Search Results (126)

Understanding and accurately estimating cognitive workload is crucial for the development of adaptive, user-centered interactive systems across a variety of domains including augmented reality, automotive driving assistance, and intelligent tutoring systems. Cognitive workload assessment enables dynamic system adaptation to improve user experience and safety. In this work, we introduce a novel framework that leverages smooth pursuit eye movements as a non-invasive and temporally precise indicator of mental effort. A key innovation of our approach is the development of trajectory-independent algorithms that address a significant limitation of existing methods, which generally rely on a predefined or known stimulus trajectory. Our framework leverages two solutions to provide accurate cognitive load estimation, without requiring knowledge of the exact target path, based on Kalman filter and B-spline heuristic classifiers. This enables the application of our methods in more naturalistic and unconstrained environments where stimulus trajectories may be unknown. We evaluated these algorithms against classical supervised machine learning models on a publicly available benchmark dataset featuring diverse pursuit trajectories and varying cognitive workload conditions. The results demonstrate competitive performance along with robustness across different task complexities and trajectory types. Moreover, our framework supports real-time inference, making it viable for continuous cognitive workload monitoring. To further enhance deployment feasibility, we propose a federated learning architecture, allowing privacy-preserving adaptation of models across heterogeneous devices without the need to share raw gaze data. This scalable approach mitigates privacy concerns and facilitates collaborative model improvement in distributed real-world scenarios. Experimental findings confirm that metrics derived from smooth pursuit eye movements reliably reflect fluctuations in cognitive states induced by working memory load tasks, substantiating their use for real-time, continuous workload estimation. By integrating trajectory independence, robust classification techniques, and federated privacy-aware learning, our work advances the state of the art in adaptive human–computer interaction. This framework offers a scientifically grounded, privacy-conscious, and practically deployable solution for cognitive workload estimation that can be adapted to diverse application contexts. Full article

Undergraduate life science education faces high attrition rates, especially among students from underrepresented groups. These disparities are often linked to differences in prior knowledge, self-efficacy, and interest, which are rarely addressed in traditional lecture-based instruction. This work explores the use of machine learning-based Intelligent Tutoring Systems (ITSs) to support personalized instruction in biology education by examining stochasticity in molecular systems. Accordingly, we developed and validated a Random Forest classification model and used it to assign instructional materials based on students’ prior knowledge and interests. We then applied the model in an introductory biology classroom and individually estimated the most promising instructional format. Results show that the most effective instruction can be reliably predicted from student performance and interest profiles, and model-based assignments may help reduce pre-existing opportunity gaps. Thus, machine-learning-driven instruction holds promise for enhancing equity in life science education by aligning materials with students’ needs, potentially reducing differences in achievement, self-efficacy, and cognitive load, which might be relevant to promoting underrepresented students. To facilitate a straightforward implementation for educators facing similar challenges associated with teaching molecular stochasticity, we developed an open-access ITS tool and provided a scalable approach for developing similar personalized learning tools. Full article

Artificial Intelligence (AI) has brought a revolution in many areas, including the education sector. It has the potential to improve learning practices, innovate teaching, and accelerate the path towards personalized learning. This work introduces Reinforcement Learning (RL) methods to develop a personalized examination scheduling system at a university level. We use two widely established RL algorithms, Q-Learning and Proximal Policy Optimization (PPO), for the task of personalized exam scheduling. We consider several key points, including learning efficiency, the quality of the personalized educational path, adaptability to changes in student performance, scalability with increasing numbers of students and courses, and implementation complexity. Experimental results, based on case studies conducted within a single degree program at a university, demonstrate that, while Q-Learning offers simplicity and greater interpretability, PPO offers superior performance in handling the complex and stochastic nature of students’ learning trajectories. Experimental results, conducted on a dataset of 391 students and 5700 exam records from a single degree program, demonstrate that PPO achieved a 42.0% success rate in improving student scheduling compared to Q-Learning’s 26.3%, with particularly strong performance on problematic students (41.3% vs 18.0% improvement rate). The average delay reduction was 5.5 months per student with PPO versus 3.0 months with Q-Learning, highlighting the critical role of algorithmic design in shaping educational outcomes. This work contributes to the growing field of AI-based instructional support systems and offers practical guidance for the implementation of intelligent tutoring systems. Full article

