Advanced AI Research Articles

Analyzing Autonomous Vehicle Collision Types to Support Sustainable Transportation Systems: A Machine Learning and Association Rules Approach

The increasing presence of autonomous vehicles (AVs) in transportation, driven by advances in AI and robotics, requires a strong focus on safety in mixed-traffic environments to promote sustainable transportation systems. This study analyzes AV crashes in California using advanced machine learning to identify patterns among various crash factors. The main objective is to explore AV crash mechanisms by extracting association rules and developing a decision tree model to understand interactions between pre-crash conditions, driving states, crash types, severity, locations, and other variables. A multi-faceted approach, including statistical analysis, data mining, and machine learning, was used to model crash types. The SMOTE method addressed data imbalance, with models like CART, Apriori, RF, XGB, SHAP, and Pearson’s test applied for analysis. Findings reveal that rear-end crashes are the most common, making up over 50% of incidents. Side crashes at night are also frequent, while angular and head-on crashes tend to be more severe. The study identifies high-risk locations, such as complex unsignalized intersections, and highlights the need for improved AV sensor technology, AV–infrastructure coordination, and driver training. Technological advancements like V2V and V2I communication are suggested to significantly reduce the number and severity of specific types of crashes, thereby enhancing the overall safety and sustainability of transportation systems.

Silicon caregivers: a multilevel analysis of European perspectives on robotic technologies for elderly care

ABSTRACT As populations age, women's workforce participation grows and AI advances, understanding attitudes towards care technologies becomes increasingly important. This study examines attitudes towards robot caregivers for older adults across 28 European countries, using 2017 Eurobarometer data from working-age adults (20–59; n = 13,839). We investigate how individual characteristics (gender, education, occupation) and local-level factors (GDP, female labour participation, over 65s as % of the population, spending on old age) are associated with comfort levels with domestic care robots. The results show that men, individuals with higher levels of educational attainment, and those in professional or managerial occupations report greater comfort with robot caregivers. Additionally, local context plays a significant role. Those living in local communities with higher female employment rates and lower spending on old-age support demonstrate higher acceptance of robotic care solutions. These findings highlight the dual influence of individual and community factors in shaping attitudes towards automated care technologies.

Unlocking the Black Box: Advancements in Explainable AI and Model Interpretability

Unlocking the Black Box: Advancements in Explainable AI and Model Interpretability

Enhancing Lung and Breast Cancer Screening with Advanced AI and Image Processing Techniques

This research investigates the application of CNNs for diagnostics improvements in lung and breast cancers based on AI image classification approaches. Using the datasets with 15,000 images describing lung cancer and 10,000 images describing cases of breast cancer, the models showed high performance: 90% for lung cancer and 99% for breast cancer classification. The descriptive analysis pointed out different features in imaging, such as dense tissue structure and irregular cell patterns; the models successfully identified these. The findings underlined the vital role that AI could play in assisting radiologists by delivering preliminary analysis, triaging high-risk cases, and leading to early cancer detection. Essential challenges were highlighted: ethical considerations concerning patients' privacy and AI algorithms' transparency. The limitation of the dataset diversity resulted in the conclusion that only broader data can ensure good generalization in various clinical settings. They recommended integrating the AI tool with clinical workflow and also called for training radiologists for effectiveness. Future research directions include real-time imaging and patient data integration for comprehensive diagnostic support and multi-modal approaches that combine imaging with genomics for more precise predictions. This leads to a more personalized cancer diagnosis and treatment plan, thus ultimately improving the results of the patients. This research, therefore, underlines the transformative capabilities of AI and image processing in modernizing cancer screening and diagnostics toward more accurate and efficient healthcare practices.

ChatGPT versus Google Gemini: a comparison to evaluate patient education guide created on common neurological disorders

Abstract Introduction This study assesses the effectiveness of AI tools, ChatGPT and Google Gemini, in educating the public about neurological conditions such as Bell’s palsy, Tetanus, and Headaches, and assess chatbot-generated patient guides based on readability and ease of understanding. Methodology In March 2024, the authors conducted a cross-sectional study to develop patient education brochures for Bell’s palsy, Tetanus vaccination, and Persistent Headache, leveraging AI models ChatGPT and Google Gemini. The brochures’ quality was assessed through readability, similarity, and a modified DISCERN score for reliability. Statistical analysis, performed in R software, compared responses from both AI models using unpaired T-tests. The correlation between ease score and reliability was explored using Pearson’s Coefficient of Correlation. Results The study revealed no significant variances in word count, sentence count, or average words per sentence between the two AI tools. However, materials generated by ChatGPT exhibited significantly higher ease scores, highlighting its proficiency in creating more understandable content (p < 0.05). Conclusions This study finds ChatGPT outperforms Google Gemini in readability despite similar metrics. This suggests ChatGPT's potential superiority in creating more understandable patient education materials. As AI advances, it’s essential to research more tools and medical conditions to ensure they meet diverse patient education needs.

