Search Results (4,658)

Drowsiness while driving poses a significant risk in terms of road safety, making effective drowsiness detection systems essential for the prevention of accidents. Facial signal-based detection methods have proven to be an effective approach to drowsiness detection. However, they bring challenges arising from inter-individual differences among drivers. Variations in facial structure necessitate personalized feature extraction thresholds, yet existing methods apply a uniform threshold, leading to inaccurate feature extraction. Furthermore, many current methods focus on only one or two facial regions, overlooking the possibility that drowsiness may manifest differently across different facial areas among different drivers. To address these issues, we propose a drowsiness detection method that combines an ensemble model with hybrid facial features. This approach enables the accurate extraction of features from four key facial regions—the eye region, mouth contour, head pose, and gaze direction—through adaptive threshold correction to ensure comprehensive coverage. An ensemble model, combining Random Forest, XGBoost, and Multilayer Perceptron with a soft voting criterion, is then employed to classify the drivers’ drowsiness state. Additionally, we use the SHAP method to ensure model explainability and analyze the correlations between features from various facial regions. Trained and tested on the UTA-RLDD dataset, our method achieves a video accuracy (VA) of 86.52%, outperforming similar techniques introduced in recent years. The interpretability analysis demonstrates the value of our approach, offering a valuable reference for future research and contributing significantly to road safety. Full article

Physical attacks pose a significant threat to the security of embedded processors, which have become an integral part of our daily lives. Processors can be vulnerable to fault injection attacks that threaten their normal and secure behavior. Such attacks can lead to serious malfunctions in applications, compromising their security and correct behavior. Therefore, it is crucial for designers and manufacturers to consider these threats while developing embedded processors. These attacks may require only a moderate level of knowledge to execute and can compromise the normal behavior of the targeted devices. These attacks can be faced by developing effective countermeasures. This paper explores the main existing countermeasures against fault injection attacks in embedded processors, to understand and implement effective solutions against those threats. Subsequently, we further investigate solutions related to RISC-V, focusing on its hardware and architecture security. Full article

Introduction: Ensuring vehicular cybersecurity is a critical challenge due to the increasing connectivity of modern vehicles, and traditional centralised learning approaches for intrusion detection pose significant privacy risks, as they require sensitive data to be shared from multiple vehicles to a central server. Objective: The aim of this study is therefore to develop an in-vehicle intrusion detection system (IVIDS) that integrates federated learning (FL) with neural networks, enabling decentralised and privacy-preserving detection of cyberattacks in vehicular networks. The proposed system extends previous research by detecting a broader range of attacks (eight types) and exploring different deep learning architectures. Methods: This study employs an extended version of the publicly available VeReMi dataset to train and evaluate multiple neural network architectures, including Multilayer Perceptrons (MLPs), Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) networks. Federated learning is utilised to enable collaborative model training across multiple vehicles without sharing raw data. Various data preprocessing techniques and differential privacy mechanisms are also explored. Results and Conclusions: The experimental results demonstrate that LSTM networks outperform both MLP and GRU architectures in classifying vehicular cyberattacks. The best LSTM model, trained with two previous message lags and standard normalisation, achieved a classification accuracy of 96.75% in detecting eight types of attacks, surpassing previous studies, and demonstrating the potential of applying neural networks designed to work with time series data. Full article

Sign language machine translation (SLMT)—the task of automatically translating between sign and spoken languages or between sign languages—is a complex task within the field of NLP. Its multi-modal and non-linear nature require the joint efforts of sign language (SL) linguists, technical experts, and SL users. Effective user involvement is a challenge that can be addressed through co-creation. Co-creation has been formally defined in many fields, e.g., business, marketing, educational, and others; however, in NLP and in particular in SLMT, there is no formal, widely accepted definition. Starting from the inception and evolution of co-creation across various fields over time, we develop a relationship typology to address the collaboration between deaf, hard of hearing, and hearing researchers and the co-creation with SL users. We compare this new typology to the guiding principles of participatory design for NLP. We then assess 111 articles from the perspective of involvement of SL users and highlight the lack of involvement of the sign language community or users in decision-making processes required for effective co-creation. Finally, we derive formal guidelines for co-creation for SLMT which take the dynamic nature of co-creation throughout the life cycle of a research project into account. Full article

