Search Results (2,043)

Falls are a major contributor to morbidity and mortality among older adults, and timely fall detection can help reduce the severity of fall-related outcomes. Wearable inertial measurement unit (IMU) sensors offer a promising solution for fall detection; however, many existing approaches rely on multiple sensing locations and computationally intensive models, which can limit their practicality for resource-constrained wearable devices. This study proposes a knowledge distillation framework for efficient wrist-based fall detection using the publicly available University of Málaga fall detection dataset (UMAFall), a benchmark dataset for human activity recognition and fall detection. Although UMAFall was not collected from older adults, it provides a useful public benchmark for evaluating IMU-based fall detection methods. Knowledge distillation was implemented using a teacher–student framework, in which a high-capacity teacher model trained with IMU data from four body locations (waist, wrist, ankle, and chest) provided soft targets for guiding a compact wrist-only CNN student model. In a held-out test evaluation using Subjects 2 and 5, the teacher model achieved 97.6% accuracy and an F1 score of 96.7%, with approximately 1.3 million trainable parameters. The independently trained wrist-based CNN achieved 90.2% accuracy and an F1 score of 87.1%. After applying knowledge distillation, the student model improved to 95.1% accuracy and an F1 score of 93.3% while maintaining the same lightweight architecture. A supplementary leave-one-subject-out analysis showed slightly higher and more stable AUC for KD-CNN than the independently trained CNN (0.96 ± 0.03 vs. 0.94 ± 0.07). These findings suggest that knowledge distillation can improve wrist-only fall detection in this feasibility evaluation, but further validation using older adults and real-world smartwatch data is needed. Full article

The traditional monitoring of forest musk deer behavior primarily relies on direct human observation or the post hoc playback analysis of ordinary surveillance videos. This approach is not only time-consuming and labor-intensive but also highly subjective, easily leading to missing or misjudged critical behavioral information. Moreover, it is difficult to achieve real-time monitoring and anomaly warning. These limitations severely constrain the efficiency of the large-scale artificial breeding of forest musk deer and the effective advancement of wild population conservation. Thus, this study proposes a forest musk deer behavioral recognition method based on an improved YOLOv8-Pose. A forest musk deer behavior image dataset covering four typical behaviors was constructed, and 18 keypoints were systematically annotated. This study designs a Dilated Spatial Pyramid Pooling-Fast (DILATED-SPPF) module and a Multi-scale Depthwise Separable Context Mixer (MDSC-Mixer) module, and integrates them into YOLOv8-Pose. Experimental results show that the improved model outperforms the original YOLOv8-Pose and comparison models such as YOLOv11/v12-Pose on key metrics of object detection (Box-mAP50 0.929, Box-mAP50-95 0.814) and pose estimation (Pose-mAP50 0.879, Pose-mAP50-95 0.565). This study further develops a visual interactive interface that intuitively presents detection results and skeleton structures. This work provides a high-precision, low-cost automated behavior analysis tool for the artificial breeding and wild conservation of forest musk deer with significant application value for enhancing the intelligence level of endangered species protection. Full article

This article examines how justice institutions produce and reproduce gender-based violence against women through the invisibilization of moral violence, with particular attention to their spatial dimensions. Drawing on the concept of juridical–patriarchal habitus, the study conceptualizes justice institutions not only as sites of legal action but as spatial formations that shape the visibility, recognition, and adjudication of harm. Using a feminist ethnographic approach, the article analyzes two cases of gender-based violence documented in 2020 in the municipality of Querétaro, Mexico. The findings demonstrate how movement into legal and institutional spaces transforms lived experiences of violence, as procedural requirements, evidentiary expectations, and institutional interactions operate as spatial filters that render certain forms of harm visible while obscuring others. In this process, justice actors construct and reproduce gendered stereotypes about what counts as violence, simultaneously positioning women as victims and subjecting them to processes of revictimization. By conceptualizing the invisibility of moral violence as a spatially mediated process, the article contributes to debates in legal and feminist geography, highlighting how institutional spaces not only respond to gender-based violence but actively participate in its production and concealment. Full article

Wearable surface electromyography (sEMG)-based gesture recognition enables intuitive human–machine interaction, but practical deployment is often limited by hardware constraints, model complexity, and inter-subject variability. In this study, we developed a high-performance wrist-worn sEMG acquisition system and a lightweight neural network, ThinNet, to achieve efficient and accurate gesture recognition. The wristband features a ring-shaped differential electrode array and embedded filtering modules, achieving a signal-to-noise ratio (SNR) of 66.96 dB, significantly higher than commercial devices. Using data from 100 participants performing six gestures, ThinNet achieved 90.47% inter-subject accuracy, with peak accuracy reaching 96.80% under a three-tier buffered decision strategy. Systematic analysis demonstrated that the model maintains high performance with only 40% fine-tuning data, indicating excellent data efficiency. Importantly, the framework supports scalability across additional users and practical deployment in real-world applications. These results highlight the combined effectiveness of hardware optimization and algorithm design in advancing wearable sEMG-based gesture recognition systems. Full article