The rapid integration of artificial intelligence technologies into higher education presents unprecedented opportunities for enhancing computational thinking development while simultaneously raising significant concerns about educational equity and algorithmic bias. This comprehensive review examines the intersection of AI integration, computational thinking pedagogy, and diversity, equity, and inclusion imperatives in higher education through a comprehensive narrative review of 167 sources of current literature and theoretical frameworks. From distilling principles from Human–AI Symbiotic Theory (HAIST) and established pedagogical integration models, this review synthesizes evidence-based strategies for ensuring that AI-enhanced computational thinking environments advance rather than undermine educational equity. The analysis reveals that effective AI integration in computational thinking education requires comprehensive frameworks that integrate ethical AI governance with pedagogical design principles, creating practical guidance for institutions seeking to harness AI’s potential while protecting historically marginalized students from algorithmic discrimination. This review contributes to the growing body of knowledge on responsible AI implementation in educational settings and provides actionable recommendations for educators, researchers, and policymakers working to create more effective, engaging, and equitable AI-enhanced learning environments. Full article

This paper presents a protocol-driven hybrid architecture that integrates Retrieval-Augmented Generation (RAG) with two complementary protocols—A Model Context Protocol (MCP) and an Agent Communication Protocol (ACP)—to deliver adaptive, transparent, and interoperable intelligent tutoring for higher-education STEM courses. MCP stores, fuses, and exposes session-, task- and course-level context (learning goals, prior errors, instructor flags, and policy constraints), while ACP standardizes multipart messaging and orchestration among specialized tutor agents (retrievers, context managers, pedagogical policy agents, execution tools, and generators). A Python prototype indexes curated course materials (two course corpora: a text-focused PDF and a multimodal PDF/transcript corpus) into a vector store and applies MCP-mediated re-ranking (linear fusion of semantic similarity, MCP relevance, instructor tags, and recency) before RAG prompt assembly. In a held-out evaluation (240 annotated QA pairs) and human studies (36 students, 12 instructors), MCP-aware re-ranking improved Recall@1, increased citation fidelity, reduced unsupported numerical claims, and raised human ratings for factuality and pedagogical appropriateness. Case studies demonstrate improved context continuity, scaffolded hinting under instructor policies, and useful multimodal grounding. The paper concludes that the ACP–MCP–RAG combination enables more trustworthy, auditable, and pedagogically aligned tutoring agents and outlines directions for multimodal extensions, learned re-rankers, and large-scale institutional deployment. Full article

The integration of generative artificial intelligence, particularly large language models, into education presents opportunities for both personalised learning and pedagogical challenges. This study focuses on electrical engineering laboratory education. We developed a configurable prototype of a generative artificial intelligence powered tutoring tool, implemented it in an undergraduate electrical engineering laboratory course, and analysed 208 student–tutoring tool interactions using a mixed-methods approach that combined research team evaluation with learner feedback. The findings show that student prompts were predominantly procedural or factual, with limited conceptual or metacognitive engagement. Structured prompt styles produced clearer and more coherent responses and were rated the highest by students, while approaches aimed at fostering reasoning and reflection were valued mainly by the research team for their pedagogical depth. This contrast highlights a consistent preference–pedagogy gap, indicating the need to embed stronger instructional guidance into artificial intelligence tutoring. To bridge this gap, a promising direction is the development of pedagogically enriched AI tutors that integrate features such as adaptive prompting, hybrid strategy blending, and retrieval-augmented feedback to balance clarity, engagement, and depth. The results provide practical and conceptual value relevant to educators, developers, and researchers interested in artificial intelligence tutors that are both engaging and pedagogically sound. For educators, the study clarifies how students interact with tutors, helping align artificial intelligence use with instructional goals. For developers, it highlights the importance of designing systems that combine usability with educational value. For researchers, the findings identify directions for further study on how design choices in artificial intelligence tutoring affect learning processes and pedagogical alignment across STEM contexts. On a broader level, the study contributes to a more transparent, equitable, and sustainable integration of generative AI in education. Full article