The Role of AI and Machine Learning in Revolutionizing Prenatal Screening and Genetic Analysis

rtificial Intelligence (AI) and Machine Learning (ML) are at the forefront of innovations in medical diagnostics, including prenatal screening and genetic analysis. The development of advanced algorithms, data processing capabilities, and predictive modeling has significantly enhanced the sensitivity, specificity, and accuracy of non-invasive prenatal testing (NIPT). This article explores recent advancements in AI- driven prenatal screening, the methodologies employed, and the future potential of AI in predictive prenatal health diagnostics, with a particular focus on improving genetic disorder detection and fetal health outcomes. The role of ethical considerations in AI-driven diagnostics is also discussed.

Advances and Challenges in Automated Drowning Detection and Prevention Systems

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.

(Re)defining Mobile Learning in the Post COVID-19 and GenAI Era

Mobile learning, thrust into the spotlight during the COVID-19 pandemic, has a rich 40-year history with a robust body of research predating 2020. This concise paper revisits mobile learning in light of the accelerated technological advancements and shifting educational practices post-pandemic. By examining the evolution of mobile learning frameworks and integrating recent advancements in AI and wearable technologies, we propose a contemporary redefinition that emphasises an accessible mobile ecology. We further explore the theoretical foundations and emerging scenarios in mobile learning, focusing on authentic learning experiences with current trends.

A Comprehensive Comparative Study of Intuitive Physics Modeling in Machine Learning Trained with Cartoon and Realistic Data

Abstract. This study delves into the influence of training data typesspecifically cartoon versus realistic visual datasetson the development of intuitive physics modeling in machine learning. Intuitive physics, the inherent human ability to understand and predict the physical properties and dynamics of objects, presents a significant challenge for current AI systems to replicate accurately. Leveraging YOLOv5, a cutting-edge object detection model, this research systematically evaluates the cognitive understanding and performance of AI models trained on distinct types of visual data. The findings reveal that the visual complexity inherent in the training datasets plays a crucial role in shaping the model's ability to generalize and accurately perform intuitive physics tasks. Models trained on cartoon datasets exhibited different learning patterns and generalization capabilities compared to those trained on realistic data, providing valuable insights into the role of data representation in AI training. This research offers both theoretical advancements in understanding AI's cognitive limitations and practical guidance for designing AI systems that can interact with the physical world more effectively. Ultimately, the study contributes to bridging the gap between human cognition and machine learning, pushing the boundaries of what AI can achieve in modeling complex, real-world phenomena.

Smooth Talking: Generative Versus Scripted Coaching Chatbot Adoption and Efficacy Comparison

Workplace coaching is an essential individual and organizational development intervention, but high costs limit its application. AI coaching chatbots could scale coaching, however, traditional scripted chatbots lacks mainstream adoption due to limited context awareness and robotic responses. Recent advances in large language models and generative AI offer an alternative, however, generative AI is linked to risks and controversies. Should coaching chatbots use generative AI? We compared a scripted, rules-based coaching chatbot (ScriptBot, n = 126) with a generative AI chatbot (GenBot, n = 116) in a randomized controlled trail experiment. We measured technology adoption (UTAUT2), self-determination (autonomy, competence, relatedness) and goal attainment. For all technology adoption and self-determination variables, GenBot outperformed ScriptBot. However, for goal attainment there was no significant difference. Using generative AI in coaching chatbots improves adoption and coaching outcomes, but for highly structured interactions such as goal attainment, scripted conversations (with lower risk) seem to work just as well.

AI-Driven Route Planning and Scheduling for Electric School Buses

This review paper explores the current state, recent advancements, challenges, and future perspectives of AI-driven approaches for route planning and scheduling of Electric School Buses (ESBs). The integration of artificial intelligence into energy management systems for electric vehicles has gained significant attention, particularly in optimizing school transportation. This study examines various AI techniques, including genetic algorithms, reinforcement learning, and game-theoretic approaches, applied to ESB management. Key focus areas include energy consumption estimation, battery capacity optimization, and Vehicle-to-Grid (V2G) strategies. The paper also addresses critical challenges such as data integration, security concerns, and operational constraints. Future perspectives highlight the potential of advanced AI techniques, smart grid integration, and personalized transportation solutions. By synthesizing current research and identifying key areas for future development, this review contributes to ongoing efforts to improve the efficiency, sustainability, and overall quality of school transportation systems through AI technologies.

