Chih-Ta Yen^1,*, Tz-Yun Chen², Un-Hung Chen³, Guo-Chang Wang³, Zong-Xian Chen³

CMC-Computers, Materials & Continua, Vol.74, No.1, pp. 83-99, 2023, DOI:10.32604/cmc.2023.032739 - 22 September 2022

Abstract A system for classifying four basic table tennis strokes using wearable devices and deep learning networks is proposed in this study. The wearable device consisted of a six-axis sensor, Raspberry Pi 3, and a power bank. Multiple kernel sizes were used in convolutional neural network (CNN) to evaluate their performance for extracting features. Moreover, a multiscale CNN with two kernel sizes was used to perform feature fusion at different scales in a concatenated manner. The CNN achieved recognition of the four table tennis strokes. Experimental data were obtained from 20 research participants who wore sensors More >

Yuqi He^1,2,3, Shirui Shao¹, Gusztáv Fekete³, Xiaoyi Yang¹, Xuanzhen Cen^1,4, Yang Song^1,4, Dong Sun^1,*, Yaodong Gu^1,*

Molecular & Cellular Biomechanics, Vol.19, No.4, pp. 221-235, 2022, DOI:10.32604/mcb.2022.027285 - 27 December 2022

Abstract Introduction: Footwork is one of the training contents that table tennis players and coaches focus on. This study aimed to gain a thorough understanding of the muscle activity of the table tennis footwork and creating a musculoskeletal model to investigate the muscle forces, joint kinematic, and joint kinetic characteristics of the footwork during topspin forehand stroke. Methods: Six male table tennis athletes (height: 171.98 ± 4.97 cm; weight: 68.77 ± 7.86 kg; experience: 10.67 ± 1.86 years; age: 22.50 ± 1.64 years) performed chasse step and one-step footwork to return the ball from the coach by… More >