Aerobics posture recognition based on neural network and sensors

Ergonomic investigations on novel dynamic postural estimator using blaze pose and transfer learning

The aim is to develop a computer-based assessment model for novel dynamic postural evaluation using RULA. The present study proposed a camera-based, three-dimensional (3D) dynamic human pose estimation model using 'BlazePose' with a data set of 50,000 action-level-based images. The model was investigated using the Deep Neural Network (DNN) and Transfer Learning (TL) approach. The model has been trained to evaluate the posture with high accuracy, precision, and recall for each output prediction class. The model can quickly analyse the ergonomics of dynamic posture online and offline with a promising accuracy of 94.12%. A novel dynamic postural estimator using blaze pose and transfer learning is proposed and assessed for accuracy. The model is subjected to a constant muscle loading factor and foot support score that could evaluate one person with good image clarity at a time.Practitioner summary: A detailed investigation of dynamic work postures is largely missing in the literature. Experimental analysis has been performed using transfer learning, BlazePose, and RULA action levels. An overall accuracy of 94.12% is achieved for dynamic postural assessment.

Visual Analysis of College Sports Performance Based on Multimodal Knowledge Graph Optimization Neural Network

In this paper, through data analysis of multimodal knowledge graph optimized neural network and visual analysis of college students’ sports performance, we use huge graph, a graph database supporting distributed storage, to store domain knowledge in the form of the knowledge graph, use Spring Boot to build a server-side framework, use Vue framework combined with vis.js to visualize relational network graphs, and design and implement a knowledge-oriented. This paper proposes a visual analytics system based on the theory of visual analytics. Based on the idea of visual analytics, this paper presents a visual analytics framework combining predictive models. This framework combines the automated analysis capability of predictive models with interactive visualization as a new idea to explore the visual analysis of student behavior and performance changes. Using relevant predictive algorithms in machine learning, corresponding models are built to refine the importance of features for visual analysis and correlate behavioral data with achievement data. In this process, multiple prediction algorithms are used to build prediction models. The model effects are analyzed and compared to select the optimal model for use in the visual analytics framework. The graphical analytic view is integrated. EduRedar, an optical analytical system for sports data based on the performance prediction model, is designed and implemented to support multidimensional and multiangle data analysis and visualize the changes in college students’ sports and performance based on accurate campus exercise data.