Search Results (31)

To address the limitations of low fusion efficiency and insufficient personalization in multimodal perception for educational intelligence, a novel deep learning framework is proposed that integrates image sensor data with textual and contextual information through a cross-modal attention mechanism. The architecture employs a cross-modal alignment module to achieve fine-grained semantic correspondence between visual features captured by image sensors and associated textual elements, followed by a personalized feedback generator that incorporates learner background and task context embeddings to produce adaptive educational guidance. A cognitive weakness highlighter is introduced to enhance the discriminability of task-relevant features, enabling explicit localization and interpretation of conceptual gaps. Experiments show the proposed method outperforms conventional fusion and unimodal baselines with 92.37% accuracy, 91.28% recall, and 90.84% precision. Cross-task and noise-robustness tests confirm its stability, while ablation studies highlight the fusion module’s +4.2% accuracy gain and the attention mechanism’s +3.8% recall and +3.5% precision improvements. These results establish the proposed method as a transferable, high-performance solution for next-generation adaptive learning systems, offering precise, explainable, and context-aware feedback grounded in advanced multimodal perception modeling. Full article

Educational games often fail to effectively merge game mechanics with educational goals, lacking adaptive feedback and real-time performance monitoring. This study explores how Human–Computer Interaction principles and adaptive feedback can enhance educational game design to improve learning outcomes and user experience. Four educational games were analyzed using a mixed-methods approach and evaluated through established frameworks, such as the Serious Educational Games Evaluation Framework, the Assessment of Learning and Motivation Software, the Learning Object Evaluation Scale for Students, and Universal Design for Learning guidelines. In addition, a novel Human–Machine Pair Inspection protocol was employed to gather real-time data on adaptive feedback, cognitive load, and interactive behavior. Findings suggest that Human–Machine Pair Inspection-based adaptive mechanisms significantly boost personalized learning, knowledge retention, and student motivation by better aligning games with learning objectives. Although the sample size is small, this research provides practical insights for educators and designers, highlighting the effectiveness of adaptive Game-Based Learning. The study proposes the Human–Machine Pair Inspection methodology as a valuable tool for creating educational games that successfully balance user experience with learning goals, warranting further empirical validation with larger groups. Full article

As new technologies shape education, helping students develop historical consciousness remains a challenge. Building on Nordic curricula that emphasize students as both “history-made” and “history-making” citizens, this paper proposes an approach that integrates artificial intelligence (AI) with implicit digital game-based learning (DGBL) to learn and develop historical consciousness in education. We outline how traditional, lecture-driven history teaching often fails to convey the abstract principles of historicity (the idea that individual identity, social institutions, values, and ways of thinking are historically conditioned) and the interpretation of the past, understanding of the present, and perspective on the future. Building on Jeismann’s definition of historical consciousness, we identify a gap between the theory-rich notions of historical consciousness and classroom practice, where many educators either do not recognize it or interpret it intuitively from the curriculum’s limited wording, leaving the concept generally absent from the classroom. We then examine three theory-based methods of enriching teaching and learning. Game-based learning provides an interactive environment in which students assume roles, make decisions, and observe consequences, experiencing historical consciousness instead of only reading about it. AI contributes personalized, adaptive content: branching narratives evolve based on individual choices, non-player characters respond dynamically, and analytics guide scaffolding. Implicit learning theory suggests that embedding core principles directly into gameplay allows students to internalize complex ideas without interrupting immersion; they learn by doing, not by explicit instruction. Finally, we propose a model in which these elements combine: (1) game mechanics and narrative embed principles of historical consciousness; (2) AI dynamically adjusts challenges, generates novel scenarios, and delivers feedback; (3) key concepts are embedded into the game narrative so that students absorb them implicitly; and (4) follow-up reflection activities transform tacit understanding into explicit knowledge. We conclude by outlining a research agenda that includes prototyping interactive environments, conducting longitudinal studies to assess students’ learning outcomes, and exploring transferability to other abstract concepts. By situating students within scenarios that explore historicity and temporal interplay, this approach seeks to transform history education into an immersive, reflective practice where students see themselves as history-made and history-making and view the world through a historical lens. Full article

