Search Results (895)

This paper introduces a biomimetic framework and novel brain-inspired AI (BIAI) models based on spiking neural networks (SNNs) for emotional state recognition from audio (speech), visual (face), and integrated multimodal audio–visual data. The developed framework, named eXCube2, uses a three-dimensional SNN architecture NeuCube that is spatially structured according to a human brain template. The BIAI models developed in eXCube2 are trainable on spatio- and spectro-temporal data using brain-inspired learning rules. Such models are explainable in terms of revealing patterns in data and are adaptable to new data. The eXCube2 models are implemented as software systems and tested on speech and video data of subjects expressing emotional states. The use of a brain template for the SNN structure enables brain-inspired tonotopic and stereo mapping of audio inputs, topographic mapping of visual data, and the combined use of both modalities. This novel approach brings AI-based emotional state recognition closer to human perception, provides a better explainability and adaptability than existing AI systems. It also results in a higher or competitive accuracy, even though this was not the main goal here. This is demonstrated through experiments on benchmark datasets, achieving classification accuracy above 80% on single-modality data and 88.9% when multimodal audio–visual data are used, and a “don’t know” output is introduced. The paper further discusses possible applications of the proposed eXCube2 framework to other audio, visual, and audio–visual data for solving challenging problems, such as recognizing emotional states of people from different origins; brain state diagnosis (e.g., Parkinson’s disease, Alzheimer’s disease, ADHD, dementia); measuring response to treatment over time; evaluating satisfaction responses from online clients; cognitive robotics; human–robot interaction; chatbots; and interactive computer games. The SNN-based implementation of BIAI also enables the use of neuromorphic chips and platforms, leading to reduced power consumption, smaller device size, higher performance accuracy, and improved adaptability and explainability. This research shows a step toward building brain-inspired AI systems. Full article

Cyber-trauma has emerged as an important concern within online gaming environments, with growing implications for children’s mental health and well-being. Multiplayer games increasingly function as routine spaces for interaction, competition, and informal learning, which may expose young players to hostile behaviours such as harassment, hate speech, exclusion, and repeated targeting. Understanding the psychological consequences of these experiences and the protective role of family support is therefore essential. This study investigates the relationship between cyber-trauma victimisation (CV) and four mental health outcomes—depressive symptoms (DS), anxiety symptoms (AS), perceived stress (PS), and emotional distress (ED)—among Generation Alpha student gamers, while examining parental support as a moderating factor. Survey data were collected from 1223 students of diverse Arab nationalities enrolled in schools in Saudi Arabia, with Saudi nationals representing approximately 15% of the sample. The results indicate that CV is a strong and consistent predictor of all examined mental health outcomes. Higher levels of CV are significantly associated with increased depressive symptoms (β = 0.58), anxiety symptoms (β = 0.55), perceived stress (β = 0.52), and emotional distress (β = 0.60) (all p < 0.001). Parental support significantly moderates these relationships, weakening the association between cyber-trauma exposure and adverse psychological outcomes. These findings contribute to the growing literature on children’s digital well-being by demonstrating that online gaming environments can serve as meaningful psychosocial stressors for young players. The results further highlight the importance of family-centred protective mechanisms, suggesting that parental emotional support, guidance, and communication can play a critical role in buffering the mental health risks associated with hostile online interactions. Full article

