AI

Background: Rapid advancements in large language models (LLMs) have significantly enhanced Retrieval-Augmented Generation (RAG) techniques, leading to more accurate and context-aware information retrieval systems. Methods: This article presents the creation of a RAG-based chatbot tailored for university course catalogs, aimed at answering queries related to course details and other essential academic information, and investigates its performance by testing it on several locally deployed large language models. By leveraging multiple LLM architectures, we evaluate performance of the models under test in terms of context length, embedding size, computational efficiency, and relevance of responses. Results: The experimental analysis obtained by this research, which builds on recent comparative studies, reveals that while larger models achieve higher relevance scores, they incur greater response times than smaller, more efficient models. Conclusions: The findings underscore the importance of balancing accuracy and efficiency for real-time educational applications. Overall, this work contributes to the field by offering insights into optimal RAG configurations and practical guidelines for deploying AI-powered educational assistants. Full article

The rapid adoption of artificial intelligence (AI) within social media platforms has fundamentally transformed the way Generation Z interacts with and navigates the digital landscape. While AI-driven algorithms enhance user experience through content personalization, they can also reinforce biases that affect the mental health and overall well-being of young individuals. This review delves into the intersections of AI bias, social medial engagement, and youth mental health, with a particular focus on how algorithmic decision-making influences exposure to harmful content, intensifies social comparison and spreads digital misinformation. By addressing these aspects, this article highlights both the risks and opportunities presented by AI-powered social media. It also advocates for evidence-based strategies to mitigate the harms associated with algorithmic bias, urging collaboration among AI developers, mental health experts, policymakers and educators at personal, community (school), and national and international levels to cultivate a safer, more supportive digital ecosystem for future generations. Full article

Background: Industry 4.0’s development requires digitalized manufacturing through Predictive Maintenance (PdM) because such practices decrease equipment failures and operational disruptions. However, its effectiveness is hindered by three key challenges: (1) data confidentiality, as traditional methods rely on centralized data sharing, raising concerns about security and regulatory compliance; (2) a lack of interpretability, where opaque AI models provide limited transparency, making it difficult for operators to trust and act on failure predictions; and (3) adaptability issues, as many existing solutions struggle to maintain a consistent performance across diverse industrial environments. Addressing these challenges requires a privacy-preserving, interpretable, and adaptive Artificial Intelligence (AI) model that ensures secure, reliable, and transparent PdM while meeting industry standards and regulatory requirements. Methods: Explainable AI (XAI) plays a crucial role in enhancing transparency and trust in PdM models by providing interpretable insights into failure predictions. Meanwhile, Federated Learning (FL) ensures privacy-preserving, decentralized model training, allowing multiple industrial sites to collaborate without sharing sensitive operational data. This proposed research developed a sustainable privacy-preserving Explainable FL (XFL) model that integrates XAI techniques like Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) into an FL structure to improve PdM’s security and interpretability capabilities. Results: The proposed XFL model enables industrial operators to interpret, validate, and refine AI-driven maintenance strategies while ensuring data privacy, accuracy, and regulatory compliance. Conclusions: This model significantly improves failure prediction, reduces unplanned downtime, and strengthens trust in AI-driven decision-making. The simulation results confirm its high reliability, achieving 98.15% accuracy with a minimal 1.85% miss rate, demonstrating its effectiveness as a scalable, secure, and interpretable solution for PdM in Industry 4.0. Full article

Background/Objectives: Artificial intelligence (AI) is increasingly integrated into everyday life, including the complex and highly regulated healthcare sector. Given healthcare’s essential role in safeguarding human life and well-being, AI deployment requires careful oversight to ensure safety, effectiveness, and ethical compliance. This paper aims to examine the current regulatory landscapes governing AI in healthcare, particularly in the European Union (EU) and the United States (USA), and to propose practical tools to support the responsible development and implementation of AI systems. Methods: The study reviews key regulatory frameworks, ethical guidelines, and expert recommendations from international bodies, professional associations, and governmental institutions in the EU and USA. Based on this analysis, the paper develops structured questionnaires tailored for AI developers and implementers to help operationalize regulatory and ethical expectations. Results: The proposed questionnaires address critical gaps in existing frameworks by providing actionable, lifecycle-oriented tools that span AI development, deployment, and clinical use. These instruments support compliance and ethical integrity while promoting transparency and accountability. Conclusions: The structured questionnaires can serve as practical tools for health technology assessments, public procurement, accreditation processes, and training initiatives. By aligning AI system design with regulatory and ethical standards, they contribute to building trustworthy, safe, and innovative AI applications in healthcare. Full article