Motor impairments significantly affect individuals’ ability to perform activities of daily living, reducing autonomy and quality of life. In response to this, robot-assisted rehabilitation has emerged as an effective and practical solution, enabling controlled limb movements and supporting functional recovery. This study presents the development of an upper-limb exoskeleton designed to assist rehabilitation by integrating neurophysiological signal processing and real-time control strategies. The system incorporates a proportional–derivative (PD) controller to execute cyclic flexion and extension movements based on a sinusoidal reference signal, providing repeatability and precision in motion. The exoskeleton integrates a brain–computer interface (BCI) that utilizes electroencephalographic signals for therapy selection and engagement enabling user-driven interaction. The EEG data extraction was possible by using the UltraCortex Mark IV headset, with electrodes positioned according to the international 10–20 system, targeting alpha-band activity in channels O1, O2, P3, P4, Fp1, and Fp2. These channels correspond to occipital (O1, O2), parietal (P3, P4), and frontal pole (Fp1, Fp2) regions, associated with visual processing, sensorimotor integration, and attention-related activity, respectively. This approach enables a more adaptive and personalized rehabilitation experience by allowing the user to influence therapy mode selection through real-time feedback. Experimental evaluation across five subjects showed an overall mean accuracy of 86.25% in alpha wave detection for EEG-based therapy selection. The PD control strategy achieved smooth trajectory tracking with a mean angular error of approximately 1.70°, confirming both the reliability of intention detection and the mechanical precision of the exoskeleton. Also, our core contributions in this research are compared with similar studies inspired by the rehabilitation needs of stroke patients. In this research, the proposed system demonstrates the potential of integrating robotic systems, control theory, and EEG data processing to improve rehabilitation outcomes for individuals with upper-limb motor deficits, particularly post-stroke patients. By focusing the exoskeleton on a single degree of freedom and employing low-cost manufacturing through 3D printing, the system remains affordable across a wide range of economic contexts. This design choice enables deployment in diverse clinical settings, both public and private. Full article

This study addresses the shortcomings of traditional exercise volume assessment methods in dynamic modeling and individual adaptation by proposing a multi-modal data fusion framework based on a spatio-temporal attention-enhanced LSTM neural network for personalized exercise volume optimization in college basketball courses. By integrating physiological signals (heart rate), kinematic parameters (triaxial acceleration, step count), and environmental data collected from smart wearable devices, we constructed a dynamic weighted fusion mechanism and a personalized correction engine, establishing an evaluation model incorporating BMI correction factors and fitness-level compensation. Experimental data from 100 collegiate basketball trainees (60 males, 40 females; BMI 17.5–28.7) wearing Polar H10 and Xsens MVN devices were analyzed through an 8-week longitudinal study design. The framework integrates physiological monitoring (HR, HRV), kinematic analysis (3D acceleration at 100 Hz), and environmental sensing (SHT35 sensor). Experimental results demonstrate the following: (1) the LSTM-attention model achieves 85.3% accuracy in exercise intensity classification, outperforming traditional methods by 13.2%, with its spatio-temporal attention mechanism effectively capturing high-dynamic movement features such as basketball sudden stops and directional changes; (2) multi-modal data fusion reduces assessment errors by 15.2%, confirming the complementary value of heart rate and acceleration data; (3) the personalized correction mechanism significantly improves evaluation precision for overweight students (error reduction of 13.6%) and beginners (recognition rate increase of 18.5%). System implementation enhances exercise goal completion rates by 10.3% and increases moderate-to-vigorous training duration by 14.7%, providing a closed-loop “assessment-correction-feedback” solution for intelligent sports education. The research contributes methodological innovations in personalized modeling for exercise science and multi-modal time-series data processing. Full article

Transcranial magnetic stimulation combined with electroencephalography (TMS-EEG) has emerged as a transformative tool for probing cortical dynamics with millisecond precision. This review examines the state-dependent nature of TMS-EEG, a critical yet underexplored dimension influencing measurement reliability and clinical applicability. By integrating TMS’s neuromodulatory capacity with EEG’s temporal resolution, this synergy enables real-time analysis of brain network dynamics under varying neural states. We delineate foundational mechanisms of TMS-evoked potentials (TEPs), discuss challenges posed by temporal and inter-individual variability, and evaluate advanced paradigms such as closed-loop and task-embedded TMS-EEG. The former leverages real-time EEG feedback to synchronize stimulation with oscillatory phases, while the latter aligns TMS pulses with task-specific cognitive phases to map transient network activations. Current limitations—including hardware constraints, signal artifacts, and inconsistent preprocessing pipelines—are critically analyzed. Future directions emphasize adaptive algorithms for neural state prediction, phase-specific stimulation protocols, and standardized methodologies to enhance reproducibility. By bridging mechanistic insights with personalized neuromodulation strategies, state-dependent TMS-EEG holds promise for advancing both basic neuroscience and precision medicine, particularly in psychiatric and neurological disorders characterized by dynamic neural dysregulation. Full article