Byzantine failures remain a critical threat to Federated Learning (FL), where malicious clients inject adversarial updates to disrupt global model convergence. From the perspective of symmetry, benign client updates typically exhibit statistical symmetry around the global consensus, whereas Byzantine attacks function as “symmetry-breaking” events that introduce skewness and distributional anomalies. Existing defenses often rely on unrealistic assumptions or fail to capture these asymmetric deviations under high-dimensional non-IID settings. In this paper, we propose a symmetry-aware Byzantine-resilient FL framework driven by a Dual-Channel Attention-Driven Anomaly Detector (DAAD). Specifically, DAAD transforms inter-client behaviors into geometrically symmetric interaction matrices—encoding Gradient Cosine Similarities and Loss Euclidean Distances—to construct dual-channel spatial representations. These representations are processed via a Convolutional Neural Network (CNN) enhanced with Squeeze-and-Excitation (SE) attention blocks, which leverage the inherent symmetry of benign consensus to extract robust adversarial signatures. The detector is pre-trained offline on a synthetic dataset incorporating a diverse portfolio of simulated attacks (e.g., Gaussian noise and label flipping). Crucially, this pre-trained model is seamlessly embedded into the online FL loop to filter updates without requiring ground-truth labels. By jointly encoding client behaviors and learning cross-modal attack signatures, our framework enables reliable detection even when over half of the clients are Byzantine. Extensive experiments on MNIST, CIFAR-10, and FEMNIST datasets demonstrate that DAAD consistently outperforms existing robust aggregation baselines in both anomaly detection accuracy and global model performance, especially under high Byzantine ratios and non-IID conditions. Full article

Background: Professional identity and ethical integrity are foundational to nursing practice and are shaped in part by educational experiences. This study evaluated an online Holocaust and genocide educational seminar delivered to fourth-year Bachelor of Science in Nursing (BSN) students and explored how students linked seminar content to professional identity formation, ethical vigilance, and patient advocacy. Methods: We conducted a descriptive mixed-methods educational evaluation. Students completed an anonymous pre-seminar survey (demographics, motivations for studying nursing, self-identified desirable professional qualities, and self-rated knowledge of the Holocaust and other genocides) and an anonymous post-seminar feedback survey with four open-ended questions. Quantitative items were summarized descriptively; qualitative data were analyzed using inductive qualitative content analysis. Results: Of the 205 students who attended the seminar, 133 completed the pre-seminar survey, and 110 completed the post-seminar survey. Students reported high baseline knowledge of the Holocaust but limited knowledge of the Armenian and Rwandan genocides. The five themes that emerged are as follows: (1) ethical judgment and the influence of nurses; (2) patient advocacy and social justice; (3) the effect of historical and contemporary trauma on students’ learning experience; (4) genocide awareness and prevention; and (5) approaches to education and content presentation. Conclusions: Carefully facilitated Holocaust and genocide education, delivered through interactive online pedagogy and structured debriefing, may support late-stage nursing students’ reflection on ethical integrity and professional identity during the transition to professional practice. Full article

The rapid development of a new-type power system dominated by renewable energy has introduced growing complexity and variability into grid topology and dynamics, posing significant challenges for transmission interface power flow control. Traditional regulation methods based on operator experience and deterministic optimization often fail to achieve real-time optimality under such dynamic conditions. Leveraging its strong capability for autonomous learning and feature perception, deep reinforcement learning (DRL) offers a promising approach for addressing these challenges. This paper proposes a safe DRL-based control framework for online transmission interface power flow regulation. A Safe Soft Actor–Critic (SSAC) agent is developed, embedding power system security constraints directly into the decision process to ensure operational safety. A secure EMS-interactive training platform with containerized parallel learning is established to accelerate model convergence and improve adaptability to changing operating conditions. The developed SSAC agent is deployed in the Jiangsu Power Grid Energy Management System (EMS) for validation. Simulation and field test results demonstrate that the proposed method can generate control strategies online within milliseconds, achieving a 99.3% interface overload mitigation rate and 3.32% network loss reduction, outperforming conventional sensitivity-based optimization methods in both timeliness and economic efficiency. These results demonstrate strong real-time computational capability and compatibility with EMS-based dispatch workflows, indicating promising practical deployment potential for transmission interface control in renewable-dominated power systems. Full article