This paper introduces a pioneering hybrid framework that integrates Q-learning/deep Q-network (DQN) with a locally deployed large language model (LLM) to enhance obstacle avoidance in embedded robotic systems. The STM32WB55RG microcontroller handles real-time decision-making using sensor data, while a Raspberry Pi 5 computer runs a quantized TinyLlama LLM to dynamically refine navigation strategies. The LLM addresses traditional Q-learning limitations, such as slow convergence and poor adaptability, by analyzing action histories and optimizing decision-making policies in complex, dynamic environments. A selective triggering mechanism ensures efficient LLM intervention, minimizing computational overhead. Experimental results demonstrate significant improvements, including up to 41% higher deadlock recovery (81% vs. 40% for Q-learning + LLM), up to 34% faster time to goal (38 s vs. 58 s for Q-learning + LLM), and up to 14% lower collision rates (11% vs. 25% for Q-learning + LLM) compared to standalone Q-learning/DQN. This novel approach presents a solution for scalable, adaptive navigation in resource-constrained embedded robotics, with potential applications in logistics and healthcare. Full article

Artificial intelligence, the simulation of human intelligence by computers and machines, has found its way into healthcare, helping surgeons, doctors, radiologists, and many more. However, over 80% of healthcare professionals consists of people working in allied health professions such as nurses, physiotherapists, and midwives. Considering the aging of the general population around the world, the workforce shortages in these occupations are especially crucial. As the COVID-19 pandemic demonstrated, globally, most healthcare systems are strained, and there is a consensus that current healthcare systems are not sustainable with the increasing challenges. AI is often viewed as one of the potential solutions for not only reducing the strain on the healthcare workforce, but also to sustain the current workforce. Still, most AI applications are being developed for the medical community and often allied health is overlooked or not even considered despite comprising a large proportion of the total workforce. In addition, the interest of the private sector to invest specifically in the allied health workforce is low since the financial incentive is low. This paper provides examples of AI solutions for seven important allied health professions. To increase the uptake of AI solutions in allied healthcare, AI companies need to connect more with professional associations and be as patient-oriented as many claim to be. There also needs to be more AI schooling for allied healthcare professionals to increase adoption of these AI solutions. Full article

Background: Screening for substance use disorder (SUD) is a critical step to address the ongoing opioid crisis in the U.S., but fewer than 10% of people at risk screen. Technology may play a role in substantially increasing screening by making screening accessible through artificially intelligent (AI) chatbots. Methods: This was a single-arm mixed-methods pilot study to establish the system usability of an AI chatbot delivering information about substances, substance use disorder, and treatment options, and implementing self-screening for anxiety, depression, and substance use disorder. Participants were asked to engage with the AI chatbot for seven days and could self-select to screen. Results: Of the 92 participants enrolled, 91 engaged with the system at least once, and 29 (32%) completed at least one screener. Those who screened were given a referral if they exhibited moderate or severe anxiety, depression, and/or SUD. Over three-quarters (83%) of those screened received a referral for treatment, and 50% of those referred made an appointment for care. Users indicated that they found the system helpful and informative, and they felt comfortable screening. Conclusions: While other AI systems that share information about mental health and substance use exist, we know of no other AI chatbot that is being deployed specifically to facilitate SUD screening and referral. The system we describe here shows potential to support self-screening. Users generally find the system acceptable to use. AI technology may allow for improved access to SUD screening and treatment referrals, a critical step in responding to the opioid crisis. Full article

