Search Results (696)

Skeleton-based action recognition is a critical technology for intelligent sports analysis. Although the human skeletal structure exhibits inherent bilateral symmetry, sensor noise on resource-constrained edge devices frequently induces geometric distortion and topological asymmetry. Consequently, achieving a balance between high accuracy and real-time performance remains a significant challenge. To this end, we propose EMS-GCN, an Efficient Multi-scale Shift Graph Convolutional Network that integrates geometric priors. Specifically, we design a Gaussian kernel-driven topology refinement module to mitigate structural noise inherent in sensor data. By leveraging geometric symmetry and Gaussian distances among nodes, this module dynamically constrains graph topology learning, thereby effectively rectifying the structural asymmetry and ambiguity induced by noise. Furthermore, we construct a Multi-scale Shift Linear Attention (MSLA) module to replace computationally intensive temporal convolutions. Leveraging temporal shift invariance, this module captures multi-scale contexts via parameter-free shift operations. Furthermore, we introduce a linear temporal attention mechanism to model global temporal dependencies with linear complexity, effectively resolving the information asymmetry inherent in long-range interactions. Finally, EMS-GCN incorporates a dual-branch attention structure to adaptively calibrate feature responses. Extensive experiments demonstrate that our model maintains high recognition accuracy with only 0.56M parameters, representing a reduction of over 60% compared to mainstream baselines. These results validate the efficacy of leveraging geometric and temporal symmetries to enhance real-time sports analysis. Full article

Background/Objectives: Observational learning allows people to acquire new skills by observing the actions of others embedded in their social environment. From childhood, observational learning is a central process in human cognitive development, playing a crucial role in the acquisition of complex skills. Children and adults with autism spectrum disorder (ASD) often exhibit deficits in what are considered prerequisites for observational learning to occur (i.e., attending, imitation, delayed imitation, consequence discrimination). Considering this, the present review examined the literature on the complex and timely question of whether individuals with ASD can learn by observation, while accounting for the social versus non-social nature/content of the tasks. Methods: This work was a narrative review aimed at providing an overview of published studies in which observational learning was analyzed in individuals with ASD. Twenty-two studies met the inclusion criteria and were eligible for this review. Results: The core findings indicate that individuals with ASD may be able to learn by observing others, especially when taught the prerequisites for observational learning. Furthermore, the findings indicate that observation may be an effective way to expand the typically restricted and circumscribed interests of children with ASD and to increase emotion recognition skills. Conclusions: Overall, these findings have significant educational, clinical, social, and economic implications, supporting the use of observational learning strategies for both social and non-social skills to reduce reliance on expensive one-on-one teaching and to address some of the core deficits of ASD. Full article

As a non-invasive mucosal immunization strategy, intranasal vaccines are highly promising for preventing respiratory infectious diseases. Among them, recombinant subunit vaccines represent a safe and ideal option, as they induce targeted mucosal immunity without the safety risks associated with live-vectored or nucleic acid vaccines. However, nasal mucosal defenses rapidly clear antigens before immune activation, limiting protective efficacy. Therefore, intranasal vaccine adjuvants—key regulators of immune response intensity, duration, and type—are essential to overcome mucosal tolerance and improve immunogenicity. Based on a systematic search and analysis of 127 peer-reviewed articles (2010–2026) in PubMed, Web of Science, and Embase, this study comprehensively summarizes the mechanisms, applications, and limitations of existing and candidate adjuvants for intranasal vaccines. This review systematically categorizes and discusses the nasal mucosal barrier, major adjuvant types (e.g., pattern recognition receptor agonists, cytokine adjuvants, and carrier adjuvants), and their mechanisms of action. It also identifies key bottlenecks: insufficient mucosal targeting, inconsistent global safety evaluation standards for adjuvants, and interference from pre-existing antibodies in humans. Furthermore, this review highlights future development directions, including biomimetic adjuvants, pH-responsive nanoadjuvants, and thermostable vaccine formulations. This systematic review clarifies key scientific and technical barriers in intranasal vaccine adjuvant development. The findings provide valuable references for advancing the translation of intranasal vaccines from emergency countermeasures to routine, accessible preventive tools for respiratory infectious diseases. Full article