Human–robot collaboration (HRC) can be defined as the close interaction between a human user and a robot working together to accomplish a specific task. True collaboration, however, can only be realized when humans and robots can share the same workspace simultaneously and move freely within it. To address these problems, Learning from Demonstrations (LfD) helps robots become competent in solving plenty of complicated tasks, greatly reducing programming times and allowing task generalization. However, complex robot tasks require complex path planning modeling for a robot to move from one place to another in a heavily constrained workspace following a collision-free path. To this end, a robot programming framework based on Dynamic Movement Primitives (DMPs) is proposed. The framework derives and implements a solution for robot path planning and includes a new DMP formulation with volumetric obstacle avoidance for robot LfD. The formulation equips robotic systems with the capability of online adaptation in the presence of dynamic obstacles. Quantitative evaluations demonstrate high success rates (>96% in tested scenarios) in collision avoidance and typical trajectory adaptation times in the order of milliseconds (<5 ms), supporting its applicability. These methods have been applied in both simulation and real robotic scenarios using a UR10e collaborative robot from Universal Robots for testing and validation purposes. The results indicate that the proposed approach can effectively make the robot follow a user-defined trajectory and learn how to adapt it to avoid collisions with volumetric obstacles of different shapes and poses in an unconstrained human–robot collaborative environment. Full article

Efficient workflow scheduling in cloud–edge environments is severely bottlenecked by long-horizon dependencies and myopic resource fragmentation. This paper proposes the Decoupled Offline Sequence-based (DOS) scheduling framework to address these challenges. By decoupling expert policy learning from runtime deployment, DOS utilizes a multi-dimensional priority-aware linearization strategy to deterministically transform DAG-structured workflows into dependency-consistent sequences. Leveraging offline expert trajectories, we train UDC, a Gated CNN achieving unified sequence modeling via innovative triplet-to-unary encoding, equipped with explicit action masking to distill long-horizon spatio-temporal packing patterns. This mechanism enables rapid feed-forward inference without costly online environment interactions or policy updates. Extensive evaluations on real-world Alibaba cluster workloads demonstrate that DOS not only consistently minimizes average makespan compared to classical heuristics, but also drastically reduces resource-blocked steps under extreme concurrency versus online Actor–Critic experts. Crucially, compared to the Decision Transformer (DT) baseline, the UDC model achieves strictly scale-invariant and significantly lower inference latency, highlighting its robust scalability and practicality for large-scale continuum systems. Full article

The high-speed Electromagnetic Suspension (EMS) maglev guidance system exhibits inherent characteristics of strong nonlinearity, parameter time-variation, and complex external disturbances. To further optimize and improve the control performance of the guidance system for high-speed maglev trains, a novel intelligent control strategy that integrates the Deep Deterministic Policy Gradient (DDPG) algorithm with Super-Twisting Sliding Mode Control (STSMC) is proposed. Focusing on a single-ended guidance unit with differential control of dual electromagnets, an STSMC controller is first designed based on a cascaded control framework. To overcome the limitation of offline parameter tuning in dynamic operational conditions, a reinforcement learning optimization framework employing DDPG is introduced. A multi-objective hybrid reward function is formulated, incorporating error convergence, sliding mode stability, and chattering suppression, thereby realizing the online self-tuning of core STSMC parameters via real-time interaction between the agent and the environment. Numerical simulations under typical disturbance conditions verify that the proposed DDPG-STSMC controller significantly reduces the amplitude of guidance gap variation and accelerates dynamic recovery compared to conventional PID control. Its superior performance in disturbance rejection, control accuracy, and operational adaptability is validated. This study, conducted through high-fidelity numerical simulations based on actual system parameters, provides a robust theoretical foundation for subsequent hardware-in-the-loop (HIL) experimentation. Full article

Rumour propagation in online social networks poses significant risks to public trust, economic stability, and crisis management. Existing models often struggle with heterogeneous feature spaces, adversarial dynamics between rumours and debunking information, and data sparsity in early outbreak stages. This study introduces a cross-domain framework for group behaviour prediction that integrates unified representation learning, game-theoretic adversarial modelling, and transfer adaptation. A hybrid BERT–Node2Vec encoder captures both semantic richness and structural influence, while evolutionary game theory quantifies competitive interactions between rumour-spreaders and refuters. To alleviate data scarcity, Joint Distribution Adaptation (JDA) aligns heterogeneous feature spaces across domains, enabling robust transfer learning. Evaluated on simulated and real-world social media datasets, the proposed model demonstrates improved accuracy and interpretability in predicting rumour diffusion trends under adversarial conditions. These findings highlight the value of integrating semantic, structural, and behavioural signals into a scalable architecture, offering a practical solution for safeguarding digital ecosystems against misinformation. Full article

