The paradigm of web search is currently shifting from reactive information retrieval to Agentic AI, where proactive systems autonomously synthesise information to assist users. However, for these agents to be effective, they must understand which user parameters drive behaviour to resolve the personalisation cold-start problem. While cognitive architecture is a recognised factor, empirical evidence linking specific traits to web search interaction remains unclear. This paper investigates the Verbal-Imagery (V-I) cognitive style dimension and its influence on proactive search behaviour, mental workload (MWL), and overall search user interface (SUI) alignment. Through a controlled user study (N = 20), web search behaviours were evaluated using interaction logs and think-aloud protocols, while MWL and usability were assessed via NASA-TLX and the System Usability Scale (SUS). Our findings reveal that verbalisers and imagers adopt statistically distinct navigational preferences: ver-balisers prefer sporadic, reactive interactions, while imagers rely on structured, proactive synthesis such as the Knowledge Panel. It is worth noting that qualitative data identifies a "trust gap" in AI-generated overviews based on cognitive modality preferences. These results demonstrate that the V-I dimension is a critical parameter for user modelling in agentic systems. We conclude by proposing requirements for user-aware agentic information retrieval, providing a framework for agents to dynamically adapt their representation strategies to minimise cognitive friction and enhance trust in proactive computing environments. This work is licensed under a Creative Commons "Attribution 4.0 International" license.

Cognitive style, a user's habitual approach to information processing, offers a promising approach to personalising information searching (IS) systems, yet the underlying style-related search behaviours remain poorly understood. This study investigates how the Wholist–Analytic and Verbal–Imagery dimensions of cognitive style influence search behaviour and prefrontal cortex (PFC) activation during the Post-focus stage of exploratory search. Forty participants completed comparison search tasks while we recorded behavioural metrics, subjective workload ratings, and functional near-infrared spectroscopy (fNIRS) data. Our results demonstrate that cognitive style significantly predicted search engine results page (SERP) interaction patterns: analytics and imagers adopted structured navigation with detailed reading, whereas wholists and verbalisers preferred sporadic navigation with rapid scanning. Critically, fNIRS revealed distinct PFC activation patterns, specifically in the Ventrolateral PFC (VLPFC) and Dorsolateral PFC (DLPFC), corresponding to these behavioural differences. By mapping neuro-cognitive profiles to IR behaviours, this work provides empirical grounding for designing ''style-aware'' adaptive IR interfaces that tailor information density and navigational support to individual cognitive profiles.

Many studies have shown that collaborative tasks in immersive virtual reality (VR) and augmented reality (AR) environments can enhance collaborative outcomes in learning, training, and game-based contexts. However, the literature offers limited information on how these environments differentially shape social presence and collaborative engagement, particularly among unfamiliar users. This study addresses this gap by examining differences in social presence and collaborative engagement between VR and AR environments for unfamiliar pairs. A between-subjects experiment used an escape room game that featured three collaborative tasks, identically implemented in both VR and AR. The key difference was that the VR experience was stationary, while the AR experience required physical movement between rooms. The study involved 52 participants, divided into VR and AR groups, where two unfamiliar participants were paired into teams to complete the tasks. The results indicate significant differences in collaborative dynamics and user perception between the two environments. Specifically, VR pairs reported a stronger sense of immersion and flow state, whereas AR pairs demonstrated greater contextual awareness and behavioral coordination. Cybersickness measures also differed between conditions; given the locomotion mismatch, this pattern should be interpreted cautiously and not attributed to the environment alone. This finding improves understanding of the impact of immersive environments on collaborative processes and offers insights for designing collaborative XR applications (e.g., training and game-based teamwork), particularly for unfamiliar users.

Abstract Substantial financial losses due to fraud drive the need for accurate detection algorithms. However, machine learning classifiers frequently show bias towards non-fraudulent classes due to class imbalance, where fraudulent instances occur much less frequently. Current oversampling techniques, such as the Synthetic Minority Oversampling TEchnique and Generative Adversarial Networks, generate noisy samples, produce suboptimal proportions of minority classes, and neglect majority class distributions, leading to degraded classifier performance. To address these limitations, this study investigates the feasibility of reinforcement learning (RL) for selecting generated minority samples. This study proposes a general-purpose RL-based sample selection method that is agnostic to both oversampling technique and classifier, which dynamically filters the generated minority samples using classifier feedback and information from minority and majority neighborhoods. The investigation reveals technical challenges, including sparse reward and high computational cost, which must be addressed for RL to become a practical solution for minority sample selection.