The human biological advantage over AI

AbstractRecent advances in AI raise the possibility that AI systems will one day be able to do anything humans can do, only better. If artificial general intelligence (AGI) is achieved, AI systems may be able to understand, reason, problem solve, create, and evolve at a level and speed that humans will increasingly be unable to match, or even understand. These possibilities raise a natural question as to whether AI will eventually become superior to humans, a successor “digital species”, with a rightful claim to assume leadership of the universe. However, a deeper consideration suggests the overlooked differentiator between human beings and AI is not the brain, but the central nervous system (CNS), providing us with an immersive integration with physical reality. It is our CNS that enables us to experience emotion including pain, joy, suffering, and love, and therefore to fully appreciate the consequences of our actions on the world around us. And that emotional understanding of the consequences of our actions is what is required to be able to develop sustainable ethical systems, and so be fully qualified to be the leaders of the universe. A CNS cannot be manufactured or simulated; it must be grown as a biological construct. And so, even the development of consciousness will not be sufficient to make AI systems superior to humans. AI systems may become more capable than humans on almost every measure and transform our society. However, the best foundation for leadership of our universe will always be DNA, not silicon.

"Come to us first": Centering Community Organizations in Artificial Intelligence for Social Good Partnerships

Artificial Intelligence for Social Good (AI4SG) has emerged as a growing body of research and practice exploring the potential of AI technologies to tackle social issues. This area emphasizes interdisciplinary partnerships with community organizations, such as non-profits and government agencies. However, amidst excitement about new advances in AI and their potential impact, the needs, expectations, and aspirations of these community organizations--and whether they are being met--are not well understood. Understanding these factors is important to ensure that the considerable efforts by AI teams and community organizations can actually achieve the positive social impact they strive for. Drawing on the Data Feminism framework, we explored the perspectives of community organization members on their partnerships with AI teams through 16 semi-structured interviews. Our study highlights the pervasive influence of funding agendas and the optimism surrounding AI's potential. Despite the significant intellectual contributions and labor provided by community organization members, their goals were frequently sidelined in favor of other stakeholders, including AI teams. While many community organization members expected tangible project deployment, only two out of 14 projects we studied reached the deployment stage. However, community organization members sustained their belief in the potential of the projects, still seeing diminished goals as valuable. To enhance the efficacy of future collaborations, our participants shared their aspirations for success, calling for co-leadership starting from the early stages of projects. We propose data co-liberation as a grounding principle for approaching AI4SG moving forward, positing that community organizations' co-leadership is essential for fostering more effective, sustainable, and ethical development of AI.

The Self-Improving Customer Service System: How AI Learns from Every Interaction

This article explores the transformative impact of self-improving AI systems in customer service, examining the parallels between AI and human learning processes, the mechanics of AI self-improvement, and the advantages of AI's learning at scale. It delves into real-world applications and impacts across various industries, highlighting improvements in personalization, efficiency, accuracy, customer satisfaction, and cost reduction. The article also addresses ethical considerations such as data privacy, transparency, and bias mitigation, while offering a future outlook on advanced AI capabilities in emotional intelligence, predictive service, and seamless human-AI collaboration. Through a comprehensive analysis of current technologies and future possibilities, this study provides insights into how self-improving AI is revolutionizing customer service, promising more efficient, personalized, and satisfying experiences for customers.

Optimizing LLM Strategies for Playing Mendikot using Prompt Engineering

This study investigates the integration of a large language model (LLM) enhanced by prompt engineering and game theory to effectively engage in the strategic card game Mendikot. By refining complex prompts and leveraging a tailored visual understanding of game dynamics, we significantly bolster the decision-making prowess of the LLM. Our methodology involved the systematic simplification of game prompts to facilitate deeper learning and faster response times, coupled with the implementation of a visual recognition system to interpret and react to game states dynamically. The results illustrate that the adapted LLM outperforms traditional AI approaches in strategic decision-making tasks, underscoring a substantial improvement in both the accuracy and efficiency of game-play. This research not only demonstrates a viable model for enhancing AI interaction in recreational gaming but also opens avenues for deploying advanced AI strategies in complex strategic environments, offering insights into the broader application of AI in leisure and competitive arenas. The findings suggest that AI can transcend conventional gaming roles, potentially transforming strategic gameplay in digital and physical platforms.

