Search

Given the limitations of traditional methods in automatic feature extraction, the study aims to improve the accuracy of posture recognition in adolescent running training through deep learning techniques. This study first constructed a human pose motion model to capture complex pose changes during the motion process. Furthermore, an algorithm framework combining convolutional neural networks and long short-term memory networks was proposed, and optimized by integrating attention modules to enhance the model’s ability to capture key action details and improve recognition accuracy. The outcomes indicated that the recognition accuracy of the raw data processed using the convolutional neural network algorithm is 0.93, which is improved to 0.96 after preprocessing, while the accuracy of the long-short-term memory network algorithm is 0.91 on the raw data and 0.95 after preprocessing. The Inception combined with long-short-term memory network algorithm optimised by incorporating the attention module has the highest accuracy of 0.98 on the preprocessed data, while that on the 0.95 on the raw data, and 1.0 on specific actions such as running and riding. It can be found that the attention module significantly improves the recognition accuracy of the algorithm and its ability to recognise complex actions. This study not only improves the way that teenagers train to run, but it also creates new opportunities for the use of deep learning methods in the context of sports-assisted training.

Manual laborers are often at an increased risk for work-related musculoskeletal disorders (WMSDs) due to improper work postures or the lifting of excessively heavy objects. Therefore, conducting an effective ergonomic assessment of workers is crucial for enhancing productivity and minimizing the occurrence of WMSDs. The Ergonomic Posture Risk Assessment (EPRA) is a widely used method for this assessment. However, traditional EPRA methods rely on human or sensor input, leading to subjective bias, instability, and reduced accuracy. This study addresses these issues by proposing an objective machine-learning approach. It employs a non-intrusive computer vision technique for posture capture, enabling rapid analysis of the worker’s activities through Random Forest analysis. The dataset for risk assessment is generated from the worker’s skeletal joint posture data, collected using Movenet Thunder in conjunction with an inertial motion capture device and the Rapid Entire Body Assessment (REBA) standard. The Particle Swarm Optimization Random Forest (PSO-RF) model is then utilized to predict risk scores for various postures, incorporating limb length ratios to tackle challenges associated with observing torsional joints. The model’s effectiveness in detecting poor posture is subsequently evaluated. The findings indicate that the PSO-RF model successfully identifies poor postures and computes the corresponding REBA scores with 89% accuracy, 93% precision, 91% F1 score, 89% recall, and a kappa value of 82%. This research demonstrates that the machine learning approach, utilizing computer vision and Random Forest, can effectively conduct EPRA to prevent musculoskeletal injuries, providing a data-driven and accurate method for enhancing workplace safety and health.

The emotional context of a given environment can profoundly influence an individual’s feelings and responses. Nonetheless, current emotion recognition methodologies primarily concentrate on analyzing the target subject’s features and inadequately integrate these features with the contextual information of the scene. To tackle this challenge, we introduce a novel emotion recognition model that employs three independent and prioritized deep convolutional neural networks, alongside a feature fusion enhancement technique, to effectively merge facial information, body pose information, and subject features within the overall image. By amalgamating the performance of object detection models and deep convolutional network models, our framework capitalizes on the strengths of multiple approaches. Experiments with the Emotic dataset validate that our proposed model is technically innovative and surpasses existing methods and benchmark models in terms of feature fusion performance. Moreover, our evaluation of the proposed method on the Emotic dataset underscores the significance of environmental contextual information in shaping human emotions.

The current researches trend to adopt a low-resolution hot spot map to restore the original high-resolution representation to save computing cost, resulting in unsatisfactory detection performance, especially in human body recognition with a highly complex background. Aiming at this problem, we proposed a model of parallel connection of multiple sub-networks with different resolution levels on a high-resolution main network. It can maintain the network structure of a high-resolution hot spot map in the whole operation process. By using this structure in the human key point vector field network, the accuracy of human posture recognition has been improved with high-speed operation. To validate the proposed model’s effectiveness, two common benchmark data sets of COCO key point data set and MPII human posture data set are used for evaluation. Experimental results show that our network achieves the accuracy of 72.3% AP and 92.2% AP in the two data sets, respectively, which is 3%-4% higher than those of the existing mainstream researches. In our test, only the accuracy of backbone’s SimpleBaseline with ResNet-152 is close to ours, yet our network realized a much lower computing cost.