Knowledge Tracing aims to assess students’ mastery of knowledge concepts in real time, playing a crucial role in providing personalized learning services in intelligent tutoring systems. In recent years, researchers have attempted to introduce Neural Architecture Search (NAS) into knowledge tracing tasks to automatically design more efficient network structures. However, existing NAS-based methods for Knowledge Tracing suffer from excessively large search spaces and slow search efficiency, which significantly constrain their practical applications. To address these limitations, this paper proposes an Adaptive Neural Architecture Search framework based on Transformers for KT, called ANT-KT. Specifically, we design an enhanced encoder that combines convolution operations with state vectors to capture both local and global dependencies in students’ learning sequences. Moreover, an optimized decoder with a linear attention mechanism is introduced to improve the efficiency of modeling long-term student knowledge state evolution. We further propose an evolutionary NAS algorithm that incorporates a model optimization efficiency objective and a dynamic search space reduction strategy, enabling the discovery of high-performing yet computationally efficient architectures. Experimental results on two large-scale real-world datasets, EdNet and RAIEd2020, demonstrate that ANT-KT significantly reduces time costs across all stages of NAS while achieving performance improvements on multiple evaluation metrics, validating the efficiency and practicality of the proposed method. Full article

As AI systems become more integrated into society, the relationship between humans and AI is shifting from simple automation to co-creative collaboration. This evolution is particularly important in education, where human intuition and imagination can combine with AI’s computational power to enable innovative forms of learning and teaching. This study is grounded in the #ppAI6 model, a framework that describes six levels of creative engagement with AI in educational contexts, ranging from passive consumption to active, participatory co-creation of knowledge. The model highlights progression from initial interactions with AI tools to transformative educational experiences that involve deep collaboration between humans and AI. In this study, we explore how educators and learners can engage in deeper, more transformative interactions with AI technologies. The #ppAI6 model categorizes these levels of engagement as follows: level 1 involves passive consumption of AI-generated content, while level 6 represents expansive, participatory co-creation of knowledge. This model provides a lens through which we investigate how educational tools and practices can move beyond basic interactions to foster higher-order creativity. We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for reporting the levels of creative engagement with AI tools in education. This review synthesizes existing literature on various levels of engagement, such as interactive consumption through Intelligent Tutoring Systems (ITS), and shifts focus to the exploration and design of higher-order forms of creative engagement. The findings highlight varied levels of engagement across both learners and educators. For learners, a total of four studies were found at level 2 (interactive consumption). Two studies were found that looked at level 3 (individual content creation). Four studies focused on collaborative content creation at level 4. No studies were observed at level 5, and only one study was found at level 6. These findings show a lack of development in AI tools for more creative involvement. For teachers, AI tools mainly support levels two and three, facilitating personalized content creation and performance analysis with limited examples of higher-level creative engagement and indicating areas for improvement in supportive collaborative teaching practices. The review found that two studies focused on level 2 (interactive consumption) for teachers. In addition, four studies were identified at level 3 (individual content creation). Only one study was found at level 5 (participatory co-creation), and no studies were found at level 6. In practical terms, the review suggests that educators need professional development focused on building AI literacy, enabling them to recognize and leverage the different levels of creative engagement that AI tools offer. Full article