To address the limitations of existing learning path recommendation methods—such as poor adaptability, weak personalization, and difficulties in processing long sequences of student behavior and interest data—this paper proposes a personalized learning path recommendation system for the second classroom based on large language model (LLM) technology, with a focus on integrating the pre-trained model GPT-4. The goal is to improve recommendation accuracy and personalization by leveraging GPT-4’s strong long-sequence modeling capability. The system fuses students’ multimodal data (e.g., physiological signals, facial expressions, activity levels, and emotional states), extracts deep features using GPT-4, and generates tailored learning paths based on individual feature vectors. It also incorporates incremental learning and self-attention mechanisms to enable real-time feedback and dynamic adjustments. A generative adversarial network (GAN) is introduced to enhance diversity and innovation in recommendations. The experimental results show that the system achieves a personalized recommendation accuracy of over 92%, with coverage and recall rates exceeding 91% and 93%, respectively. Feedback adjustment time remains within 1.5 s, outperforming mainstream models. This study provides a novel and effective technical framework for personalized learning in the second classroom, promoting both efficient resource utilization and student development. Full article

Neuro-Affective Intelligence (NAI) integrates neuroscience, psychology, and artificial intelligence to support neurodivergent children through personalized Child–Machine Interaction (CMI). This paper presents an adaptive neuro-affective system designed to enhance engagement in children with neurodevelopmental disorders through serious games. The proposed framework incorporates real-time biophysical signals—including EEG-based concentration, facial expressions, and in-game performance—to compute a personalized engagement score. We introduce a novel mechanism, Bayesian Immediate Feedback Learning (BIFL), which dynamically selects visual, auditory, or textual stimuli based on real-time neuro-affective feedback. A multimodal CNN-based classifier detects mental states, while a probabilistic ensemble merges affective state classifications derived from facial expressions. A multimodal weighted engagement function continuously updates stimulus–response expectations. The system adapts in real time by selecting the most appropriate cue to support the child’s cognitive and emotional state. Experimental validation with 40 children (ages 6–10) diagnosed with Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) demonstrates the system’s effectiveness in sustaining attention, improving emotional regulation, and increasing overall game engagement. The proposed framework—combining neuro-affective state recognition, multimodal engagement scoring, and BIFL—significantly improved cognitive and emotional outcomes: concentration increased by 22.4%, emotional engagement by 24.8%, and game performance by 32.1%. Statistical analysis confirmed the significance of these improvements ($p<0.001$, Cohen’s $d>1.4$). These findings demonstrate the feasibility and impact of probabilistic, multimodal, and neuro-adaptive AI systems in therapeutic and educational applications. Full article

This study explores how Speech and Elocution Training (SET) activates language potential and fosters career-oriented development among higher vocational students through self-efficacy mechanisms. Through qualitative interviews with four vocational graduates who participated in SET 5 to 10 years ago, the research identifies three key findings. First, SET comprises curriculum content (e.g., workplace communication modules such as hosting, storytelling, and sales pitching) and classroom training using multimodal TED resources and Toastmasters International-simulated practices, which spark language potential through skill-focused, realistic exercises. Second, these pedagogies facilitate a progression where initial language potential evolves from nascent career interests into concrete job-seeking intentions and long-term career plans: completing workplace-related speech tasks boosts confidence in career choices, planning, and job competencies, enabling adaptability to professional challenges. Third, SET aligns with Bandura’s four self-efficacy determinants; these are successful experiences (including personalized and virtual skill acquisition and certified affirmation), vicarious experiences (via observation platforms and constructive peer modeling), verbal persuasion (direct instructional feedback and indirect emotional support), and the arousal of optimistic emotions (the cognitive reframing of challenges and direct desensitization to anxieties). These mechanisms collectively create a positive cycle that enhances self-efficacy, amplifies language potential, and clarifies career intentions. While highlighting SET’s efficacy, this study notes a small sample size limitation, urging future mixed-methods studies with diverse samples to validate these mechanisms across broader vocational contexts and refine understanding of language training’s role in fostering linguistic competence and career readiness. Full article