The learning-based, passive, device-free wireless human activity recognition (WHAR) systems still face significant challenges, especially in real-world deployments. Environmental differences and domain diversities cause signals collected in the source domain to have a different distribution from those in the target domain, and this affects the accuracy. To achieve domain generalization (DG), a multi-scale linear attention vision transformer (ViT) based feature extractor and domain adversarial learning with Wasserstein distance are proposed. By aligning both marginal and conditional distributions across different source domains, the adversarial learning reduces the differences between trained and unseen domains. As a result, the extracted features become domain-invariant in the latent space, ensuring accuracy is preserved in new or unseen domains. Extensive evaluations using commercial IEEE 802.11ac routers with human activity data collected over different days, environments, human subjects, and obstacle configurations show that the proposed Wi-ViTAL achieves 97.57% average accuracy for five-label classification and more than 76% for eight-label classification in unseen domains. Wi-ViTAL also demonstrates an overall DG improvement compared to other recent benchmarks.

The adoption of immersive virtual reality (IVR) for gamified rehabilitation is increasing. However, a significant challenge relates to perceptions of virtual environments as empty and isolating, potentially increasing stress, particularly among older users (patients). This paper explores the use of a virtual peer mentor (VPM) in a custom IVR-rehabilitation game to provide guidance and companionship. This game specifically targets patients recovering from acute myocardial infarction (AMI), commonly known as a heart attack. Grounded in social support theory, the VPM provides three types of support: (1) informational support, through pre-exercise narratives detailing a shared medical history; (2) instrumental support, through real-time demonstrations of clinically-validated exercise movements; and (3) emotional support, through positive feedback and encouragement. A within-subjects study involving 30 hospitalized AMI patients (all over 47 years old) evaluated the effectiveness of the VPM-integrated IVR-rehabilitation game. Each participant experienced a baseline (no VPM) and VPM-integrated version of the game on separate days. The results from the Intrinsic Motivation Inventory (IMI) and the social presence module of the Game Experience Questionnaire (GEQ-SPM) show that the VPM resulted in significant increases in engagement, and statistically significant lower pressure/tension. Furthermore, participants exhibited high user acceptance (76.7%) and task-completion rates (98.5%), with minimal cybersickness. The findings demonstrate that a psychologically-grounded VPM can effectively reduce stress in middle- and older-age patients in an IVR rehabilitation setting.

The convergence of virtual reality live streaming and AI-driven avatars has emerged as a significant technological trend. However, current integration attempts remain in the proof-of-concept stage, with the primary challenge of automatic interaction system establishment. To build interactive intelligence anime avatars within VR frameworks, we have developed a multimodal interaction architecture centered on dialogue agents, realizing comprehensive understanding, reasoning, and response. Our approach 1).proposes high granularity explicit-implicit understanding and a dual-center switchable reasoning mechanism to support flexible responses. 2).innovates a dual-source animation mechanism for co-speech face-body visualization and a textual command module for supervising crossmodal animation, and 3).enhances expressiveness through mapping persona, content, voice, and motion to anime style. Experimental results demonstrate the state-of-the-art performance of VRtalk, highlighting its practical significance and future potential.

Recent advancements in immersive virtual reality (IVR) have highlighted its expanding potential in educational settings. However, the influence of learners’ interpersonal relationships on their preferences for gamification elements in collaborative environments remains underexplored. This study introduces an avatar-based multiplayer IVR game designed to promote collaborative learning through improved social interaction. The game features a maze with three challenging puzzles, which require teamwork and problem-solving skills, encouraging communication and information sharing among participants. In addition, the study investigates the impact of different gamification elements on groups consisting of either peers or strangers, involving a total of 44 participants. The findings revealed significant improvements in communication and collaboration skills, along with increased motivation and engagement, across both group types. Moreover, participants exhibited distinct preferences for specific gamification elements, largely influenced by the nature of their social relationships and individual tendencies. This study offers valuable insights into the design of IVR-based collaborative educational environments with an emphasis on social interaction and game mechanics. It also identifies key factors shaping individual preferences for gamification elements, particularly in relation to social dynamics and personal preferences.