Breast cancer is a leading cause of mortality among women, disproportionately affecting Hispanic populations in the U.S., particularly those with limited health literacy and language access. To address these disparities, we present a bilingual, web-based educational platform tailored to low-literacy Hispanic users. The platform supports full navigation in English and Spanish, with seamless language switching and both written and spoken input options. It incorporates automatic speech recognition (ASR) capable of handling code-switching, enhancing accessibility for bilingual users. Educational content is delivered through culturally sensitive videos organized into four categories: prevention, detection, diagnosis, and treatment. Each video includes embedded and post-video assessment questions aligned with Bloom’s Taxonomy to foster active learning. Users can monitor their progress and quiz performance via a personalized dashboard. An integrated chatbot, powered by large language models (LLMs), allows users to ask foundational breast cancer questions in natural language. The platform also recommends relevant resources, including nearby treatment centers, and support groups. LLMs are further used for ASR, question generation, and semantic response evaluation. Combining language technologies and LLMs reduces disparities in cancer education and supports informed decision-making among underserved populations, playing a pivotal role in reducing information gaps and promoting informed healthcare decisions. Full article

The increasing ubiquity of wearable computing and multimodal interaction technologies has created unprecedented opportunities for natural and seamless human–computer interaction. However, most existing systems adapt only to external user actions such as speech, gesture, or gaze, without considering internal cognitive or affective states. This limits their ability to provide intelligent and empathetic adaptations. This paper addresses this critical gap by proposing the Neuro-Adaptive Multimodal Architecture (NAMI), a principled, modular, and reproducible framework designed to integrate behavioral and neurophysiological signals in real time. NAMI combines multimodal behavioral inputs with lightweight EEG and peripheral physiological measurements to infer cognitive load and engagement and adapt the interface dynamically to optimize user experience. The architecture is formally specified as a three-layer pipeline encompassing sensing and acquisition, cognitive–affective state estimation, and adaptive interaction control, with clear data flows, mathematical formalization, and real-time performance on wearable platforms. A prototype implementation of NAMI was deployed in an augmented reality Java programming tutor for postgraduate informatics students, where it dynamically adjusted task difficulty, feedback modality, and assistance frequency based on inferred user state. Empirical evaluation with 100 participants demonstrated significant improvements in task performance, reduced subjective workload, and increased engagement and satisfaction, confirming the effectiveness of the neuro-adaptive approach. Full article

The integration of Virtual Worlds (VW) and Intelligent Tutoring Systems (ITS) represents a transformative advancement in education, combining immersive, interactive learning with AI-driven personalization. This study explores the synergies between these technologies, analyzing their benefits, challenges, and applications in domains such as medical training, STEM education, and language learning. Findings highlight their shared characteristics of adaptability, real-time feedback, and collaborative learning. However, challenges such as computational demands, pedagogical complexity, and ethical concerns must be addressed. Future research should focus on hybrid models leveraging blockchain, IoT, and augmented reality to enhance adaptive and scalable learning experiences. Full article

This study investigates the adoption of PyChatAI, a bilingual AI-powered chatbot for Python programming education, among female computer science students at Jouf University. Guided by the Technology Acceptance Model 3 (TAM3), it examines the determinants of user acceptance and usage behaviour. A Solomon Four-Group experimental design (N = 300) was used to control pre-test effects and isolate the impact of the intervention. PyChatAI provides interactive problem-solving, code explanations, and topic-based tutorials in English and Arabic. Measurement and structural models were validated via Confirmatory Factor Analysis (CFA) and Structural Equation Modelling (SEM), achieving excellent fit (CFI = 0.980, RMSEA = 0.039). Results show that perceived usefulness (β = 0.446, p < 0.001) and perceived ease of use (β = 0.243, p = 0.005) significantly influence intention to use, which in turn predicts actual usage (β = 0.406, p < 0.001). Trust, facilitating conditions, and hedonic motivation emerged as strong antecedents of ease of use, while social influence and cognitive factors had limited impact. These findings demonstrate that AI-driven bilingual tools can effectively enhance programming engagement in gender-specific, culturally sensitive contexts, offering practical guidance for integrating intelligent tutoring systems into computer science curricula. Full article

