Search Results (985)

Virtual reality (VR) has emerged as a complex technological domain that demands high levels of realism and interactivity. At the core of this immersive experience lies a broad spectrum of mathematical modeling techniques. This survey explores how mathematical foundations support and enhance key VR components, including physical simulations, 3D spatial analysis, rendering pipelines, and user interactions. We review differential equations and numerical integration methods (e.g., Euler, Verlet, Runge–Kutta (RK4)) used to simulate dynamic environments, as well as geometric transformations and coordinate systems that enable seamless motion and viewpoint control. The paper also examines the mathematical underpinnings of real-time rendering processes and interaction models involving collision detection and feedback prediction. In addition, recent developments such as physics-informed neural networks, differentiable rendering, and neural scene representations are presented as emerging trends bridging classical mathematics and data-driven approaches. By organizing these elements into a coherent mathematical framework, this work aims to provide researchers and developers with a comprehensive reference for applying mathematical techniques in VR systems. The paper concludes by outlining the open challenges in balancing accuracy and performance and proposes future directions for integrating advanced mathematics into next-generation VR experiences. Full article

Whether learners can correctly complete exercises is influenced by multiple factors, including their mastery of relevant knowledge concepts and the interdependencies among these concepts. To investigate how the structure of the knowledge space—particularly the complex relationships among learners, exercises, and knowledge points—affects learning outcomes, this study proposes the Hierarchical Heterogeneous Graph Knowledge Tracing model (HHGKT). A hierarchical heterogeneous graph was constructed to capture two types of interactions—“learner–knowledge concept” and “exercise–knowledge concept”—and incorporate the interdependencies among knowledge concepts into the graph structure. By leveraging this hierarchical representation, the model’s ability to characterize learners and exercises was enhanced. A hierarchical heterogeneous graph encompassing users, exercises, and knowledge concepts was built based on the ASSISTments dataset, and simulation experiments were conducted. The results indicate that the proposed structure effectively represents the complexity of the knowledge space. Incorporating knowledge concept interdependencies improves prediction accuracy by 1.79%, while the hierarchical heterogeneous graph outperforms traditional bipartite graphs by approximately 1.5 percentage points in accuracy. These findings demonstrate that the model better integrates node and relational information, offering valuable insights for knowledge space modeling and its application in educational contexts. Full article

Depression represents a major global health challenge, yet traditional clinical diagnosis faces limitations, including high costs, limited coverage, and low patient willingness. Social media platforms provide new opportunities for early depression screening through user-generated content. However, existing methods often lack systematic integration of clinical knowledge and fail to leverage multi-modal information comprehensively. We propose a DSM-5-guided methodology that systematically maps clinical diagnostic criteria to computable social media features across three modalities: textual semantics (BERT-based deep semantic extraction), behavioral patterns (temporal activity analysis), and topic distributions (LDA-based cognitive bias identification). We design a hierarchical architecture integrating BERT, Bi-LSTM, hierarchical attention, and multi-task learning to capture both character-level and post-level importance while jointly optimizing depression classification, symptom recognition, and severity assessment. Experiments on the WU3D dataset (32,570 users, 2.19 million posts) demonstrate that our model achieves 91.8% F1-score, significantly outperforming baseline methods (BERT: 85.6%, TextCNN: 78.6%, and SVM: 72.1%) and large language models (GPT-4 few-shot: 86.9%). Ablation studies confirm that each component contributes meaningfully with synergistic effects. The model provides interpretable predictions through attention visualization and outputs fine-grained symptom assessments aligned with DSM-5 criteria. With low computational cost (~50 ms inference time), local deployability, and superior privacy protection, our approach offers significant practical value for large-scale mental health screening applications. This work demonstrates that domain-specialized methods with explicit clinical knowledge integration remain highly competitive in the era of general-purpose large language models. Full article

As artificial intelligence (AI) is increasingly used in classrooms, tutoring systems, and learning platforms, it is essential that these tools are not only powerful, but also easy to understand, fair, and supportive of real learning. Many current AI systems can generate fluent responses or accurate predictions, yet they often fail to clearly explain their decisions, reflect students’ cultural contexts, or give learners and educators meaningful control. This gap can reduce trust and limit the educational value of AI-supported learning. This paper introduces the PEARL framework, a human-centered approach for designing and evaluating explainable AI in education. PEARL is built around five core principles: Pedagogical Personalization (adapting support to learners’ levels and curriculum goals), Explainability and Engagement (providing clear, motivating explanations in everyday language), Attribution and Accountability (making AI decisions traceable and justifiable), Representation and Reflection (supporting fairness, diversity, and learner self-reflection), and Localized Learner Agency (giving learners control over how AI explains and supports them). Unlike many existing explainability approaches that focus mainly on technical performance, PEARL emphasizes how students, teachers, and administrators experience and make sense of AI decisions. The framework is demonstrated through simulated examples using an AI-based tutoring system, showing how PEARL can improve feedback clarity, support different stakeholder needs, reduce bias, and promote culturally relevant learning. The paper also introduces the PEARL Composite Score, a practical evaluation tool that helps assess how well educational AI systems align with ethical, pedagogical, and human-centered principles. This study includes a small exploratory mixed-methods user study (N = 17) evaluating example AI tutor interactions; no live classroom deployment was conducted. Together, these contributions offer a practical roadmap for building educational AI systems that are not only effective, but also trustworthy, inclusive, and genuinely supportive of human learning. Full article