Background: Cognitive resilience is a critical factor in high-performance environments such as military operations, where sustained stress can impair attention and decision-making. In the present study, we utilized EEG and machine learning to assess cognitive resilience in elite military personnel. Methods: For this purpose, EEG signals were recorded from elite military personnel during stress-inducing attention-related and emotional tasks. The EEG signals were segmented into two temporal windows corresponding to the initial stress response (baseline) and the adaptive/recovery phase, extracting power spectral density features across delta, theta, alpha, beta, and gamma bands. Different machine learning models (Decision Tree, Random Forest, AdaBoost, XGBoost) were trained to classify temporal phases. Results: XGBoost achieved the highest accuracy (0.95), while Shapley Additive Explanations (SHAP) analysis identified delta and alpha bands (particularly in frontal and parietal regions) as key features associated with adaptive mental states. Conclusions: Our findings indicate that resilience-related neural responses can be successfully distinguished and that interpretable AI frameworks can be used for monitoring cognitive adaptation in high-stress environments. Full article

Background/Objectives: Convolutional Neural Networks (CNNs), while effective in tasks such as image classification and language processing, often experience overfitting and inefficient training due to static, structure-agnostic regularization techniques like traditional dropout. This study aims to address these limitations by proposing a more dynamic and context-sensitive dropout strategy. Methods: We introduce Probabilistic Feature Importance Dropout (PFID), a novel regularization method that assigns dropout rates based on the probabilistic significance of individual features. PFID is integrated with adaptive, structured, and contextual dropout strategies, forming a unified framework for intelligent regularization. Results: Experimental evaluation on standard benchmark datasets including CIFAR-10, MNIST, and Fashion MNIST demonstrated that PFID significantly improves performance metrics such as classification accuracy, training loss, and computational efficiency compared to conventional dropout methods. Conclusions: PFID offers a practical and scalable solution for enhancing CNN generalization and training efficiency. Its dynamic nature and feature-aware design provide a strong foundation for future advancements in adaptive regularization for deep learning models. Full article

Background: The integration of Artificial Intelligence (AI) into Business Process Management Systems (BPMSs) has led to the emergence of AI-Augmented Business Process Management Systems (ABPMSs). These systems offer dynamic adaptation, real-time process optimization, and enhanced knowledge management capabilities. However, key challenges remain, particularly regarding explainability, user engagement, and behavioral integration. Methods: This study presents a novel framework that synergistically integrates the Socialization, Externalization, Combination, and Internalization knowledge model (SECI), Agile methods (specifically Scrum), and cutting-edge AI technologies, including explainable AI (XAI), process mining, and Robotic Process Automation (RPA). The framework enables the formalization, verification, and sharing of knowledge via a well-organized, user-friendly software platform and collaborative practices, especially Communities of Practice (CoPs). Results: The framework emphasizes situation-aware explainability, modular adoption, and continuous improvement to ensure effective human–AI collaboration. It provides theoretical and practical mechanisms for aligning AI capabilities with organizational knowledge management. Conclusions: The proposed framework facilitates the transition from traditional BPMSs to more sophisticated ABPMSs by leveraging structured methodologies and technologies. The approach enhances knowledge exchange and process evolution, supported by detailed modeling using BPMN 2.0. Full article

Synthetic medical text generation has emerged as a solution to data scarcity and privacy constraints in clinical NLP. This review systematically evaluates the use of Large Language Models (LLMs) for structured medical text generation, examining techniques such as retrieval-augmented generation (RAG), structured fine-tuning, and domain-specific adaptation. Four search queries were applied following the PRISMA methodology to identify and extract data from 153 studies. Key benchmarking metrics, such as performance measures, and qualitative insights, including methodological trends and challenges, were documented. The results show that while LLM-generated text improves fluency, hallucinations and factual inconsistencies persist. Structured consultation models, such as SOAP and Calgary–Cambridge, enhance coherence but do not fully prevent errors. Hybrid techniques that combine retrieval-based grounding with domain-specific fine-tuning improve factual accuracy and task performance. Conventional evaluation metrics (e.g., ROUGE, BLEU) are insufficient for medical validation, highlighting the need for domain-specific benchmarks. Privacy-preserving strategies, including differential privacy and PHI de-identification, support regulatory compliance but may reduce linguistic quality. These findings are relevant for clinical NLP applications, such as AI-powered scribe systems, where structured synthetic datasets can improve transcription accuracy and documentation reliability. The conclusions highlight the need for balanced approaches that integrate medical structure, factual control, and privacy to enhance the usability of synthetic medical text. Full article