Collaborative robots are increasingly deployed in human-shared industrial workspaces, where perception is a key enabler for safe interaction, flexible manipulation, and human-aware task execution. In the context of Industry 5.0, computer vision for cobots must meet not only accuracy requirements but also human-centered constraints such as safety, transparency, robustness, and practical deployability. This paper surveys computer-vision approaches used in collaborative robotics and organizes them through a task-driven taxonomy covering detection, segmentation, tracking, pose estimation, action/gesture recognition, and safety monitoring. Beyond a descriptive literature review, the paper provides a task-driven qualitative analytical perspective that relates families of computer vision methods to key industrial constraints, including occlusion, lighting variability, clutter, domain shift, real-time latency, and annotation cost, and summarizes comparative strengths and failure modes using unified criteria. We further discuss challenges related to data availability and evaluation practices, highlighting gaps in reproducibility, standardized metrics, and real-world validation in shared human–robot environments. Finally, we outline implementation and deployment considerations across common software stacks (e.g., Python-based pipelines and MATLAB-based prototyping), emphasizing ROS2 integration, edge inference, and lifecycle maintenance. The survey concludes with research directions toward robust multimodal perception, explainable human-aware vision, and benchmarkable safety-critical perception for next-generation collaborative robotic systems. Full article

Concrete placement surfaces are characterized by intensive construction processes, frequent equipment interactions, and strong spatial dynamics, which make it difficult to identify unsafe actions of construction workers in real time and to accurately quantify and warn about regional safety risks. To address these challenges, this study proposes a safety monitoring method for construction workers operating on complex concrete placement surfaces. First, a coupled risk assessment framework integrating regional hazard levels, unsafe action risks, and worker authorization is established based on trajectory intersection theory (TIT). Subsequently, a multi-source continuous sensing system is developed by integrating global navigation satellite system (GNSS) positioning, inertial measurement unit (IMU)-based human activity recognition (HAR) using a BiLSTM-Attention model, and unmanned aerial vehicle (UAV)-based 3D realistic scene modeling. On this basis, real-time visualization and risk warning of worker trajectories, action states, and spatial risks are achieved through multi-source data fusion and a WebGL-based visualization platform. Field validation results indicate that the proposed system can generate alarm outputs that are consistent with the predefined risk rules within 3 s in typical construction scenarios, demonstrating rule-consistent real-time feasibility and stable system response performance. Full article

An intelligent multi-step action recognition system was designed for long-term caregiver training and assessment. Leveraging MediaPipe for precise and real-time human pose estimation, the system extracts detailed spatiotemporal body and hand keypoints. Temporal convolutional networks are employed to effectively capture temporal dependencies and complex features from sequential motion data. Dynamic time warping provides robust sequence alignment, allowing flexible comparison between performed actions and standard templates despite temporal variations in execution speed or style. A finite state machine imposes logical constraints by modeling expected action step sequences, enabling accurate detection of sequence anomalies or deviations. This hybrid architecture supports comprehensive evaluation and real-time feedback, facilitating improved caregiver skill acquisition, process adherence, and quality control within long-term care settings. The system aims to advance digital transformation in healthcare education by providing a scalable, precise, and adaptive training solution. Full article

The rapidly expanding body of biomedical literature encompasses a wealth of information concerning the pharmacological effects, mechanisms of action, adverse reactions, and repurposing potential of small-molecule therapeutics. Nevertheless, the systematic extraction and integration of this knowledge continue to pose substantial challenges. In this study, we propose an integrated text-mining framework for the automated extraction and structured representation of information on the biological activities of low-molecular-weight compounds, exemplified by angiotensin-converting enzyme (ACE) inhibitors as a representative pharmacological class. A corpus comprising over 20,000 PubMed titles and abstracts reporting in vitro, in vivo, and clinical investigations of ACE inhibitors was assembled. Chemical compounds, proteins/genes, and diseases were recognized using a previously developed named entity recognition model based on conditional random fields. Entity-level associations were extracted at the sentence level through a rule-based approach employing manually curated pattern phrases, followed by normalization via automated queries to PubChem, UniProt, and the Human Disease Ontology. The proposed methodology facilitated the extraction of approximately 22,000 unique and normalized associations encompassing drug-target, drug-disease, and drug-drug relationships. In addition to confirming well-established therapeutic effects and clinically recognized drug combinations, the analysis identified underexplored pharmacological activities of ACE inhibitors, including antineoplastic, antifibrotic, and neuropsychiatric properties, along with mechanistic associations involving matrix metalloproteinases and neurotrophic signaling pathways. Collectively, these findings underscore the potential of automated literature mining to advance systematic knowledge integration and data-driven hypothesis generation in the contexts of drug repurposing and safety evaluation. Full article

