Research and Analysis of Sport Medical Data Processing Algorithms Based on Deep Learning and Internet of Things

Abstract

With the development of computer and information technology, more and more data and image information are generated in medical field. Sports medicine, as an important branch of medical cause, is responsible for ensuring national sports safety and rehabilitation after injury. How to use a large number of sports medical data and cases to accurately analyze and mine useful data and information has become an important research direction of sports medical data processing and mining. This paper will focus on the information mining and analysis of large sports medical data, focusing on the loss of training mode and the accuracy of convolution algorithm. In order to achieve effective prediction and risk assessment of sports medicine-related diseases, this paper starts with the improved convolutional neural network deep learning algorithm, and adopts the resampling algorithm with self-adjusting function, supplemented by tensor convolution self-coding algorithm. Ural network model assists multi-dimensional data analysis of sports medicine. Finally, in order to build an intelligent medical data platform for sports medicine, this paper innovatively proposes a cloud-based hardware-in-the-loop simulation model. Experiments show that this method provides reference and technical support for the realization of a real cloud-based fusion system.

Keywords

• Sport medicine
• improved deep learning algorithm
• sport medicine big data
• tensor convolution self-coding deep learning algorithm
• cloud-end fusion hardware-in-the-loop simulation model