Cloud storage continues to experience recurring provider-side breaches, raising concerns about the confidentiality and recoverability of user data. This study addresses this challenge by introducing an Artificial Intelligence (AI)-driven hybrid architecture for secure, reconstruction-resistant multi-cloud storage. The system applies telemetry-guided fragmentation, where fragment sizes are dynamically predicted from real-time bandwidth, latency, memory availability and disk I/O, eliminating the predictability of fixed-size fragmentation. All payloads are compressed, encrypted with AES-128 and dispersed across independent cloud providers, while two encrypted fragments are retained within a VeraCrypt-protected local vault to enforce a distributed trust threshold that prevents cloud-only reconstruction. Synthetic telemetry was first used to evaluate model feasibility and scalability, followed by hybrid telemetry integrating real Microsoft system traces and Cisco network metrics to validate generalization under realistic variability. Across all evaluations, XGBoost and Random Forest achieved the highest predictive accuracy, while Neural Network and Linear Regression models provided moderate performance. Security validation confirmed that partial-access and cloud-only attack scenarios cannot yield reconstruction without the local vault fragments and the encryption key. These findings demonstrate that telemetry-driven adaptive fragmentation enhances predictive reliability and establishes a resilient, zero-trust framework for secure multi-cloud storage. Full article

Empathic behavior is increasingly incorporated into socially assistive robots, yet little is known about how older adults’ personality-based self-regulatory processes shape responses to such designs. The present study examined a recognition-based “mirror effect” framework of narcissistic self-regulation, referring to the ways individuals maintain a valued self-image through social feedback and acknowledgment. We focused on two core dimensions: narcissistic admiration, characterized by self-promotion and the pursuit of affirmation, and narcissistic rivalry, characterized by defensiveness, antagonism, and sensitivity to threat. Community-dwelling older adults (N = 527; M_age = 72.73) were randomly assigned to view a video of a socially assistive robot interacting in either an empathic or a cold manner. Participants reported their perceived recognition by the robot, defined as the subjective experience of feeling seen, acknowledged, and valued, as well as multiple robot evaluations (anthropomorphism, likability, perceived intelligence, safety, and intention to use). At the mean level, empathic robot behavior increased perceived recognition, anthropomorphism, and likability but did not improve perceived intelligence, safety, or intention to use. Conditional process analyses revealed that narcissistic admiration was positively associated with perceived recognition, which in turn predicted more favorable robot evaluations, regardless of robot behavior. In contrast, narcissistic rivalry showed a behavior-dependent pattern: rivalry was associated with reduced perceived recognition and less favorable evaluations primarily in the empathic condition, whereas this association reversed in the cold condition. Importantly, once perceived recognition and narcissistic traits were accounted for, the cold robot was evaluated as more intelligent, safer, and more desirable to use than the empathic robot. Studying these processes in older adults is theoretically and practically significant, as later life is marked by shifts in social roles, autonomy concerns, and sensitivity to interpersonal evaluation, which may alter how empathic technologies are experienced. Together, the findings identify perceived recognition as a central psychological mechanism linking personality and robot design and suggest that greater robotic empathy is not universally beneficial, particularly for users high in rivalry-related threat sensitivity. Full article