The increasing integration of artificial intelligence into educational processes offers new opportunities to address critical issues in higher education, such as student dropout, academic underperformance, and the need for personalized tutoring. This scoping review aims to map the scientific literature on the use of AI techniques to predict academic performance, risk of dropout, and the need for academic advising, with an emphasis on e-learning or technology-mediated environments. The study follows the Joanna Briggs Institute PCC strategy, and the review was reported following the PRISMA-ScR checklist for search reporting. A total of 63 peer-reviewed empirical studies (2019–2025) were included after systematic filtering from the Scopus and Web of Science databases. The findings reveal that supervised machine learning models, such as decision trees, random forests, and neural networks, dominate the field, with an emerging interest in deep learning, transfer learning, and explainable AI. Academic, behavioral, emotional, and contextual variables are integrated into increasingly complex and interpretable models. Most studies focus on undergraduate students in digital and hybrid learning contexts, particularly in regions with high dropout rates. The review highlights the potential of AI to enable early intervention and improve the effectiveness of tutoring systems, while noting limitations such as lack of model generalization and ethical concerns. Recommendations are provided for future research and institutional integration. Full article

This paper examines the current implementation of Artificial Intelligence (AI) in higher education and its implications for inclusivity, particularly for minority groups. Using a rapid review methodology, it synthesises academic literature, policy reports, and case studies to explore how AI is reshaping educational environments. The analysis reveals that although AI technologies—such as adaptive learning systems, intelligent tutoring, and predictive analytics—are increasingly adopted, their primary aim remains institutional efficiency rather than fostering equity. Initiatives explicitly designed to support underrepresented students are rare, exposing a gap between technological innovation and inclusive practice. The study identifies key barriers, including socioeconomic inequality, cultural and linguistic bias, and limited institutional capacity, which are often compounded by AI systems trained on non-representative data. While isolated case studies demonstrate that (e.g., culturally) responsive AI can enhance educational access for marginalised learners, these remain exceptions rather than norms. The findings suggest that without deliberate efforts to embed inclusivity in AI design and deployment, existing inequalities may be perpetuated or worsened. The paper concludes that realising AI’s inclusive potential requires ethical frameworks, diverse development teams, and equitable access strategies. It calls for future empirical research focused on practical interventions that reduce disparities, contributing to a more just and inclusive higher education landscape. Full article

The intersection of Artificial Intelligence (AI) and education is revolutionizing learning and teaching in this digital era, with Generative AI and large language models (LLMs) providing even greater possibilities for the future. The digital transformation of language education demands innovative approaches that combine pedagogical rigor with explainable AI (XAI) principles, particularly for low-resource languages. This paper presents a novel methodology that integrates Business Process Model and Notation (BPMN) with Multi-Agent Systems (MAS) to create transparent, workflow-driven language tutors. Our approach uniquely embeds XAI through three mechanisms: (1) BPMN’s visual formalism that makes agent decision-making auditable, (2) Retrieval-Augmented Generation (RAG) with verifiable knowledge provenance from textbooks of the National Institute of Languages of Luxembourg, and (3) human-in-the-loop validation of both content and pedagogical sequencing. To ensure realism in learner interaction, we integrate speech-to-text and text-to-speech technologies, creating an immersive, human-like learning environment. The system simulates intelligent tutoring through agents’ collaboration and dynamic adaptation to learner progress. We demonstrate this framework through a Luxembourgish language learning platform where specialized agents (Conversational, Reading, Listening, QA, and Grammar) operate within BPMN-modeled workflows. The system achieves high response faithfulness (0.82) and relevance (0.85) according to RAGA metrics, while speech integration using Whisper STT and Coqui TTS enables immersive practice. Evaluation with learners showed 85.8% satisfaction with contextual responses and 71.4% engagement rates, confirming the effectiveness of our process-driven approach. This work advances AI-powered language education by showing how formal process modeling can create pedagogically coherent and explainable tutoring systems. The architecture’s modularity supports extension to other low-resource languages while maintaining the transparency critical for educational trust. Future work will expand curriculum coverage and develop teacher-facing dashboards to further improve explainability. Full article