(1) Background: Machine unlearning plays a crucial role in privacy protection and model optimization, particularly in forgetting entire categories of data in classification tasks. However, existing methods often struggle with high computational costs, such as estimating the inverse Hessian, or require access to the original training data, limiting their practicality. (2) Methods: In this work, we introduce Scrub-and-Learn, which is a category-aware weight modification framework designed to remove class-level knowledge efficiently. By modeling unlearning as a continual learning task, our method leverages re-encoded labels of samples from the target category to guide weight updates, effectively scrubbing unwanted knowledge while preserving the rest of the model’s capacity. (3) Results and Conclusions: Experimental results on multiple benchmarks demonstrate that our method effectively eliminates targeted categories—achieving a recognition rate below $5\%$—while preserving the performance of retained classes within a $4\%$ deviation from the original model. Full article

Background: Robotic-based therapy has emerged as a prominent treatment modality for the rehabilitation of hand function impairment resulting from strokes. Aim: In this context, feature engineering becomes particularly important to estimate the intention of upper limb movements by utilizing machine learning models, especially when a hardware embedded-on-board implementation is expected, due to the strong computational, energy, and latency constraints. Methods: The present study details the implementation of four cutting-edge feature engineering techniques (random forest, minimum redundancy maximum relevance (MRMR), Davies–Bouldin index, and t-tests) in the context of machine learning algorithms (neuronal networks and bagged forests) deployed within a resource-constrained autonomous embedded system. Results: The findings of this study demonstrate that by assigning relative importance to features and removing redundant or superfluous information, it is possible to enhance the system’s execution by up to 31% while preserving the model’s performance at a comparable level. Conclusions: This work proves the usefulness of TinyML as an approach to properly integrate AI into constrained edge embedded systems to support complex strategies such as the proposed hand gesture recognition for the smart rehabilitation of post-stroke patients. Full article

Background/Objectives: Large Language Models (LLMs) like ChatGPT, LLAMA, and Mistral are widely used for automating tasks such as content creation and data analysis. However, due to their training on publicly available internet data, they may inherit social biases. We aimed to investigate the social biases (i.e., ethnic, gender, and disability biases) in these models and evaluate how different model versions handle them. Methods: We instruction-tuned popular models (like Mistral, LLAMA, and Gemma), and for this we curated a dataset constructed by collecting and modifying diverse data from various public datasets. Prompts were run through a controlled pipeline, and responses were categorized (e.g., biased, confused, repeated, or accurate) and analyzed. Results: We found that models responded differently to bias prompts depending on their version. Fine-tuned models showed fewer overt biases but more confusion or censorship. Disability-related prompts triggered the most consistent biases across models. Conclusions: Bias persists in LLMs despite instruction tuning. Differences between model versions may lead to inconsistent user experiences and hidden harms in downstream applications. Greater transparency and robust fairness testing are essential. Full article

Neural Ordinary Differential Equations (Neural ODEs) have emerged as a promising approach for learning the continuous-time behaviour of dynamical systems from data. However, Neural ODEs are black-box models, posing challenges in interpreting and understanding their decision-making processes. This raises concerns about their application in critical domains such as healthcare and autonomous systems. To address this challenge and provide insight into the decision-making process of Neural ODEs, we introduce the eXplainable Neural ODE (XNODE) framework, a suite of eXplainable Artificial Intelligence (XAI) techniques specifically designed for Neural ODEs. Drawing inspiration from classical visualisation methods for differential equations, including time series, state space, and vector field plots, XNODE aims to offer intuitive insights into model behaviour. Although relatively simple, these techniques are intended to furnish researchers with a deeper understanding of the underlying mathematical tools, thereby serving as a practical guide for interpreting results obtained with Neural ODEs. The effectiveness of XNODE is verified through case studies involving a Resistor–Capacitor (RC) circuit, the Lotka–Volterra predator-prey dynamics, and a chemical reaction. The proposed XNODE suite offers a more nuanced perspective for cases where low Mean Squared Error values are obtained, which initially suggests successful learning of the data dynamics. This reveals that a low training error does not necessarily equate to comprehensive understanding or accurate modelling of the underlying data dynamics. Full article

