Title: Research on athlete's wrong movement prediction method based on multimodal eye movement recognition

Authors: Luojing Wang

Addresses: Shangqiu Polytechnic, Shangqiu 476000, China

Abstract: In order to solve the problems of large prediction error, long time consumption and large amount of interference data in the prediction results of traditional methods, an athlete's wrong movement prediction method based on multimodal eye movement recognition is proposed. Firstly, the spectral clustering algorithm is used to mine the wrong movements. Secondly, the least square method is used to improve the support vector machine, and the improved support vector machine is used to classify athletes' wrong movements according to the statistical characteristics of athletes' wrong movements. Finally, based on the classification results and the historical data of athletes' wrong movements, the trend of athletes' wrong movements is predicted by the multimodal eye movement recognition method to complete the prediction of athletes' wrong movements. The experimental results show that the method causes small prediction error, consumes short prediction time and has a low proportion of interference data.

Keywords: multimodal eye movement recognition; wrong movement; feature extraction; action mining; support vector machine.

DOI: 10.1504/IJRIS.2022.126658

International Journal of Reasoning-based Intelligent Systems, 2022 Vol.14 No.4, pp.176 - 183

Received: 30 Sep 2021
Accepted: 14 Jul 2022
Published online: 31 Oct 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article