Over the past decades, China has faced an increasingly severe fire issue, resulting in significant human and financial losses. Consequently, the importance of enhancing fire safety education for citizens has become more pronounced. However, due to safety risks in actual fire scenes, the practical use of firefighting equipment was often learned passively through text or video resources, posing challenges in ensuring users can proficiently operate actual equipment. Virtual reality (VR) emerged as a promising technology to provide users with a low-risk environment to gain hands-on experience with firefighting equipment. Therefore, this study aimed to assess the effectiveness of a specially designed VR game-based firefighting extinguishing equipment training (FEET) that integrated VR with serious gaming elements. The study evaluated the effectiveness of FEET through a comparison between high (HI) and low (LI) immersiveness VR and a non-immersive (NI) setting as a baseline. The study incorporated haptic feedback mechanisms, such as audio and vibration, to enhance user immersiveness within the HI setting. The focus of the study was on evaluating knowledge acquisition, user experiences, and interaction preferences for the proposed FEET design. The study adopted three distinct learning sequences to mitigate the VR halo effects. The results of the study indicated that both VR-based learning methods yielded outstanding user experiences that significantly surpassed the NI setting. Furthermore, the study showed that haptic feedback with richer game contents further enhanced user experiences, underscoring the importance of simulating realistic sensing in improving learning outcomes.

Machine learning (ML) techniques are applied for profiling computing and processing resources data collected while running deep neural network models on edge devices. Adaptive deep neural network (DNN) model switching requires proper benchmarking for categorizing AI models based on their applications and computational resources enabled by their processing accelerators. Based on benchmark metrics, DNN models can be classified into tiny, low, small, medium, and large resources, then identify DNN models that perform well within resource constraints. Ensure efficient resource allocation, latency management, and trade-off between accuracy and resource. In this work, we propose a benchmark for edge transfer artificial intelligence learning service (TALS) that uses ML techniques. They aim at classifying DNN models by their target edge applications while running edge inferences. We used both unsupervised learning (UL) and supervised learning (SL) techniques to identify the most effective features for the TALS models and to benchmark the performance of edge devices. To achieve this, two approaches were investigated: first, determining features based on edge inference’s computing resources profiling using principal component analysis; and second, classifying the DNN models at the target application level using a regression approach based on historical resource utilization data. In addition, we propose a dynamic model transfer learning that switches between a set of pre-trained and optimized and quantized DNN models based on the cost function. ML techniques learn resource-aware prediction from new resource allocation data and ensure that the multicriteria switch cost selects the inference task models that meet the edge resource constraint requirements. The experimental results highlight a strong relationship between the supervised learning model and the clustering execution method. The dynamic switching approach on real edge devices demonstrates dynamic switching between models according to inference task complexity. We conclude that dynamic switching models allows to ensure smooth operation without overloading resources in edge intelligence.

Path planning is the core of autonomous robot navigation, which helps the robot to find a collision-free path to the destination based on the environment information. Most current path planning methods only consider the path length, but the optimal path may deviate from the shortest when considering other environmental factors such as uneven terrain or regions with varying traversal costs. Similarly, in scenarios prioritizing energy efficiency, a sole focus on path length may lead to suboptimal solutions. In this paper, an improved Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) with adaptive weight vector, external archive, and constrained update strategy namely the MOEA/D-EAWA is proposed. This algorithm not only considers the path length but also four additional objectives such as smoothness, traveling time, terrain (elevation), and speed limit (expected delay). In addition, MOEA/D-EAWA is better suited for such many-objective path planning problem which has an irregular, discrete, and sparse Pareto front. The simulation results from 90 map instances demonstrate that the proposed method outperforms the existing approaches.

Immersive Virtual Reality (IVR) exergaming presents a promising avenue to integrate physical exercise with engaging virtual experiences, potentially encouraging sustained physical activity. However, maintaining user motivation over extended periods poses a significant challenge. Recent research has introduced the Dynamic Difficulty Adjustment (DDA) mechanism, dynamically regulating exergame difficulty based on specific conditions to enhance user adaptation. While prior studies have predominantly focused on gaming performance to adjust difficulty, they often overlook the emotional impact on user motivation. This study investigates users' emotional responses to the game timer change (TC) as a DDA mechanism during IVR exergaming. Results indicate that subjects in the TC-implemented game displayed more neutral emotions, concomitant with improved gaming performance. Conversely, subjects in the game without TC exhibited a broader range of detected emotions (sad and happy), suggesting difficulties in adapting to in-game difficulty levels incongruent with their gaming abilities. Overall, this study establishes a foundation for future research in affective computing-based IVR exergaming, aiming to develop an intelligent autonomous DDA mechanism tailored to users' physical and mental conditions.

Physics education posed challenges, with students' limited interest attributed to the subject's abstract nature as well as educators' struggles in conveying complex concepts effectively. To address these challenges, a collaborative-based, high-immersion virtual reality (IVR) game approach for physics education was proposed in this study. The focus of this study was to enhance student motivation and improving learning outcome through the integration of serious game elements. Eight distinct serious game elements were explored, incorporating narrative, autonomy, accomplishment, ownership, social interaction, challenge, and immersion into the game design. Students were assigned to complete three physics experiments within the game where they required to work collaboratively. Results indicated high ratings for integrated game features, with questionnaire responses revealing enhanced motivation among students who found physics less interesting. These findings highlighted the effectiveness of collaborative learning within IVR serious games, offering a valuable framework for future serious game design in physics education.

