Deep Learning-Based Worker Posture Classification for Ergonomic Risk Evaluation in Manufacturing

Vision-Based Progress Compliance and Worker Health Monitoring in Concrete Pouring and Vibration

This paper proposes a vision-based framework named concrete progress and concrete health monitoring (CPCHM) for automated compliance supervision and health risk assessment during concrete pouring and vibration operations. The framework integrates YOLOv8-pose for worker posture estimation and YOLOv8-detection for equipment identification, achieving average accuracies of 92.8% and 99.5%, respectively. By fusing posture and equipment features, a support vector machine classifier distinguishes between pouring and vibration operations with 90.8% accuracy and an F1-score of 90.3%. Further, a spatiotemporal graph convolutional network is employed to model elbow joint dynamics and assess musculoskeletal risks, reaching a behavioral classification accuracy of 89.6%. To address occlusion and multiworker collaboration, CPCHM introduces a distance-based operator identification method and an adaptive region-of-interest inference mechanism, maintaining stable keypoint tracking and continuous elbow-angle estimation even under partial visibility. The framework is embedded on a Jetson nano edge device, which automatically triggers an acoustic buzzer alert when pouring durations exceed 90 min or vibration times fall outside the 5–15 s standard. CPCHM provides a compact, sensor-free, and scalable solution for integrating progress compliance monitoring and ergonomic health assessment, enabling intelligent and real-time supervision in dynamic concrete construction environments.

Hybrid deep learning with attention mechanism for monitoring and classifying physical exercise postures using sensor data.

Accurate detection and classification of different physical exercise postures play a crucial role in monitoring fitness levels, preventing injuries, and personalizing workout routines. Traditional approaches using handcrafted feature extraction and shallow classifiers often suffer from low generalization and limited scalability. To address these limitations, this paper explores advanced deep learning models such as convolutional neural networks (CNN), recurrent neural networks (RNN), capsule networks (CapsNet), gated recurrent units (GRU), and multilayer perceptron (MLP), along with hybrid architectures, to accurately classify exercise quality categories. The models were trained on sensor data collected from smart devices, capturing motion dynamics and postural changes. Among the evaluated models, Capsule Network achieved the highest accuracy of 0.99, followed by hybrid MLP with CNN and transformer model with 0.97, demonstrating superior capability in recognizing complex activity patterns. The results show that deep learning models can effectively identify different exercise postures with high precision and recall, paving the way for intelligent fitness monitoring systems. Future work includes optimizing the models for real-time applications and extending the system to include a wider range of physical activities.

Comprehensive Analysis of Complex Yoga Posture Classification Model Based on Diversify Input Environment and Prediction of Correct Yoga Posture

Yoga Posture Recognition and Classification Systems: A Comprehensive Review of Multi-Modal Approaches and Applications

Purpose: This study aims to critically review hybrid yoga posture recognition systems in order to propose an integrated multi-layer hybrid framework for accurate, real-time posture assessment in healthcare and rehabilitation contexts. Design / Methodology / Approach: Yoga posture recognition methods were taxonomically analysed using a four-dimensional framework, including input modality, feature representation, learning paradigms (SVM, CNN, LSTM), and system-level integration, with multi-metric performance evaluation. Research Limitation: The proposed hybrid framework is conceptually validated but has not yet been empirically tested in a real-world clinical cohort, representing a direction for future experimental work. Findings: Hybrid deep learning systems have the best accuracy (94%- 97%), although all solutions trade off accuracy, computational cost, and practical generalizability. Practical Implication: The hybrid CNN-LSTM system developed will support real-time posture monitoring and provide corrective feedback for remote rehabilitation, fitness coaching, and edge-deployable healthcare. Social Implication: These applications help reduce healthcare inequalities, lower treatment costs, and improve quality of life for diverse populations worldwide. Originality/Value: This integrated architecture is evaluated using a comprehensive multi-metric assessment protocol for recognising yoga postures.

A Smart Health Evaluation System and Optimization Mechanism for Sports Actions Incorporating BigGAN

To meet the growing demand for sports motion recognition in training assistance, rehabilitation assessment, and intelligent monitoring, this study developed an auxiliary action-recognition evaluation framework incorporating a Big Generative Adversarial Network (BigGAN)-based data augmentation mechanism. An experimental subset was first constructed from representative sports actions in the Nanyang Technological University RGB+D120 (NTU RGB+D120) dataset, including running, jumping, throwing, and gymnastics movements. BigGAN was subsequently employed to generate augmented training samples, while truncation strategies and class-embedding mechanisms were introduced to increase pose variability and visual diversity. The generated samples were used exclusively during model training, whereas only real samples were retained in the validation and test sets to ensure an unbiased performance evaluation. The quality of the generated data was assessed using Fréchet Inception Distance (FID), Inception Score (IS), Learned Perceptual Image Patch Similarity (LPIPS), nearest-neighbor retrieval, and truncation-threshold sensitivity analysis. Samples exhibiting semantic inconsistencies, structural distortions, or near-duplicate characteristics were removed through quality control procedures. Experimental results showed that the proposed framework achieved an accuracy of 89.8%, a recall of 89.2%, and an F1-score of 89.5% on the test set. The generated samples yielded an average FID of 38.80, an average LPIPS value of 0.331, and a nearest-neighbor duplication rate of 3.5%. In addition, the BigGAN-enhanced model demonstrated more consistent classification performance across different sports categories. Running achieved the highest recognition accuracy, whereas throwing remained the most challenging category. The augmentation strategy improved the model's robustness to intra-class variability in several action categories. Nevertheless, the proposed framework provides only auxiliary support for action recognition and cannot replace professional assessments conducted by coaches, clinical practitioners, or biomechanical analysis systems. These findings offer a reproducible foundation for data augmentation, action classification, and intelligent feedback in sports motion monitoring applications.

Sex estimation from hand-wrist radiographic images: an artificial intelligence approach.