Hands are central to nearly every aspect of daily life, so losing an upper limb due to amputation can severely affect a person’s independence. Robotic prostheses offer a promising solution by mimicking many of the functions of a natural arm, leading to an increasing need for advanced prosthetic designs. However, developing an effective robotic hand prosthesis is far from straightforward. It involves several critical steps, including creating accurate models, choosing materials that balance biocompatibility with durability, integrating electronic and sensory components, and perfecting control systems before final production. A key factor in ensuring smooth, natural movements lies in the method of control. One popular approach is to use electromyography (EMG), which relies on electrical signals from the user’s remaining muscle activity to direct the prosthesis. By decoding these signals, we can predict the intended hand and arm motions and translate them into real-time actions. Recent strides in machine learning have made EMG-based control more adaptable, offering users a more intuitive experience. Alongside this, researchers are exploring tactile sensors for enhanced feedback, materials resilient in harsh conditions, and mechanical designs that better replicate the intricacies of a biological limb. This review brings together these advancements, focusing on emerging trends and future directions in robotic upper-limb prosthesis development. Full article

The progressive advancements in education due to the advent of transformative technologies has led to the emergence of customized/personalized learning systems that dynamically adapts to an individual learner’s preferences in real-time mode. The learning route and style of every learner is unique and their understanding varies with the complexity of core components. This paper presents a hybrid approach that integrates generative adversarial networks (GANs), feedback-driven personalization, explainable artificial intelligence (XAI) to enhance knowledge component (KC) prediction and to improve learner outcomes as well as to attain progress in learning. By using these technologies, this proposed system addresses the challenges, namely, adapting educational content to an individual’s requirements, creating high-quality content based on a learner’s profile, and implementing transparency in decision-making. The proposed framework starts with a powerful feedback mechanism to capture both explicit and implicit signals from learners, including performance parameters viz., time spent on tasks, and satisfaction ratings. By analysing these signals, the system vigorously adapts to each learner’s needs and preferences, ensuring personalized and efficient learning. This hybrid model dynamic knowledge component prediction system (DKPS) exhibits a 35% refinement in content relevance and learner engagement, compared to the conventional methods. Using generative adversarial networks (GANs) for content creation, the time required to produce high-quality learning materials is reduced by 40%. The proposed technique has further scope for enhancement by incorporating multimedia content, such as videos and concept-based infographics, to give learners a more extensive understanding of concepts. Full article

This paper presents the development and initial evaluation of a novel protocol for robot-assisted lower limb rehabilitation. It integrates dual-modal patient interaction, employing mirror therapy and an auto-adaptive EMG-driven control system, designed to enhance lower limb rehabilitation in patients with hemiparesis impairments. The system features a robotic platform specifically engineered for lower limb rehabilitation, which operates in conjunction with a virtual reality (VR) environment. This immersive environment comprises a digital twin of the robotic system alongside a human avatar representing the patient and a set of virtual targets to be reached by the patient. To implement mirror therapy, the proposed protocol utilizes a set of inertial sensors placed on the patient’s healthy limb to capture real-time motion data. The auto-adaptive protocol takes as input the EMG signals (if any) from sensors placed on the impaired limb and performs the required motions to reach the virtual targets in the VR application. By synchronizing the motions of the healthy limb with the digital twin in the VR space, the system aims to promote neuroplasticity, reduce pain perception, and encourage engagement in rehabilitation exercises. Initial laboratory trials demonstrate promising outcomes in terms of improved motor function and subject motivation. This research not only underscores the efficacy of integrating robotics and virtual reality in rehabilitation but also opens avenues for advanced personalized therapies in clinical settings. Future work will investigate the efficiency of the proposed solution using patients, thus demonstrating clinical usability, and explore the potential integration of additional feedback mechanisms to further enhance the therapeutic efficacy of the system. Full article