Observational studies are widely used in Human-Computer Interaction (HCI) research to evaluate usability and user experience with technologies. However, the act of observation may influence participant behaviour and performance, threatening the validity of study findings. This paper investigates the impact of three observation types on participant outcomes in a simulated HCI study context. Participants completed Sudoku puzzles under baseline (no observation), human observation, sensor-based observation, and combined human/sensor conditions. Performance was assessed by puzzle completion rates. The mental workload was measured via NASA-TLX surveys, heart rate, galvanic skin response, and infrared thermal imaging. Results showed observations negatively impacted performance versus baseline, with human observers inducing the greatest distraction. Experienced participants were more influenced than novices. Task medium also affected engagement and observation reactivity. Findings demonstrate observations introduce bias in HCI research, emphasising careful consideration of observation methods to improve result validity.

Infrared thermal imaging presents significant potential in various domains. However, the widespread development of this technology is hindered by the high cost associated with acquiring high-quality thermal imaging sensors. To overcome this challenge, super-resolution techniques have emerged as a viable solution for extracting valuable information from low-resolution thermal images. While generative adversarial networks (GANs) have been widely adopted for thermal imaging super-resolution, their performance is limited by the inherent lack of detail in low-resolution training images, resulting in reduced fidelity and accuracy in generating high-resolution reconstructions. To tackle this challenge, this letter introduces FEGAN, a novel approach that enhances the performance of GANs by incorporating a feature-oriented enhanced (FE) mechanism within the generative network (GN). The FE plays a pivotal role in extracting high-frequency texture and edge details from lowresolution inputs and reconstructing them into enhanced images. This process substantially improves textures and edges within the training set of thermal images. Furthermore, refinements have been applied to both the GN and the discriminative network (DN) to enhance feature extraction efficiency. The experimental findings unequivocally demonstrate the superior performance of FEGAN compared to state-of-the-art methods. FEGAN achieves impressive performance metrics, including PSNR of 27.18, SSIM of 0.6523, FSIM of 0.5500, and LPIPS of 0.1221, highlighting its remarkable capabilities in the realm of thermal image superresolution.

Robot-assisted catheterization offers a promising technique for cardiovascular interventions, addressing the limitations of manual interventional surgery, where precise tool manipulation is critical. In remote-control robotic systems, the lack of force feedback and imprecise navigation challenge cooperation between the surgeon and robot. This study proposes a manipulation-based evaluation framework to assess the cooperative performance between different operators and robot using kinesthetic, kinematic, and haptic data from multi-sensor technologies. The proposed evaluation framework achieves a recognition accuracy of 99.99% in assessing the cooperation between operator and robot. Additionally, the study investigates the impact of delay factors, considering no delay, constant delay, and variable delay, on cooperation characteristics. The findings suggest that variable delay contributes to improved cooperation performance between operator and robot in a primary-secondary isomorphic robotic system, compared to a constant delay factor. Furthermore, operators with experience in manual percutaneous coronary interventions exhibit significantly better cooperative manipulate on with the robot system than those without such experience, with respective synergy ratios of 89.66%, 90.28%, and 91.12% based on the three aspects of delay consideration. Moreover, the study explores interaction information, including distal force of tools-tissue and contact force of hand-control-ring, to understand how operators with different technical skills adjust their control strategy to prevent damage to the vascular vessel caused by excessive force while ensuring enough tension to navigate complex paths. The findings highlight the potential of variable delay to enhance cooperative control strategies in robotic catheterization systems, providing a basis for optimizing surgeon-robot collaboration in cardiovascular interventions.

Indoor positioning in the firefighting ground shows promising application prospects for enhancing rescue safety and efficiency. Low visibility and signal interference caused by smoke pose significant difficulties for visual Simultaneous Localization and Mapping (SLAM) systems and radio frequency-based localization methods, while the performance of existing pedestrian dead reckoning (PDR) methods is affected by unpredictable user gaits. This paper introduces a gait analysis-based PDR (GA-PDR) for deriving heading estimation in PDR to improve its localization performance. The proposed method determines the step pattern by analyzing the features of inertial measurement unit data, thereby enabling the classification of forward, left- and right-turn and around-turn from left or right-side movements. In addition, this study introduces a redundant turn elimination method to differentiate false positive patterns via a time-domain heading analysis for turn movements. The location tracking performance with the proposed GA-PDR approach is validated using a self-created dataset established under a smoke-filled experiment, the results of which indicate a lower loop closure error compared with the traditional PDR in all of the tested scenarios.