Cloud adoption necessitates relinquishing data control to cloud service providers (CSPs), involving diverse stakeholders with varying security and privacy (S&P) needs and responsibilities. Building upon previously published work, this paper addresses the persistent challenge of a lack of standardized, transparent methods for consumers to select and quantify appropriate S&P measures. This work introduces a stakeholder-centric methodology to identify and address S&P challenges, enabling stakeholders to assess their cloud service protection capabilities. The primary contribution lies in the development of new classifications and updated considerations, along with tailored S&P features designed to accommodate specific service models, deployment models, and stakeholder roles. This novel approach shifts from data or infrastructure perspectives to comprehensively account for S&P issues arising from stakeholder interactions and conflicts. A prototype framework, utilizing a rule-based taxonomy and the Goal–Question–Metric (GQM) method, recommends essential S&P attributes. Multi-criteria decision-making (MCDM) is employed to measure protection levels and facilitate benchmarking. The evaluation of the implemented prototype demonstrates the framework’s effectiveness in recommending and consistently measuring security features. This work aims to reduce consumer apprehension regarding cloud migration, improve transparency between consumers and CSPs, and foster competitive transparency among CSPs. Full article

Students are faced with a wide range of writing tasks during their studies, including writing literature reviews, summarising papers and producing reflective reports. Writing tasks present a challenge for students who are not writing in their native language due to studying overseas. Indeed, students writing in their native language have a distinct advantage in assignments involving writing. The rapid emergence of Generative Artificial Intelligence (Gen-AI) over the past three years has the potential to significantly impact the quality and efficiency of writing of non-native English speakers by providing international students with an opportunity to minimise the language barrier when writing in academia. This paper reports on a series of structured exercises we developed to determine how using Gen-AI tools built on large language models (LLMs) such as ChatGPT and Claude might improve student writing in the context of computing degrees. Two of the exercises were successfully repeated with a second and independent group of students. We analyse some issues to be aware of when using Gen-AI tools and make suggestions as to their effective use. The key underlying message is that students need to develop their own distinct voice. Full article

This paper addresses the issue of distinguishing commercially played songs from non-music audio in radio broadcasts, where automatic song identification systems are commonly employed for reporting purposes. Service call costs increase because these systems need to remain continuously active, even when music is not being broadcast. Our solution serves as a preliminary filter to determine whether an audio segment constitutes “music” and thus warrants a subsequent service call to an identifier. We collected 139 h of non-consecutive 5 s audio samples from various radio broadcasts, labeling segments from talk shows or advertisements as “non-music”. We implemented multiple data augmentation strategies, including FM-like pre-processing, trained a custom Convolutional Neural Network, and then built a live inference platform capable of continuously monitoring web radio streams. This platform was validated using 1360 newly collected audio samples, evaluating performance on both 5 s chunks and 15 s buffers. The system demonstrated consistently high performance on previously unseen stations, achieving an average accuracy of 96% and a maximum of 98.23%. The intensive pre-processing contributed to these performances with the benefit of making the system inherently suitable for FM radio. This solution has been incorporated into a commercial product currently utilized by Italian clients for royalty calculation and reporting purposes. Full article

This research explores the impact of social media metrics on revenue growth, specifically focusing on Instagram, a leading platform for businesses to engage consumers and promote offerings. It examines key metrics such as reach, impressions, interaction rate, and virality rate, which gauge user engagement with brand content. A novel metric, the loyalty rate, is introduced, combining interaction and virality rates to measure follower loyalty—those who not only engage but also share content, enhancing organic reach. The methodology involved comprehensive statistical analyses, including descriptive statistics, Pearson’s correlations, and regression models, to investigate the relationship between social media metrics and monthly turnover. The findings reveal a moderate positive correlation between the loyalty rate and turnover, although the statistical significance was insufficient to establish a direct relationship. In contrast, metrics like follower count exhibited a stronger influence on financial performance, indicating that follower growth may be more critical for revenue generation. This study concludes that while engagement and loyalty matter, their effect on turnover is part of a broader digital strategy encompassing various factors beyond direct interactions. Practical recommendations are made for enhancing the loyalty rate and expanding research to include other platforms, like Facebook and LinkedIn, for a more comprehensive understanding of social media’s impact on financial outcomes. Full article

