at educating and raising public awareness. The practical implications of this study could contribute to shaping policies that encourage the development of smart cities, not only in Novi Sad but also in other urban areas across Serbia and the region. This study confirms the importance of citizen engagement and technological literacy in the transformation of urban environments through smart solutions, underscoring the potential of these technologies to improve everyday life and achieve sustainable urban development.

The accuracy of traditional topic models may be compromised due to the sparsity of co-occurring vocabulary in the corpus, whereas conventional word embedding models tend to excessively prioritize contextual semantic information and inadequately capture domain-specific features in the text. This paper proposes a hybrid semantic representation method that combines a topic model that integrates conceptual knowledge with a weighted word embedding model. Specifically, we construct a topic model incorporating the Probase concept knowledge base to perform topic clustering and obtain topic semantic representation. Additionally, we design a weighted word embedding model to enhance the contextual semantic information representation of the text. The feature-based information fusion model is employed to integrate the two textual representations and generate a hybrid semantic representation. The hybrid semantic representation model proposed in this study was evaluated based on various English composition test sets. The findings demonstrate that the model presented in this paper exhibits superior accuracy and practical value compared to existing text representation methods.

Text CAPTCHAs are crucial security measures deployed on global websites to deter unauthorized intrusions. The presence of anti-attack features incorporated into text CAPTCHAs limits the effectiveness of evaluating them, despite CAPTCHA recognition being an effective method for assessing their security. This study introduces a novel color augmentation technique called Variational Color Shift (VCS) to boost the recognition accuracy of different networks. VCS generates a color shift of every input image and then resamples the image within that range to generate a new image, thus expanding the number of samples of the original dataset to improve training effectiveness. In contrast to Random Color Shift (RCS), which treats the color offsets as hyperparameters, VCS estimates color shifts by reparametrizing the points sampled from the uniform distribution using predicted offsets according to every image, which makes the color shifts learnable. To better balance the computation and performance, we also propose two variants of VCS: Sim-VCS and Dilated-VCS. In addition, to solve the overfitting problem caused by disturbances in text CAPTCHAs, we propose an Auto-Encoder (AE) based on Large Separable Kernel Attention (AE-LSKA) to replace the convolutional module with large kernels in the text CAPTCHA recognizer. This new module employs an AE to compress the interference while expanding the receptive field using Large Separable Kernel Attention (LSKA), reducing the impact of local interference on the model training and improving the overall perception of characters. The experimental results show that the recognition accuracy of the model after integrating the AE-LSKA module is improved by at least 15 percentage points on both M-CAPTCHA and P-CAPTCHA datasets. In addition, experimental results demonstrate that color augmentation using VCS is more effective in enhancing recognition, which has higher accuracy compared to RCS and PCA Color Shift (PCA-CS).

Industrial product e-commerce refers to the specific application of the e-commerce concept in industrial product transactions. It enables industrial enterprises to conduct transactions via Internet platforms and reduce circulation and operating costs. Industrial literature, such as policies, reports, and standards related to industrial product e-commerce, contains much crucial information. Through a systematical analysis of this information, we can explore and comprehend the development characteristics and trends of industrial product e-commerce. To this end, 18 policy documents, 10 industrial reports, and five standards are analyzed by employing text-mining methods. Firstly, natural language processing (NLP) technology is utilized to pre-process the text data related to industrial product commerce. Then, word frequency statistics and TF-IDF keyword extraction are performed, and the word frequency statistics are visually represented. Subsequently, the feature set is obtained by combining these processes with the manual screening method. The original text corpus is used as the training set by employing the skip-gram model in Word2Vec, and the feature words are transformed into word vectors in the multi-dimensional space. The K-means algorithm is used to cluster the feature words into groups. The latent Dirichlet allocation (LDA) method is then utilized to further group and discover the features. The text-mining results provide evidence for the development characteristics and trends of industrial product e-commerce in China.