This study addresses the problem of authorship attribution with a novel method for modeling writing style using dependency tree subtree parsing. This method exploits the syntactic information of sentences using mixed syntactic n-grams (mixed sn-grams). The method comprises an algorithm to generate mixed sn-grams by integrating words, POS tags, and dependency relation tags. The mixed sn-grams are used as style markers to feed Machine Learning methods such as a SVM. A comparative analysis was performed to evaluate the performance of the proposed mixed sn-grams method against homogeneous sn-grams with the PAN-CLEF 2012 and CCAT50 datasets. Experiments with PAN 2012 showed the potential of mixed sn-grams to model a writing style by outperforming homogeneous sn-grams. On the other hand, experiments with CCAT50 showed that training with mixed sn-grams improves accuracy over homogeneous sn-grams, with the POS-Word category showing the best result. The study’s results suggest that mixed sn-grams constitute effective stylistic markers for building a reliable writing style model, which machine learning algorithms can learn. Full article

Background/Objectives: The resilience of safety-critical systems is gaining importance due to the rise in cyber and physical threats, especially within critical infrastructure. Traditional static resilience metrics may not capture dynamic system states, leading to inaccurate assessments and ineffective responses to cyber threats. This work aims to develop a data-driven, adaptive method for resilience metric learning. Methods: We propose a data-driven approach using inverse reinforcement learning (IRL) to learn a single, adaptive resilience metric. The method infers a reward function from expert control actions. Unlike previous approaches using static weights or fuzzy logic, this work applies adversarial inverse reinforcement learning (AIRL), training a generator and discriminator in parallel to learn the reward structure and derive an optimal policy. Results: The proposed approach is evaluated on multiple scenarios: optimal communication network rerouting, power distribution network reconfiguration, and cyber–physical restoration of critical loads using the IEEE 123-bus system. Conclusions: The adaptive, learned resilience metric enables faster critical load restoration in comparison to conventional RL approaches. Full article

In this article, we propose a robust star classification methodology leveraging light curves collected from 15 datasets within the Kepler field in the visible optical spectrum. By employing a Bagging neural network ensemble approach, specifically an Bagging-Performance Approach Neural Network (BAPANN), which integrates three supervised neural network architectures, we successfully classified 760 samples of curves which represent 9 type of stars. Our method demonstrated a high classification accuracy of up to 97% using light curve datasets containing 13, 20, 50, 150, and 450 points per star. The BAPANN achieved a minimum error rate of 0.1559 and exhibited efficient learning, requiring an average of 29 epochs. Additionally, nine types of stellar variability were classified through 45 conducted tests, taking into account error margins of 0, 5, and 10 for the light curve samples. These results highlight the BAPANN model’s robustness against uncertainty and ability to converge quickly in terms of iterations needed for learning, training, and validation. Full article

In today’s high-stakes arenas—from healthcare to defense—algorithms are advancing at an unprecedented pace, yet they still lack a crucial element of human decision-making: an instinctive caution that helps prevent harm. Inspired by both the protective reflexes seen in military robotics and the human amygdala’s role in threat detection, we introduce a novel idea: an integrated module that acts as an internal “caution system”. This module does not experience emotion in the human sense; rather, it serves as an embedded safeguard that continuously assesses uncertainty and triggers protective measures whenever potential dangers arise. Our proposed framework combines several established techniques. It uses Bayesian methods to continuously estimate the likelihood of adverse outcomes, applies reinforcement learning strategies with penalties for choices that might lead to harmful results, and incorporates layers of human oversight to review decisions when needed. The result is a system that mirrors the prudence and measured judgment of experienced clinicians—hesitating and recalibrating its actions when the data are ambiguous, much like a doctor would rely on both intuition and expertise to prevent errors. We call on computer scientists, healthcare professionals, and policymakers to collaborate in refining and testing this approach. Through joint research, pilot projects, and robust regulatory guidelines, we aim to ensure that advanced computational systems can combine speed and precision with an inherent predisposition toward protecting human life. Ultimately, by embedding this cautionary module, the framework is expected to significantly reduce AI-induced risks and enhance patient safety and trust in medical AI systems. It seems inevitable for future superintelligent AI systems in medicine to possess emotion-like processes. Full article