Unmanned aerial vehicles (UAVs) have wide application prospects in disaster search and rescue, ecological monitoring and environmental inspection tasks, where target search is a key link to realize autonomous task execution. UAVs often face challenges related to limited onboard computational resources and inefficient environmental coverage when used for target search. To address these issues, this paper proposes an autonomous search method for UAVs based on combined lightweight target detection and coverage path planning. In this method, the target search task was decomposed into two core parts: target recognition and path planning. Firstly, in terms of target recognition, the YOLOv8n model was subjected to channel pruning and INT8 quantization to reduce its computational complexity, while HSV space data augmentation was incorporated to enhance recognition robustness in complex environments. Secondly, path planning was formulated as a dual-layer task comprising “spatial coverage + target confirmation.” A grid-based search environment model was constructed, and a coverage path planning strategy was put forward that integrated breadth-first search (BFS) with local greedy optimization to achieve efficient traversal of predefined search areas. Simultaneously, the A* algorithm was employed for path backtracking to cover omitted regions. Finally, a simulation platform for UAV target search was built to validate the recognition performance and search efficiency of the proposed method. The experimental results demonstrated that the proposed method significantly improved the UAV target search efficiency and reduced the path redundancy while ensuring the recognition accuracy, thereby offering an effective solution for autonomous UAV search on resource-constrained embedded platforms. Full article

Cross-domain emotion recognition based on electroencephalogram (EEG) is a challenging task, as EEG signals collected from different subjects or at different moments exhibit significant differences in distribution. How to enable deep learning model to learn the common feature space and reduce the distribution differences between the source and target domains is an important research direction. For this problem, we propose a Supervised Contrastive Variational AutoEncoder Network (SCVAE-Net), which possesses enhanced abilities for extracting consistent features across source and target domains, thereby improving cross-domain EEG emotion recognition performance. Specifically, this method utilizes the reconstruction mechanism and latent space probabilization of VAE to obtain intermediate features that are more consistent and transferable. Furthermore, the maximum mean discrepancy loss is employed to further reduce the distribution discrepancy of these features. To alleviate the degradation of discriminative ability during domain alignment, we introduce multi-view supervised contrastive learning in multi-source domains to enhance the intra-class consistency and inter-class separability of latent features. Under the cross-subject and cross-session settings, SCVAE-Net achieves accuracies of 95.01%/96.84% on SEED and 74.94%/79.44% on SEED-IV, respectively. These experimental results demonstrate the effectiveness of the proposed method in cross-domain EEG emotion recognition. Full article

Traditional taste evaluation relies heavily on manual sensory analysis, which is highly subjective and inefficient with poor cross-individual generalization, limiting its application in industrial flavor detection. To achieve accurate cross-subject taste recognition, this paper proposes an electroencephalogram (EEG) classification method based on a meta-learning wavelet graph convolutional neural network (ML-WGCNet) under sweet- and bitter-taste stimuli. Sucrose (sweetness) and quinine (bitterness) were used as stimulation sources, each prepared at six concentration gradients, including a water control. EEG signals were detected from 20 subjects. First, the Morlet wavelet transform was applied to decompose the EEG signals in the time–frequency domain, extracting the maximum and average energy values from five frequency bands as core features. A graph structure was then constructed using electrodes as nodes and Pearson correlation coefficients between electrodes as edge weights. A lightweight graph convolutional neural network (GCN) is employed to model spatial correlations among brain regions. Finally, by integrating a meta-learning framework and adopting leave-one-subject-out cross-validation, the model can rapidly adapt to new subjects. The experimental results show that the proposed method achieves average accuracies of 76.03% and 77.01% in cross-subject classification of sweet and bitter tastes, respectively. The corresponding precision values are 79.94% and 79.53%, the recall values are 75.77% and 78.51%, and the F1-scores are 78.24% and 78.08%, respectively, demonstrating that the proposed model significantly outperforms existing mainstream EEG classification methods. Full article