Voice or text? The role of physician media choice on patient experience in online medical communities

AbstractOnline medical communities (OMCs) are a type of online healthcare, in which physician‐patient interaction can be comprised of a variety of media options such as pictures, text, and voice. These media formats are often used to create a personalized patient experience in AI‐driven conversational healthcare platforms. To explore how physician media usage affects patient experience, we propose a counterfactual causal inference model using AI‐driven data mining methods on 131,083 online consultation records and 7,666,111 messages sent by physicians from one of the largest OMCs in China. Our study reveals the negative impact of physician use of voice on patient experience, compared to text. Drawing upon social support theory, we identify the mechanism by which physician media usage for voice produces a negative effect. The findings indicate that the negative effect of physicians' voice‐media usage occurs mainly in low‐risk disease conditions, by weakening the role of professional and emotional support. In contrast, in high‐risk disease conditions, voice‐media usage strengthens the role of professional and emotional support in improving the patient's experience. Our study is one of the first to focus on the social support attributes of the different media formats used in OMCs. We use advanced AI text‐analysis algorithms to extract features related to social support in physician‐patient conversations, and thus contribute to the use of AI in feature extraction for research.

A Survey of AI-Powered Proactive Threat-Hunting Techniques: Challenges and Future Directions

The study narrates the dimensions of AI-powered threat hunting techniques that keep changing and draws on their importance in cybersecurity measures while dealing with advanced cyber threats. While the cyber adversary is continuously adapting and innovating, the integration of advanced AI algorithms, including reinforcement learning and hybrid models, has become one of the key strategies for real-time threat detection and response. The research investigates the transformative potential of these algorithms to facilitate adaptive systems that can quickly recognize and act on new attack vectors. It also discusses the integration of AI with emergent technologies like blockchain, quantum computing, and IoT in the dimension of their potential to leverage threat intelligence and response mechanisms. This would naturally lead to increased efficiency in threat hunting by leveraging the strengths brought into this endeavor by both the AI systems and human analysts. The study also advocates for the development of strong policy and governance frameworks to drive home some ethical concerns in deploying AI in cybersecurity. Such a framework is very important for addressing challenges on data privacy, accountability, and transparency. The findings bring into sharp relief that, in this continuing evolution of the cybersecurity landscape, what will work best is a proactive stance-a proactive stance that incorporates innovative technologies with human ingenuity and ethics. This white paper broadly documents the considerable promise of AI in threat hunting and strategic advances needed to harden organizational defenses against a dynamic threat environment.

AI-Driven Numerical Optimization for Carbon Footprint Reduction and Sustainable Supply Chain Management in the Fashion Industry

This study explores how AI-driven optimization can help lower the carbon footprint of the fashion industry's supply chain. By using advanced AI models, the research delves into sustainable strategies across core areas—sourcing, production, logistics, and retail—focusing on reducing emissions, energy use, water consumption, and waste. Techniques like linear programming, genetic algorithms, and reinforcement learning showcase how AI can bring about real, measurable environmental benefits. The findings reveal that these optimized processes boost energy efficiency, save water, and cut down waste, making them valuable tools for sustainable supply chain management. The study wraps up with practical recommendations for adopting AI-based models to help the fashion industry embrace sustainability more effectively.

Deepfakes and Higher Education: A Research Agenda and Scoping Review of Synthetic Media

The availability of software which can produce convincing, yet synthetic media poses both threats and benefits to tertiary education globally. While other forms of synthetic media exist, this study focuses on deepfakes: advanced Generative AI (GenAI) imitations of real people’s likeness or voice. This conceptual paper assesses the current literature on deepfakes across multiple disciplines by conducting an initial scoping review of 182 peer-reviewed publications. The review reveals three major trends: detection methods, malicious applications, and potential benefits, although no specific studies on deepfakes in the tertiary educational context were found. Following a discussion of these trends, we apply the findings to postulate the major risks and potential mitigation strategies of deepfake technologies in higher education, as well as potential beneficial uses to aid the teaching and learning of both deepfakes and synthetic media. This culminates in the proposal of a research agenda to build a comprehensive, cross-cultural approach to investigate deepfakes in higher education.

Intelligent Data Governance Frameworks : A Technical Overview

This comprehensive article explores the transformative potential of AI-driven data governance frameworks in addressing modern data management challenges. The article examines the limitations of traditional governance methods in the face of exponential data growth, regulatory complexities, and diverse data sources. It delves into the architecture, core components, and benefits of intelligent governance systems that leverage advanced AI technologies such as machine learning, natural language processing, and reinforcement learning. The article highlights significant improvements in operational efficiency, compliance accuracy, and data quality achieved through AI-driven solutions. Furthermore, it investigates future directions, including the integration of explainable AI, federated learning, and blockchain technology, while acknowledging the challenges that need to be addressed for widespread adoption.