Background: Digitalisation and gamification are increasingly integrated into higher education, often accompanied by claims of enhanced engagement but also concerns regarding the erosion of student–teacher interaction. While prior research has focused on the effectiveness of tools or learning outcomes, less attention has been paid to how digitally mediated teaching reconfigures the interactional relations between participants. This study examined a hybrid, gamified learning setting in the MICE (Meetings, Incentives, Conferences, and Exhibitions) domain, with a particular focus on the interactional dynamics between teachers and students. Methods: The study employed a CyberSystemic interaction-observation framework to examine a four-week pilot course that combines synchronous online teaching, digital self-learning materials, and group project work. Observations were conducted by participating teachers during planning, execution, and immediate follow-up. Student perspectives were captured through a post-course survey using a 5-point Likert scale, complemented by qualitative follow-up interviews focused on prospective adaptations in future interaction cycles. Results: Interaction observations revealed high levels of student activation during time-bounded, task-oriented phases, particularly in group work and gamified activities, alongside periods of passivity during lecture-heavy phases. Survey results indicate generally positive evaluations of interactive and reflective course elements, though substantial variance exists across participants. Interaction density between teachers and students increased during execution and declined sharply afterwards, suggesting situational rather than sustained relational coupling. Conclusions: The findings indicate that gamified and digitally supported learning environments can enhance short-term engagement and operational coordination, but do not automatically stabilise student–teacher relations or learning processes over time. Within the observed timeframe, gamification appeared most effective when embedded within structured interaction and human facilitation rather than treated as a substitute for them. The study emphasises the significance of temporality and interaction design in assessing collective intelligence while highlighting how immediate feedback can inform future operational and managerial adaptation in hybrid educational systems. Full article

Digital harassment is an increasing challenge in higher education, with implications for students’ psychological well-being, perceived safety, and engagement in digital learning. As artificial intelligence (AI) increasingly mediates communication, visibility, and interaction across educational platforms, students’ exposure to online harm is shaped not only by individual behaviour but also by algorithmically structured interaction environments. Understanding these conditions is essential for protecting student well-being and supporting sustainable participation in AI-enhanced learning. This study examines university students’ exposure to digital harassment in AI-mediated learning environments using an expanded Unified Theory of Acceptance and Use of Technology (UTAUT) framework. Survey data were collected from 2185 students, including Saudi nationals and international students enrolled in Saudi Arabian universities, representing Saudi Arabia and 32 other developing and emerging countries (33 countries in total). The model analyses associations among technological literacy, cybersecurity awareness, social media engagement intensity, digital identity visibility, AI-mediated interactions, and cultural norms, while also accounting for disciplinary and cultural context differences. The results indicate that AI-mediated interactions are most strongly associated with exposure to digital harassment. Higher social media engagement, more restrictive cultural norms, and greater visibility of digital identity are associated with increased exposure, whereas technological literacy and cybersecurity awareness are associated with lower reported exposure. Furthermore, greater exposure to digital harassment is linked to poorer mental health outcomes and reduced continuity in e-learning participation. Overall, the findings suggest that digital harassment in AI-driven educational settings is a structural sociotechnical issue associated with greater embeddedness in algorithmically mediated learning environments, rather than an isolated behavioural issue. The study highlights the need for responsible AI governance, enhanced digital literacy education, and culturally responsive institutional policies to support inclusive and sustainable higher education. Full article