The digital economy, driven by innovative technologies and artificial intelligence (AI), is transforming economic systems and increasing the demand for accurate assessments of digital competitiveness. This study addresses the inconsistencies in country rankings derived from global digital indices and aims to determine whether these rankings differ due to methodological variations. It also examines whether the rankings correlate significantly across different evaluation frameworks. The research focuses on 29 European countries and analyzes rankings from four widely recognized indices: the World Digital Competitiveness Ranking (WDCR), Network Readiness Index (NRI), AI Readiness Index (AIRI), and Digital Quality of Life Index (DQLI). To assess the consistency and variability in rankings from 2019 to 2024, the study applies Friedman’s ANOVA and Kendall’s coefficient of concordance. The results demonstrate strong correlations at the level of country rankings, indicating a high degree of consistency, but also confirm statistically significant differences in rankings among the indices, which reflect the diversity of their conceptual foundations. Countries such as Finland, the Netherlands, and Denmark consistently achieve top rankings, indicating convergence, while more variability is observed in indices like the DQLI. These findings highlight the importance of rank-based, multidimensional assessments in evaluating digital competitiveness. They support the use of such assessments as policy tools for monitoring progress, identifying gaps, and promoting inclusive digital development. Full article

Social media allows people to express and share a variety of experiences, opinions, beliefs, interpretations, or viewpoints on a single topic. Summarizing a collection of social media posts (microblogs) on one topic may be challenging and can result in an incoherent summary due to multiple perspectives from different users. We introduce a novel approach to microblog summarization, the Multiple-View Summarization Framework (MVSF), designed to efficiently generate multiple summaries from the same social media dataset depending on chosen perspectives and deliver personalized and fine-grained summaries. The MVSF leverages component-of-perspective computing, which can recognize the perspectives expressed in microblogs, such as sentiments, political orientations, or unreliable opinions (fake news). The perspective computing can filter social media data to summarize them according to specific user-selected perspectives. For the summarization methods, our framework implements three extractive summarization methods: Entity-based, Social Signal-based, and Triple-based. We conduct comparative evaluations of MVSF summarizations against state-of-the-art summarization models, including BertSum, SBert, T5, and Bart-Large-CNN, by using a gold-standard BBC news dataset and Rouge scores. Furthermore, we utilize a dataset of 18,047 tweets about COVID-19 vaccines to demonstrate the applications of MVSF. Our contributions include the innovative approach of using user perspectives in summarization methods as a unified framework, capable of generating multiple summaries that reflect different perspectives, in contrast to prior approaches of generating one-size-fits-all summaries for one dataset. The practical implication of MVSF is that it offers users diverse perspectives from social media data. Our prototype web application is also implemented using ChatGPT to show the feasibility of our approach. Full article

Electronic Medical Records (EMRs) are central to the modern healthcare system. Recent advances in artificial intelligence (AI), particularly generative artificial intelligence (GenAI), have opened new opportunities for the advancement of EMRs. This scoping review aims to explore the current real-world applications of GenAI within EMRs to support an understanding of AI applications in healthcare. A literature search was conducted following PRISMA-ScR guidelines. The search was conducted using Ovid MEDLINE, up to 28 October 2024, using a peer-reviewed search strategy. Overall, 55 studies were included. A list of five themes was generated by human reviewers based on the literature review: data manipulation (24), patient communication (9), clinical decision making (8), clinical prediction (8), summarization (4), and other (2). The majority of studies originated from the United States (35). Both proprietary and commercially available models were tested, with ChatGPT being the most commonly referenced LLM. As these models continue to be developed, their diverse use cases within EMRs have the potential to improve patient outcomes, enhance access to medical data, streamline hospital workflows, and reduce physician workload. However, continued problems surrounding data privacy, trust, bias, model hallucinations, and the need for robust evaluation remain. Further research considering the ethical, medical, and societal implications of GenAI applications in EMRs is essential to validate these findings and address existing limitations to support healthcare advancement. Full article

