Secure prediction and assessment of sports injuries using deep learning based convolutional neural network
Document Type
Article
Publication Date
3-1-2021
Abstract
In recent days, many information and image evidence in the field of medicine is being designed and developed by the advancement of computer technology. Presently, sport medical data is an essential department for medical sector and it is responsible for assuring sports safety based on the recovery level after an injury due to sports activity. The approach to reliably interpretation and valuable data information using a vast number of medical sports data and events has become an important research path in the collection and analysis of medical data. This paper discusses the extraction, study, and lack of training and accuracy of complex algorithms for critical sporting medical data. This paper involves with an optimized convolutional neural network (OCNN) based on deep-learning model to ensure successful detection and risk assessments of sport-medicine diseases and adopts the Self-Adjustment Resizing algorithm (SAR) augmented by the self-coding method of the convolution (SCM). CNN model helps to evaluate sports medicine in multi-dimensional results and suggested OCNN classification constitutes two convolutional layers, two pool layers, a fully connected layer, and a SoftMax structure that can be used for the classification of sport-related medical data. The CNN facilitates multi-dimensional sports medicine data analysis and to conclude a cloud-based loop model to create an advanced medical data network for sports medicine. Experiments illustrate that this approach offers technical support and guide to deploying a specific cloud-based fusion system.
Publication Title
Journal of Ambient Intelligence and Humanized Computing
First Page Number
3399
Last Page Number
3410
DOI
10.1007/s12652-020-02560-4
Recommended Citation
Song, Hesheng; xiu-ying Han; Montenegro-Marin, Carlos Enrique; and krishnamoorthy, Sujatha, "Secure prediction and assessment of sports injuries using deep learning based convolutional neural network" (2021). Kean Publications. 1001.
https://digitalcommons.kean.edu/keanpublications/1001