Semi-automated urban rail transit systems still rely on human intervention during safety-critical events, yet emergency takeover performance has received far less attention than in SAE Level-3 road automation. This study focuses on the reaction phase of emergency takeover, defined as the interval from anomaly onset to the train operator’s first control action. We propose a conditional two-stage evaluation framework that jointly assesses event recognition and control execution quality. A simulation-based experiment was conducted to replicate GoA2 operating conditions under controlled emergency scenarios. Three indicators were extracted: (i) event recognition accuracy derived from eye-tracking and retrospective recall, (ii) takeover reaction time, and (iii) initial action accuracy reflecting compliance with operational speed or braking limits. An attention-enhanced multilayer perceptron (MLP) was developed to dynamically weight input features and improve interpretability. The proposed model achieved stable subject-wise performance, with an average accuracy of 0.86 and a macro F1-score of 0.857. These results support the feasibility of interpretable learning-based evaluation for human-in-the-loop safety assessment and provide practical implications for improving operator readiness monitoring and operational safety management in semi-automated metro systems. Full article

This work presents TransLowNet, an online framework for video anomaly detection, classification, and spatial localization. The system segments incoming video streams into clips processed by an X3D-S feature extractor to obtain spatio-temporal representations, which are analyzed by dedicated modules for anomaly detection and recognition, while a MoG2-based stage estimates the spatial regions of anomalous activity. Evaluated on the UCF-Crime dataset, TransLowNet achieved 80.0% AUC, 54.5% accuracy, and 20.3% mAP@0.5, offering an efficient and interpretable approach for continuous video surveillance. Full article

Human pose classification, along with related tasks such as action recognition, is a crucial area in deep learning due to its wide range of applications in assisting human activities. Despite significant progress, it remains a challenging problem because of high inter-class similarity, dataset noise, and the large variability in human poses. In this paper, we propose a lightweight yet highly effective modular attention-based architecture for human pose classification, built upon a Swin Transformer backbone for robust multi-scale feature extraction. The proposed design integrates the Spatial Attention module, the Context-Aware Channel Attention Module, and a novel Dual Weighted Cross Attention module, enabling effective fusion of spatial and channel-wise cues. Additionally, explainable AI techniques are employed to improve the reliability and interpretability of the model. We train and evaluate our approach on two distinct datasets: Yoga-82 (in both main-class and subclass configurations) and Stanford 40 Actions. Experimental results show that our model outperforms state-of-the-art baselines across accuracy, precision, recall, F1-score, and mean average precision, while maintaining an extremely low parameter count of only 0.79 million. Specifically, our method achieves accuracies of 90.40% and 87.44% for the 6-class and 20-class Yoga-82 configurations, respectively, and 94.28% for the Stanford 40 Actions dataset. Full article

Near misses—clinical events that could have resulted in patient harm but did not—are increasingly recognized as critical yet underutilized sources of insight in surgical quality improvement. In thoracic surgery, where procedures are physiologically demanding and care pathways are highly interdependent, near misses frequently precede major complications and expose latent system vulnerabilities rather than isolated technical errors. A structured narrative review methodology was employed, including a targeted literature search of major biomedical databases and thematic synthesis of relevant studies. This narrative review synthesizes evidence from patient safety science, surgical quality literature, and thoracic surgery—specific outcomes research to examine how near misses can be systematically leveraged to improve care. We discuss the transition from individual-centered explanations of adverse events to system-based models that emphasize human factors, communication, escalation pathways, and organizational culture. Particular attention is given to contemporary quality frameworks such as failure to rescue and textbook outcome, which highlight the importance of early recognition, coordinated response, and recovery from complications rather than complication avoidance alone. We further explore the central role of psychological safety and leadership behaviors in enabling meaningful learning from near misses. By reframing near misses as actionable data rather than anecdotal “close calls,” quality improvement emerges as a core professional responsibility in thoracic surgery. We conclude that excellence in thoracic surgery should be defined not by the absence of complications, but by the capacity of surgical systems to learn, adapt, and prevent future harm. Full article

The growing recognition of the need for systemic approaches to urban climate transitions calls for comprehensive monitoring and evaluation frameworks that extend beyond Greenhouse Gas emissions to include measures that impact human behaviours, as well as process indicators that enable timely adjustments to climate action pathways. The extant literature offers limited insights into EU regional patterns and differences in the assessment of actions toward climate neutrality. This study examines indicators of process and co-benefit selected for the pilot projects of cities that aim to be climate neutral by 2030 in 21 European countries, and it aligns the indicators set utilised in the NetZeroCities pilot projects with the international frameworks of United Nations Sustainable Development Goals and New European Bauhaus. The findings highlight the relevance accorded by cities in all European regions to learning, awareness and participation, and inform on potential regional differences in the prioritisation of specific sustainability goals across North, West, South and East Europe. The methodology contributes to the sustainability science and transdisciplinary literature by aligning cities’ indicators with the SDG and NEB frameworks. Findings suggest that the EU focus on engagement, participation and social learning is being taken up by cities; furthermore, they contribute insights for a potentially more geographically and culturally aware design of European urban climate transitions. Full article