The deployment of emotion-recognition technologies expands across healthcare education and gaming sectors to improve human–computer interaction. These systems examine facial expressions together with vocal tone and physiological signals, which include pupil size and electroencephalogram (EEG), to detect emotional states and deliver customized responses. The technology provides benefits through accessibility, responsiveness, and adaptability but generates multiple complex ethical issues. The combination of emotional profiling with biased algorithmic interpretations of culturally diverse expressions and affective data collection without meaningful consent presents major ethical concerns. The increased presence of these systems in classrooms, therapy sessions, and personal devices makes the potential for misuse or misinterpretation more critical. The paper integrates findings from literature review and initial emotion-recognition studies to create a conceptual framework that prioritizes data dignity, algorithmic accountability, and user agency and presents a conceptual framework that addresses these risks and includes safeguards for participants’ emotional well-being. The framework introduces structural safeguards which include data minimization, adaptive consent mechanisms, and transparent model logic as a more complete solution than privacy or fairness approaches. The authors present functional recommendations that guide developers to create ethically robust systems that match user principles and regulatory requirements. The development of real-time feedback loops for user awareness should be combined with clear disclosures about data use and participatory design practices. The successful oversight of these systems requires interdisciplinary work between researchers, policymakers, designers, and ethicists. The paper provides practical ethical recommendations for developing affective computing systems that advance the field while maintaining responsible deployment and governance in academic research and industry settings. The findings hold particular importance for high-stakes applications including healthcare, education, and workplace monitoring systems that use emotion-recognition technology. Full article

Stroke remains a significant global health challenge, particularly in low- and middle-income Countries (LMICs), where two-thirds of stroke-related deaths occur, and disability-adjusted life years are seven times higher compared to high-income Countries (HICs). The majority of stroke survivors suffer from upper limb impairment, severely limiting their daily activities and significantly diminishing their overall quality of life. Rehabilitation plays a critical role in restoring function and independence, but it faces challenges such as low engagement, limited customization, difficulty tracking progress, and accessibility barriers, particularly in LMICs. Immersive virtual reality (imVR) has shown promise in addressing these challenges, but most commercial imVR systems lack therapeutic design and cultural adaptation. This study aimed to develop culturally adaptable imVR games for upper limb stroke rehabilitation (ULSR) in the context of LMICs, with a particular focus on Ethiopia. The AdaptRehab VR system was developed including six imVR games (Basket Bloom, Strike Zone, TapQuest, FruitFall Frenzy, Precision Pitch, and Bean Picker Pro) through co-creation approaches involving Ethiopian and Belgian physiotherapists, stakeholders, and patients, incorporating game development mechanics in rehabilitation, such as therapeutic aims, cultural factors, feedback, automatic progression recording, task variety, and personalized rehabilitation. It was designed with the Unity 3D engine and Oculus Quest headsets, supporting controllers and hand tracking. This culturally tailored imVR platform has demonstrated significant potential to enhance ULSR accessibility, patient motivation, and outcomes in resource-constrained settings, addressing critical gaps in stroke rehabilitation solutions. In conclusion, the AdaptRehab VR system was successfully developed as a culturally contextualized imVR platform tailored to tackle ULSR challenges in LMICs, with a specific focus on Ethiopia. Full article

Feedback is an essential component of the teaching–learning process; however, it can vary in quality due to different contexts and students’ and professors’ individual characteristics. This research explores the effect of generative artificial intelligence (GenAI) in strengthening personalized and timely feedback by initially defining an adaptable framework to integrate GenAI into feedback mechanisms defined in theoretical frameworks. We applied a between-subjects analysis in an experimental research design with 263 undergraduate students across multiple disciplines based on an approach consisting of a pretest–post-test process and control and focus groups to evaluate students’ perceptions of artificial intelligence-enhanced feedback versus traditional professor-led feedback. The results show that students who used GenAI declared statistically significantly higher satisfaction levels and a greater sense of ownership in the feedback process. Additionally, GenAI scaffolded continuous improvement and active student participation through a structured and accessible feedback environment, determining that 97% of students are willing to reuse the tool. These findings show that GenAI is a valuable tool to complement professors in the creation of an integrated feedback model. This study draws directions on future research on the combination of artificial intelligence and innovative strategies to produce a long-term impact on education. Full article