The rapid spread of generative artificial intelligence (AI) in higher education creates both opportunities for innovation and challenges for academic integrity, ethical use, and students’ critical thinking, particularly in scientific writing. This study examines whether a synchronous live coaching format can support students in developing reflective and responsible AI practices. A mixed-methods cross-sectional evaluation was conducted at a German distance-learning university with a strong focus on health and social sciences. An online survey was administered to 168 students who participated in voluntary live coaching sessions on “AI in Scientific Writing”. Quantitative items assessed perceived competence gains, ethical awareness, and confidence in handling AI tools, while open-ended questions captured qualitative feedback on the format’s strengths and improvement needs. Students reported that the coaching enhanced their understanding of responsible AI use and scientific integrity and valued the opportunity for open discussion, peer interaction, and the supportive attitude of instructors. Reflective and dialogic elements were perceived as particularly beneficial. Overall, the findings suggest that synchronous live coaching can contribute to fostering ethical awareness and higher-order thinking in AI-supported academic work, especially when it integrates structured input with dialogue, reflection, and peer learning. Full article

Small Private Online Courses (SPOCs) have gained attention as a promising approach to blended learning in higher education, particularly within the Flipped Classroom framework. Unlike Massive Open Online Courses (MOOCs), SPOCs cater to a limited number of students, allowing for more personalized learning experiences and enhanced interaction with instructors. This case study examines the integration of a SPOC titled “Introduction to Quantum Physics” into the undergraduate course “Introduction to Modern Physics” at the University of Crete. The research employs a mixed-methods approach, combining quantitative and qualitative data collection methods. Quantitative data were obtained from a questionnaire distributed to students and an analysis of student grades, while qualitative insights were derived from interviews with the course instructors. The findings indicate that the SPOC was associated with positive student engagement and comprehension of complex physics concepts, aligning with previous research on blended learning effectiveness. However, challenges were identified, including the need for increased student–instructor interaction in the online component. Recommendations for improving the SPOC model include the development of interactive activities and enhanced instructor support. This study aims to contribute to the growing body of research on the Flipped Classroom framework in higher education, highlighting the potential utility of SPOCs to enrich learning experiences. Full article

Task-oriented dialogue systems face a tension between comprehensive constraint elicitation (task adequacy) and conversational efficiency (minimizing turns). Current preference learning frameworks treat preferences as static, unable to capture the dynamic evolution of interaction states that evolve across dialogue progression. We present Dual-DPO, a framework that embeds multi-objective preferences into data construction via turn-aware scoring. Our approach decouples objective balancing from policy updates through offline preference scalarization, addressing the optimization instability challenges in online multi-objective reinforcement learning. Experiments on MultiWOZ 2.4 demonstrate 28–35% dialogue turn reduction while maintaining Joint Goal Accuracy > 89% ($p<0.001$). Pareto frontier analysis shows 94% coverage with hypervolume $HV=0.847$. Independent expert evaluation by 10 PhD-level researchers ($n=300$ assessments, inter-rater agreement $\alpha =0.78$) confirms 32% user satisfaction improvement ($p<0.001$). Theoretical analysis demonstrates that offline scalarization, which correlates with improved optimization stability, achieves $3.2\times$ lower gradient variance than online multi-reward optimization by eliminating sampling stochasticity. Our approach enables balanced treatment of competing objectives through Pareto-optimal trade-offs. These results highlight a symmetric and balanced treatment of competing objectives within a Pareto-optimal optimization framework. Full article

An online off-policy asynchronous real-time model reference tracking control (OOART-MRTC) algorithm is proposed and validated for unmanned aerial vehicles (UAVs) characterized by faulty actuation and parametric uncertainty. The optimal control problem is posed based on approximate dynamic programming (ADP) and reinforcement learning (RL) theory, using a virtual state-space representation constructed exclusively on input–output true system data, which exploits the observability theory. OOART-MRTC learns control by interacting with the system, starting from an initial stabilizing controller derived from an approximate uncertain model. Learning convergence and stability under the proposed adaptive behavior are analyzed. Since the learning iterations cannot update within a sampling period, an asynchronous mechanism is proposed for updating the controller parameters, leveraging real-time control and multi-tasking. The complexity associated with the resulting high-dimensional system is solved by efficient linear parameterization and validated on a realistic case study where three coupled double integrators describe the UAV attitude control. Full article