Wearable inertial sensors produce multi-axis motion signals with rich spatial and temporal structure. Existing deep-learning pipelines for human activity recognition (HAR) rarely tackle three issues jointly: explicit modeling of the body-part grouping of multi-location inertial channels, bidirectional temporal modeling at linear-time cost, and dynamic, time-varying attention for non-stationary motion. We aim to close these three gaps within a single architecture. To this end we propose Dynamic-Attentive Selective Mamba (DASM), which combines three components: Group-Aware Convolutions (GroupConv) for body-part-aware local features, a Bidirectional Mamba (BiMamba) module for linear-time forward and backward temporal context, and a Dynamic CBAM (DCBAM) that produces per-timestep channel and spatial attention for non-stationary windows. On the UCI Daily and Sports Activities dataset (19 classes, 8 subjects), under stratified segment-level 5-fold cross-validation (3 seeds, 15 runs/model), DASM reaches 99.89% accuracy and F1, a 0.11% gain over CNN-BiGRU-CBAM and 0.50% over Multi-STMT; under leave-one-subject-out (LOSO), it reaches 89.34%, 1.69% above the strongest baseline. The 10.55% drop under LOSO shows that segment-level results overestimate cross-subject generalization. Ablations show small but statistically detectable gains (Cohen’s $d\in [0.4,0.7]$ per module, $d\ge 1.5$ full-vs-baseline). We therefore position the contribution as a structured architecture within a near-saturated benchmark; broader deployment claims require multi-dataset subject-independent validation. Full article

This paper presents a robust and efficient mmWave radar-based human activity recognition (HAR) framework optimized for practical real-time indoor deployment. Addressing computational inefficiencies and limited recognition scopes in existing systems, the framework introduces two core contributions: Multi-class Spatio-Temporal Network (MuST-Net), a lightweight, multi-class network, and an online detection process for enhanced temporal stability. MuST-Net utilizes a hybrid 2D convolutional neural network and temporal convolutional network architecture to recognize seven distinct classes, significantly broadening the system’s recognition repertoire. The online detection process implements a novel sliding-window post-processing chain that employs an activity-buffering mechanism, which maintains temporal continuity and effectively suppresses spurious detections at activity boundaries. Experimental results demonstrate the superior performance of our unified framework, attaining over 98.6% accuracy for multi-class classification by MuST-Net and achieving at least 97% accuracy for activity detection and a crucial 100% recall for fall detection. Robustness is validated across three distinct indoor environments and nine subjects—with two of the three sites entirely unseen during training—confirming strong generalization under installation, environment, and subject variations. Full article

This study evaluates the mechanical properties of Hinoki (Chamaecyparis obtusa) from Japan to determine reliable design values for its application as structural dimension lumber species in the United States. A comprehensive experimental program was conducted on 1464 (approximately 240 per grade/size) dimension lumber in-grade specimens sourced from prominent Hinoki-growing regions of Japan. These specimens were tested in bending, compression perpendicular to the grain, and horizontal shear. Tests were conducted, and the results were subjected to statistical analysis and adjustment factors to determine base reference values in accordance with ASTM International standards. The four-point bending tests showed moderate numerical variation across growing regions; however, one-way ANOVA confirmed no statistically significant regional effect on MOR or MOE. Compression parallel to grain and tensile strength were estimated from the MOR values using empirical relationships per ASTM D1990. The base design values after adjustments for 15% moisture content, specimen size, and volume effects fall within the expected range for high-quality structural species and support the acceptability of Hinoki as a load-carrying wood species. The results constitute the first complete, statistically verified dataset for Hinoki, and provide a basis for its use in wood design specifications such as the National Design Specification (NDS) for Wood Construction (NDS). Wider recognition of Hinoki as a viable structural species could expand its commercial use and support sustainable forest management practices in Japan. Full article

Faced with the challenges of cross-cultural communication of public opinion in emergency events, traditional sentiment recognition methods struggle to accurately capture the complex semantics under multi-lingual and multi-symbol systems. This paper takes the powerful 7.7-magnitude earthquake that struck Myanmar in 2025 as a case study. It constructs a multi-dimensional public opinion annotation framework that integrates four types of semantic information—time, space, subject, and sentiment—by extracting data from multi-source textual materials, including social media, news reports, and government announcements. Building on this foundation, we design an improved Model-Agnostic Meta-Learning (MAML) model that incorporates cultural features to enhance sentiment recognition performance in low-resource cross-linguistic scenarios. Experimental results show that the model outperforms traditional methods in terms of sentiment classification accuracy, cultural semantic deviation rate and metaphor recognition ability. Furthermore, the research reveals the coupling mechanism of public opinion communication of “cultural modulation–agenda game”, and clarifies the influence paths and weight distributions among multiple subjects. The research results provide theoretical support and practical paths for improving the governance capacity of cross-border public opinion in emergency events and the construction of multilingual monitoring models. Full article