Recommender systems have evolved significantly in recent years, using advanced techniques such as explainable artificial intelligence, reinforcement learning, and graph neural networks to enhance both efficiency and transparency. This study presents a novel framework, $X{R}^2{K}^{2}G$ (X for explainability, first R for recommender systems, the second R for reinforcement learning, first K for knowledge graph, the second K stands for knowledge distillation, and G for graph-based techniques), with the goal of developing a next-generation recommender system with a focus on careers empowerment. To optimize recommendations while ensuring sustainability and transparency, the proposed method integrates reinforcement learning with graph-based representations of career trajectories. Additionally, it incorporates knowledge distillation techniques to further refine the model’s performance by transferring knowledge from a larger model to a more efficient one. Our approach employs reinforcement learning algorithms, graph embeddings, and knowledge distillation to enhance recommendations by providing clear and comprehensible explanations for the recommendations. In this work, we discuss the technical foundations of the framework, deployment strategies, and its practical applicability in real-world career scenarios. The effectiveness and interpretability of our approach are demonstrated through experimental results. Full article

The need to review maritime education has been highlighted in the relevant literature. Maritime curricula should incorporate recent technological advances, as well as address the needs of the maritime sector. In this paper, the Fuzzy Delphi Method (FDM) and the Fuzzy Analytic Hierarchy Process (FAHP) are utilized in order to propose a fuzzy multicriteria decision-making (MCDM) methodology that can be used to assess the importance of new technologies in maritime education and design a fuzzy evaluation model that can assist in maritime education policy-making. This study integrates the perspectives of the main maritime education stakeholders, namely, lecturers and maritime sector management. We selected data from a group of 19 experienced maritime professors and maritime business managers. The results indicate that new technologies such as artificial intelligence (AI), augmented and virtual reality (AR/VR), the Internet of Things (IoT), digital twins (DTs), and cybersecurity, as well as eLearning platforms, constitute a set of requirements that maritime education policies should meet by designing their curricula appropriately. This study suggests that fuzzy logic MCDM methods can be used as a human-centered AI approach for developing explainable education policy-making models that integrate stakeholder requirements and capture the subjectivity that is often inherited in their perspectives. Full article

This study presents an empirical investigation into the energy consumption of discriminative and generative AI models within real-world MLOps pipelines. For discriminative models, we examine various architectures and hyperparameters during training and inference and identify energy-efficient practices. For generative AI, large language models (LLMs) are assessed, with a focus primarily on energy consumption across different model sizes and varying service requests. Our study employs software-based power measurements, ensuring ease of replication across diverse configurations, models, and datasets. We analyse multiple models and hardware setups to uncover correlations among various metrics, identifying key contributors to energy consumption. The results indicate that, for discriminative models, optimising architectures, hyperparameters, and hardware can significantly reduce energy consumption without sacrificing performance. For LLMs, energy efficiency depends on balancing model size, reasoning complexity, and request-handling capacity, as larger models do not necessarily consume more energy when utilisation remains low. This analysis provides practical guidelines for designing green and sustainable ML operations, emphasising energy consumption and carbon-footprint reductions while maintaining performance. This paper can serve as a benchmark for accurately estimating total energy use across different types of AI models. Full article

Social media and mobile devices, commonly referred to as socimedevices, have become integral to students’ daily lives, influencing both their academic performance and overall well-being. Depending on usage patterns, these technologies can positively or negatively impact students’ education. In recent years, many researchers have introduced several models, including neural networks (NNs), machine learning (ML), and deep learning (DL), to identify the impact on student academic performance using a socimedevice. Here, we propose a comparative model named the MLRec model, where we assess how well different machine learning methods predict the dynamics of student life and provide a recommendation to society, parents, and academic advisors. Here, we have preprocessed our real dataset by various methods, which is collected from 10 schools and has 25 features totaling 275 instances from different districts of Bangladesh. After that, we applied 15 ML algorithms for training and testing. Then, we compared the algorithms using criteria such as accuracy, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), coefficient of determination (R²), Explained Variance (EV), and Tweedie Deviance Score (D²). Subsequently, we selected the Extra Tree Classifier (ETC) algorithm based on its superior performance, achieving an accuracy of 86%, an MSE of 25%, and an EV of 40%. We also used Explainable AI (LIME and SHAP) techniques to visualize the root causes of social networks’ effects on students’ school performance. Our results show that using social media excessively adversely affects academic pursuits. Full article