During the process of digital-system development from prototype to live implementation, differences in user interactions, perceived usability, and overall satisfaction can emerge. These differences often arise due to various factors, which may include the fidelity of the software prototype, the limitations of the prototyping tool, and the complexity of the live digital system. Recognizing these potential usability discrepancies between prototypes and live digital systems, assessment of how well user experience (UX) test approaches, such as usability testing and the System Usability Scale (SUS), reflect the UX in using the digital-system prototype and its counterpart deployed live system emerged as an important research gap. To address this gap, this study compares usability testing and SUS results among a Figma web prototype and its counterpart live web digital system, for the telecom service extension process as a representative digital-system case study. The research study involved a testing process with a total of 10 participants across the Figma prototype and live-web-system test environments, in which different sensing devices that included versatile types of mobile phones were utilized. The research study presents usability testing results related to the overlap in perceived usability issues for the same digital-product developments in both testing environments, which are experienced on different types of mobile sensing devices. The usability testing results are presented as reports on the frequency of occurrence of web system usability issues and corresponding severity levels. The obtained results demonstrated that prototype testing is highly effective for detecting a wide range of usability issues early in the digital-product development phase. The paper also evaluates the predictive capabilities of SUS assessment for the case of the Figma web prototype and its counterpart live web system in the phase of digital-product development. The results show that the SUS evaluation, when applied to digital-system prototype testing, can provide early in the development process a reliable indication of the perceived usability of its counterpart digital system, once it is developed and deployed. The findings presented in the paper offer valuable guidance for software designers and developers seeking to make prototypes and their counterpart real digital-product deployments with improved digital-product overall user experience. Full article

The rapid growth of e-commerce and the booming online fashion industry are driving growing user demand for sophisticated, compatible fashion outfits. As an emerging multimodal information retrieval technology, fashion compatibility modeling aims to predict the compatibility degree for any given outfit and provide complementary item recommendations for incomplete outfits. Although existing research has made significant progress in exploring fashion compatibility tasks from a multimodal perspective, it has yet to fully exploit the multimodal information and correlations among fashion items. To effectively tackle these challenges, a correlation-aware multimodal fusion network for fashion compatibility modeling is proposed. Long-distance correlated visual features are investigated during multimodal processing to enhance the quality of visual features. An improved dual-interaction mechanism is used to achieve deep multimodal fusion. Furthermore, we explore both negative and multi-scale correlations to obtain complex correlations among items and thereby enhance the accuracy of fashion compatibility assessment. Extensive experiments on real-world fashion datasets demonstrate that our method outperforms existing advanced benchmark models in AUC and ACC metrics. This indicates the efficiency of our model in enhancing fashion compatibility evaluation performance. Full article

Link prediction is a fundamental problem for graphs, which can reveal the potential relationships between users. Graph embedding can easily encode graph structural relations, and heterogeneous attribute features in a continuous vector space, which is effective in link prediction. However, graph embedding methods for large-scale graphs suffer high computation and space costs, and sampling enclosing subgraphs is a practical yet efficient way to obtain the most features at the least cost. Nevertheless, the existing sampling techniques may lose essential features when the random sampling number of nodes is not large, as node features are assumed to follow a uniform distribution. In this paper, we propose a novel large-scale graph sampling strategy for link prediction named Weighted Sampling Enclosing subgraphs-based Link prediction (WSEL) to resolve this issue, which maximumly preserves the structural and attribute features of enclosing subgraphs with less sampling. More specifically, we first extract the feature importance of each node in an enclosing subgraph and then take the node importance as node weight. Then, random walk node sequences are obtained by multiple weighted random walks from a target pair of nodes, generating a weighted sampling of enclosing subgraphs. By leveraging the weighted sampling enclosing subgraphs, WSEL can scale to larger graphs with much less overhead while maintaining some essential information of the original graph. Experiments on real-world datasets demonstrate that our model can scale to larger graphs while maintaining competitive link prediction performance under substantially reduced computational cost. Full article

While electroencephalography (EEG) is effective for assessing stress and mental workload, its widespread adoption is currently hindered by the complex setup of most existing EEG systems. This article presents a new in-ear EEG system and investigates its feasibility for developing robust models to quantify stress and mental workload levels. The system consists of a single-channel EEG acquisition device that has a similar form factor as user-generic earpieces. All electrodes including passive, reference and bias electrodes were put on the ear, which optimized the device’s usability. We validated the system through two experiments with 66 subjects to collect EEG data under varying stress and mental workload conditions. We developed classification and regression models to predict stress and mental workload levels from the data. Cross-subject stress classification achieved 77% accuracy, while within-subject stress regression yielded an average R2 of 0.76 ± 0.20. Two-class mental workload level classification reached accuracies between 70% and 80% for the arithmetic and finger tapping tasks. Feature importance analysis revealed that frequency-domain EEG features, particularly in the alpha and beta bands, significantly contributed to the models’ performance. However, we observed lower within-subject feature variation and model accuracy for the mental rotation, potentially due to the distance between brain regions engaged and the device’s recording site. Our findings demonstrate the potential of using the presented EEG device to monitor stress and mental workload in real-time. Full article