This study proposes a novel forgery detection method based on the analysis of frequency components of images using the Discrete Fourier Transform (DFT). In recent years, face manipulation technologies, particularly Generative Adversarial Networks (GANs), have advanced to such an extent that their misuse, such as creating deepfakes indistinguishable to human observers, has become a significant societal concern. We reviewed two GAN architectures, StyleGAN and StyleGAN2, generating synthetic faces that were compared with real faces from the FFHQ and CelebA-HQ datasets. The key results demonstrate classification accuracies above 99%, with F1 scores of 99.94% for Support Vector Machines and 97.21% for Random Forest classifiers. These findings underline the fact that performing frequency analysis presents a superior approach to deepfake detection compared to traditional spatial detection methods. It provides insight into subtle manipulation cues in digital images and offers a scalable way to enhance security protocols amid rising digital impersonation threats.

Efficiently simulating solid mechanics is vital across various engineering applications. As constitutive models grow more complex and simulations scale up in size, harnessing the capabilities of modern computer architectures has become essential for achieving timely results. This paper presents advancements in running parallel simulations of solid mechanics on multi-core CPUs and GPUs using a single-code implementation. This portability is made possible by the C++ matrix and array (MATAR) library, which interfaces with the C++ Kokkos library, enabling the selection of fine-grained parallelism backends (e.g., CUDA, HIP, OpenMP, pthreads, etc.) at compile time. MATAR simplifies the transition from Fortran to C++ and Kokkos, making it easier to modernize legacy solid mechanics codes. We applied this approach to modernize a suite of constitutive models and to demonstrate substantial performance improvements across different computer architectures. This paper includes comparative performance studies using multi-core CPUs along with AMD and NVIDIA GPUs. Results are presented using a hypoelastic–plastic model, a crystal plasticity model, and the viscoplastic self-consistent generalized material model (VPSC-GMM). The results underscore the potential of using the MATAR library and modern computer architectures to accelerate solid mechanics simulations.

Drowning is among the most common reasons for children’s death aged one to fourteen around the globe, ranking as the third leading cause of unintentional injury death. With rising populations and the growing popularity of swimming pools in hotels and villas, the incidence of drowning has accelerated. Accordingly, the development of systems for detecting and preventing drowning has become increasingly critical to provide safe swimming settings. In this paper, we propose a comprehensive review of recent existing advancements in automated drowning detection and prevention systems. The existing approaches can be broadly categorized according to their objectives into two main groups: detection-based systems, which alert lifeguards or parents to perform manual rescues, and detection and rescue-based systems, which integrate detection with automatic rescue mechanisms. Automatic drowning detection approaches could be further categorized into computer vision-based approaches, where camera-captured images are analyzed by machine learning algorithms to detect instances of drowning, and sensing-based approaches, where sensing instruments are attached to swimmers to monitor their physical parameters. We explore the advantages and limitations of each approach. Additionally, we highlight technical challenges and unresolved issues related to this domain, such as data imbalance, accuracy, privacy concerns, and integration with rescue systems. We also identify future research opportunities, emphasizing the need for more advanced AI models, uniform datasets, and better integration of detection with autonomous rescue mechanisms. This study aims to provide a critical resource for researchers and practitioners, facilitating the development of more effective systems to enhance water safety and minimize drowning incidents.

Super-resolution is a technique for generating a high-resolution image or video from a low-resolution counterpart by predicting natural and realistic texture information. It has various applications such as medical image analysis, surveillance, remote sensing, etc. However, traditional single-image super-resolution methods can lead to a blurry visual effect. Reference-based super-resolution methods have been proposed to recover detailed information accurately. In reference-based methods, a high-resolution image is also used as a reference in addition to the low-resolution input image. Reference-based methods aim at transferring high-resolution textures from the reference image to produce visually pleasing results. However, it requires texture alignment between low-resolution and reference images, which generally requires a lot of time and memory. This paper proposes a lightweight reference-based video super-resolution method using deformable convolution. The proposed method makes the reference-based super-resolution a technology that can be easily used even in environments with limited computational resources. To verify the effectiveness of the proposed method, we conducted experiments to compare the proposed method with baseline methods in two aspects: runtime and memory usage, in addition to accuracy. The experimental results showed that the proposed method restored a high-quality super-resolved image from a very low-resolution level in 0.0138 s using two NVIDIA RTX 2080 GPUs, much faster than the representative method.