Background: Neuroendocrine neoplasms are frequently diagnosed after the detection of liver metastases, often when the primary tumor remains occult. Accurate non-invasive differentiation of neuroendocrine liver metastases (NELMs) from other focal hepatic lesions is therefore crucial. This study aimed to characterize the magnetic resonance imaging (MRI) features of NELMs using hepatocyte-specific contrast agents and to identify a potential radiologic “signature” that may suggest a neuroendocrine origin. Methods: This retrospective study included three cohorts: patients with histologically confirmed NELMs (n = 51; 146 lesions), patients with colorectal cancer liver metastases (n = 18; 46 lesions), and patients with benign hepatic hemangiomas (n = 28; 51 lesions). All subjects underwent standardized liver MRI with Gd-EOB-DTPA. Lesions were evaluated for size, diffusion-weighted imaging characteristics, apparent diffusion coefficient values, arterial-phase enhancement, T2-weighted signal, hepatobiliary-phase appearance, and hemorrhagic components. Statistical analyses included univariate and multivariate testing and receiver operating characteristic curve analysis. Results: NELMs commonly demonstrated arterial hyperenhancement, diffusion restriction, and variable T2 and hepatobiliary-phase signal heterogeneity. Compared with colorectal metastases and hemangiomas, NELMs showed distinctive patterns, particularly higher rates of hepatobiliary-phase heterogeneity and arterial enhancement. Lesion size, ADC metrics, T2 heterogeneity, and hemorrhage were significant discriminators. Conclusions: Hepatocyte-specific MRI enables identification of characteristic imaging features of NELMs. An integrated assessment of morphologic, diffusion, and hepatobiliary-phase findings may facilitate early recognition of neuroendocrine metastases, even when the primary tumor is unknown, improving diagnostic confidence and clinical management. Full article

Improving animal welfare through standardized management protocols remains a key challenge in intensive pig production. Auditory enrichment, such as music, represents a promising non-invasive strategy, yet its application is often empirical, lacking mechanistic understanding and objective assessment tools. This study investigated growing pigs’ active preferences for structured musical parameters to establish a precision auditory enrichment framework. Seventy-two crossbred pigs were subjected to a free-choice paradigm under simulated farm conditions, with a 2 × 2 factorial design manipulating musical stimulus type (a guqin string piece vs. a Mozart wind excerpt) and tempo (fast: 200 bpm vs. slow: 65 bpm) was continuously quantified using an enhanced YOLOv11-based automated recognition system (mean average precision mAP₅₀: 90.5% ± 1.5%). Results revealed highly parameter-dependent effects: the slow-tempo GS stimulus and the fast-tempo MF stimulus significantly prolonged occupancy time (p < 0.01) and elicited distinct profiles. The GS stimulus promoted a calm, investigative state, increasing lying, exploration, and drinking time (p < 0.05), while the MF stimulus stimulated an active playful state, characterized by increased walking and playing (p < 0.05). Other musical combinations showed negligible effects, whereas noise exposure consistently triggered stress-related responses. This study establishes an integrated “parametric design → automated assessment → specific output” methodology for precision auditory enrichment, providing an empirical basis for evidence-based acoustic protocols in commercial pig production. Full article

Surface electromyography (sEMG) enables non-invasive acquisition of neuromuscular activity and has shown strong potential for motion intention recognition in human–machine interaction. However, achieving reliable and real-time decoding remains critical for interactive upper-limb assistance. This study presents a structured sEMG-based framework for motion intention recognition in upper-limb assistance tasks, integrating multi-channel acquisition, standardized preprocessing, time-domain feature extraction, and supervised learning. sEMG signals from four representative motions were collected, and eight time-domain features were extracted from denoised and segmented signal windows. A compact feature subset was identified through systematic evaluation. Five classifiers were benchmarked under consistent validation conditions, with Random Forest achieving the best performance and further optimized via K-fold cross-validation. The proposed method achieved an average intra-subject accuracy of 95.23% across eight subjects and 95.72% in online interactive validation. These results demonstrate that time-domain feature fusion combined with ensemble learning provides robust and efficient motion discrimination, highlighting its potential for real-time assistive and rehabilitation applications. Full article

Objective pain assessment remains a significant challenge in clinical and research settings due to the subjective nature of self-reported measures. Physiological signals, particularly electrodermal activity (EDA), have emerged as promising indicators of autonomic responses associated with pain. Although recent advances in deep learning have improved the modelling of complex biosignals, many existing approaches remain computationally demanding, limiting their applicability for real-time monitoring in wearable and embedded systems. This paper proposes a fully convolutional network (FCN) for automated pain recognition using EDA signals. The proposed model is designed to efficiently capture temporal patterns in physiological data while maintaining low computational complexity. The approach is evaluated on the AI4Pain dataset for three-class pain classification (No Pain, Low Pain, High Pain). Experimental results show that the proposed FCN achieves an accuracy of 79.23% in offline evaluation. Furthermore, the model enables real-time inference with a latency of 0.47 ms, achieving 73.14% accuracy during real-time operation. These results demonstrate that convolutional architectures can provide an effective balance between predictive performance and computational efficiency, supporting the development of real-time physiological pain monitoring systems using wearable sensing technologies. Full article