The demand for firefighting has significantly risen in recent decades, accompanied by increased risks faced by firefighters. Tragic incidents, such as the Shanghai factory fires, have resulted in the loss of over thirty firefighter lives. One of the primary contributing factors is the abrupt breakdown in communication between firefighters inside a building and the commanding officer stationed outside, attributable to the harsh and complex indoor environment. This study aims to conduct a comparative analysis of different widely used wireless transmission methods, including Wi-Fi, Bluetooth Low Energy (BLE), and Long Range (LoRa). The experiments are conducted in a two-room setup, with two brick walls acting as a barrier. A wireless data transmitter is placed in one room, while smoke is generated. A receiver placed at varying distances collects the signal strengths. The findings indicate that LoRa exhibits the least drop in signal strength compared to the other methods. In contrast, BLE shows high signal strength variation for the same distances and is not recommended for firefighting communication purposes. This study provides valuable insights for selecting suitable wireless communication modules, particularly in the design of wearable devices for assessing safety risks faced by firefighters.

Negative emotional responses are a growing problem among drivers, particularly in countries with heavy traffic, and may lead to serious accidents on the road. Measuring stress- and fatigue-induced emotional responses by means of a wireless, wearable system would be useful for potentially averting roadway tragedies. The focus of this study was to develop and verify an emotional response-monitoring paradigm for drivers, derived from electromyography signals of the upper trapezius muscle, photoplethysmography signals of the earlobe, as well as inertial motion sensing of the head movement. The relevant sensors were connected to a microcontroller unit equipped with a Bluetooth-enabled low-energy module, which allows the transmission of those sensor readings to a mobile device in real time. A mobile device application was then used to extract the data from the sensors and to determine the driver's current emotion status, via a trained support vector machine (SVM). The emotional response paradigm, tested in ten subjects, consisted of 10 min baseline, 5 min prestimulus, and 5 min poststimulus measurements. Emotional responses were categorized into three classes: relaxed, stressed, and fatigued. The analysis integrated a total of 36 features to train the SVM model, and the final stimulus results revealed a high accuracy rate (99.52%). The proposed wearable system could be applied to an intelligent driver's safety alert system, to use those emotional responses to prevent accidents affecting themselves and/or other innocent victims.

Increased driver stress is generally recognized as one of the major factors leading to road accidents and loss of life. Even though physiological signals are reported as the most reliable means to measure driver stresses, they often require the use of unique and expensive sensors, which produce dynamic and varying readings within individuals. This paper presents a novel means to predict a driver's stress level by evaluating the movement pattern of the steering wheel. This is accomplished by using an inertial motion unit sensor, which is placed on a glove worn by the driver. The motion sensor selected for this paper was chosen because for its low cost and the fact that it is least affected by environmental factors as compared with a physiological signal. Experiments were conducted in three different environmental scenarios. The scenarios were classified as “urban,” “highway,” and “rural,” and they were chosen to simulate contrasting stress conditions experienced by the driver. In this paper, skin conductance and driver self-reports served as a reference stress to predict the driver's stress level. Galvanic skin response, a well-known stress indicator, was captured along the driver's palm and the readings were transmitted to a mobile device via low energy Bluetooth for further processing. The results revealed that indirect measurement of steering wheel movement with an inertial motion sensor could obtain accuracies up to an average rate of 94.78%. This demonstrates the opportunity for inclusion of motion sensors in wireless driver assistance systems for ambulatory monitoring of stress levels.

This study presents a novel approach to detect driver's drowsiness by applying two distinct methods in computer vision and image processing. The objective of this study is to combine both methods under one single profile instead of relied solely on a detection method to enhance the driver's drowsiness detection resolution. Therefore a non-intrusive drowsy-monitoring system is developed to alert the driver if driver falls into low arousal state. In physiological part, photoplethysmography (PPG) is analysed for its changes in signals waveform from awake to drowsy state. Meanwhile, eyes pattern or motion in image processing is addressed to detect driver fatigue. Genetic algorithm with template-matching approach is designed to detect eye region and estimate the drowsiness in different metric standard based on eyes behaviour. Moreover, PPG drowsy signals are integrated with eyes motion to derive the final probability model for delivering valid and reliable drowsiness detection system. Indeed, the proposed system provides high competitive edge over existing arbitrary drowsiness detection system where the driver's health and mental states can be monitored in real-time without constraints.