Smart environments play a key role in improving user comfort, energy efficiency, and sustainability through intelligent automation. Nevertheless, real-world deployments still face major challenges, including network instability, delayed responsiveness, inconsistent AI decisions, and limited adaptability under dynamic conditions. Many existing approaches lack advanced context-awareness, effective multi-agent coordination, and scalable learning, leading to high computational cost and reduced reliability. To address these limitations, this paper proposes MACxRL, a lightweight Multi-Agent Context-Aware Reinforcement Learning framework for autonomous smart-environment control. The system adopts a three-tier architecture consisting of real-time context acquisition, lightweight prediction, and centralized RL-based decision learning. Local agents act quickly at the edge using rule-based reasoning, while a shared CxRL engine refines actions for global coordination, combining fast responsiveness with continuous adaptive learning. Experiments show that MACxRL reduces energy consumption by 45–60%, converges faster, and achieves more stable performance than standard and deep RL baselines. Future work will explore self-adaptive reward tuning and extend deployment to multi-room environments toward practical real-world realization. Full article

E-commerce retailers bear substantial additional costs arising from high product return rates due to lenient return policies and consumers’ impulsive purchasing. This study aims to accurately predict product return behavior before payment, supporting proactive return management and reducing potential losses. Based on the Graph Transformer, we proposed a novel return prediction model, Returnformer, which focuses on capturing user–product connections represented in topological structures of bipartite graphs. The Returnformer first integrates global topological embeddings into original node features to alleviate structural information loss caused by graph partitioning. It then employs a Graph Transformer to capture long-range user–item dependencies within local subgraphs. In addition, a graph-level attention mechanism is introduced to facilitate the propagation of global return patterns across different subgraphs. Experiments on a real-world e-commerce dataset show that the Returnformer outperforms four machine learning models in terms of prediction accuracy, demonstrating superior performance compared to the state-of-the-art models. The proposed model enables retailers to identify potential return risks prior to payment, thereby supporting timely and proactive preventive interventions. Full article

This study examines digital sustainability signals and the psychological mechanisms (authenticity and trust) that relate to consumers’ sustainable food purchase intentions. While the attitude–behavior gap remains a persistent challenge in sustainability research, our study focuses on upstream factors that may help explain why intentions vary in strength. Drawing on signaling theory, this research develops and tests a framework that combines positive signals (e.g., influencer credibility) and negative signals (e.g., perceived greenwashing) to investigate the impact on green brand authenticity, brand trust, and purchase intention. Data were gathered from a survey of 324 adult social media users who follow influencers with a focus on sustainability and have recent experience buying eco-labeled food products. Using PLS-SEM, results indicate that influencer credibility has a significant and positive effect on perceptions of green brand authenticity, whereas the influence of greenwashing has a significant and negative effect. Authenticity shows a strong prediction of brand trust, and this in turn predicts green purchase intentions with trust mediating the authenticity–intention relationship to some degree. The results indicate authenticity as a key mechanism by which digital signals affect sustainable consumption. The research provides practical insights for food brands seeking to strengthen the psychological conditions that support sustainable consumption intentions. Full article

Predicting information diffusion in social networks is a fundamental problem in many applications, and one of the primary challenges is to predict the future popularity of information in social networks. However, most existing models fail to simultaneously capture the accurate micro-level user node features, meso-level linear spread features, and predict the macro-level popularity during the information propagation process, which may result in unsatisfactory prediction performance. To address this issue, we propose a new cascade prediction framework CasNS: Node-level and Sequence-level Features for Cascade Prediction. CasNS utilizes node-level features by employing a self-attention mechanism to capture the hidden features of the target node with respect to other nodes. Additionally, it leverages multiple one-dimensional convolutional layers with the dynamic routing algorithm to obtain sequence-level features across different dimensions. Through experiments on a large number of real-world datasets, our model demonstrates superior performance compared with other state-of-the-art methods, thereby validating the feasibility of our approach. Full article

The lack of explicit negative labels issue is a prevalent challenge in numerous domains, including CV, NLP, and Recommender Systems (RSs). To address this challenge, many negative sample completion methods are proposed, such as optimizing sample distribution through pseudo-negative sampling and confidence screening in CV, constructing reliable negative examples by leveraging textual semantics in NLP, and supplementing negative samples via sparsity analysis of user interaction behaviors and preference inference in RS for handling implicit feedback. However, most existing methods fail to adequately address the Missing-Not-At-Random (MNAR) nature of the data and the potential presence of unmeasured confounders, which compromise model robustness in practice. In this paper, we first formulate the prediction task in RS with implicit feedback as a positive-unlabeled (PU) learning problem. We then propose a two-phase debiasing framework consisting of exposure status imputation, followed by debiasing through the proposed doubly robust estimator. Moreover, our theoretical analysis shows that existing propensity-based approaches are biased in the presence of unmeasured confounders. To overcome this, we incorporate a robust deconfounding method in the debiasing phase to effectively mitigate the impact of unmeasured confounders. We conduct extensive experiments on three widely used real-world datasets to demonstrate the effectiveness and potential of the proposed methods. Full article