As humanity continues to strive for extraplanetary exploration, which is quickly gaining marked governmental and industrial support and recognition, there are still substantial detriments to astronaut health during long-duration spaceflight (i.e., muscle atrophy) that must be addressed. The effects of long-duration spaceflight on muscle architecture, morphology, and function have been well documented since the Apollo and Space Shuttle Programs. Countermeasures focused on resistance or aerobic training, such as the Advanced Resistive Exercise Device, Multi-modal Exercise Device, flywheel exercise, and aerobic exercise on a mounted treadmill and/or a cycle ergometer with vibration isolation system, have been assessed to combat the functional and mechanical losses in muscle while astronauts are in low Earth orbit. However, a lesser-understood countermeasure to muscle atrophy during spaceflight is neuromuscular electrical muscle stimulation (NMES). Although utilization in spaceflight is limited, ground-based research on NMES in diseased or injured populations demonstrates its effectiveness as a promoter of muscle anabolism and growth. The previous literature has suggested the use of electrical muscle stimulation as a low-effort modality of exercise for astronauts, which could effectively enhance astronaut health and contribute to mission success. The efficacy and mechanisms of action of using NMES to attenuate atrophy in astronauts will be discussed in this review. Full article

Event-based sensors provide sparse, motion-centric measurements that can reduce data bandwidth and enable always-on perception on resource-constrained edge devices. This paper presents an event-based machine vision framework for smart-home AIoT that couples a Dynamic Vision Sensor (DVS) with compute-efficient algorithms for (i) human/object detection, (ii) 2D human pose estimation, (iii) hand posture recognition for human–machine interfaces. The main methodological contributions are timestamp-based, polarity-agnostic recency encoding that preserves moving-edge structure while suppressing static background, and task-specific network optimizations (architectural reduction and mixed-bit quantization) tailored to sparse event images. With a fixed downstream network, the recency encoding improves action recognition accuracy over temporal accumulation (0.908 vs. 0.896). In a 24 h indoor monitoring experiment (640 × 480), the raw DVS stream is about 30× smaller than conventional CMOS video and remains about 5× smaller after standard compression. For human detection, the optimized event processing reduces computation from 5.8 G to 81 M FLOPs and runtime from 172 ms to 15 ms (more than 11× speed-up). For pose estimation, a pruned HRNet reduces model size from 127 MB to 19 MB and inference time from 70 ms to 6 ms on an NVIDIA Titan X while maintaining a comparable accuracy (mAP from 0.95 to 0.94) on MS COCO 2017 using synthetic event streams generated by an event simulator. For hand posture recognition, a compact CNN achieves 99.19% recall and 0.0926% FAR with 14.31 ms latency on a single i5-4590 CPU core using 10-frame sequence voting. These results indicate that event-based sensing combined with lightweight inference is a practical approach to privacy-friendly, real-time perception under strict edge constraints. Full article

Human interaction with manipulable objects relies heavily on the ability to perceive and execute grasping actions, yet it remains unclear whether the semantics of these actions are processed without conscious awareness. While previous work has identified bottom-up influences on grasp recognition, direct evidence for subliminal semantic processing of grasping actions is limited. Grounded in embodied cognition theory—which posits overlapping neural mechanisms for action language and action execution—the present study examined whether grasp-related verbs can elicit subliminal priming effects on grasping-action recognition. Using a masked priming paradigm, participants classified objects requiring either precision or power grasps while subliminal Chinese action verbs served as primes. Behavioral measures revealed faster responses for semantically congruent cue–target pairs. ERP analyses further demonstrated congruency effects in the N400 and P600 components, reflecting semantic integration and conflict monitoring, as well as modulation of the P300 associated with action-related evaluation. Both grasp types showed evidence of unconscious semantic processing, though precision- and power-grasping actions produced distinct neural patterns. These findings provide direct experimental support for subthreshold semantic activation of grasping actions and confirm the viewpoint of action-language-embodied processing. The study advances the theoretical understanding of unconscious-action semantics and offers a framework for investigating how manipulative-action meaning is accessed below the threshold of awareness. Full article