Article
Using Artificial Intelligence to Achieve Auxiliary Training of
Table Tennis Based on Inertial Perception Data
Pu Yanan
†
, Yan Jilong
†
and Zhang Heng *
Citation: Yanan, P.; Jilong, Y.; Heng,
Z. Using Artificial Intelligence to
Achieve Auxiliary Training of Table
Tennis Based on Inertial Perception
Data. Sensors 2021, 21, 6685.
https://doi.org/10.3390/s21196685
Academic Editor: Stefano Rossi
Received: 11 September 2021
Accepted: 6 October 2021
Published: 8 October 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
School of Computer and Information Science, Southwest University, Chongqing 400700, China;
puyanan@email.swu.edu.cn (P.Y.); yanjilong@email.swu.edu.cn (Y.J.)
* Correspondence: dahaizhangheng@swu.edu.cn
† These authors contributed equally to this work and should be considered co-first authors.
Abstract:
Compared with optical sensors, wearable inertial sensors have many advantages such as
low cost, small size, more comprehensive application range, no space restrictions and occlusion,
better protection of user privacy, and more suitable for sports applications. This article aims to solve
irregular actions that table tennis enthusiasts do not know in actual situations. We use wearable
inertial sensors to obtain human table tennis action data of professional table tennis players and
non-professional table tennis players, and extract the features from them. Finally, we propose a new
method based on multi-dimensional feature fusion convolutional neural network and fine-grained
evaluation of human table tennis actions. Realize ping-pong action recognition and evaluation, and
then achieve the purpose of auxiliary training. The experimental results prove that our proposed
multi-dimensional feature fusion convolutional neural network has an average recognition rate that
is 0.17 and 0.16 higher than that of CNN and Inception-CNN on the nine-axis non-professional test
set, which proves that we can better distinguish different human table tennis actions and have a more
robust generalization performance. Therefore, on this basis, we have better realized the enthusiast of
table tennis the purpose of the action for auxiliary training.
Keywords:
wearable computing; inertial sensors; human table tennis action recognition; auxiliary
training; fine-grained evaluation
1. Introduction
As China’s “national ball”, table tennis was introduced to China in 1904. After a
century of precipitation and development, it has been deeply loved by most Chinese people.
Today, China’s table tennis development trend is unstoppable, and China’s table tennis
is at the top international level in terms of echelon construction and talent allocation [
1
].
Since the COVID-19 outbreak at the end of 2019, the rise of national fitness has become
China’s national strategy, and table tennis, as China’s “national ball”, has become the sport
of choice for people of all ages in China. Moreover, the international community also has
many enthusiasts. However, table tennis has high technical content, professionalism, and
practicality. In the actual sports process, for amateur athletes, if they cannot grasp the
key points of the relevant batting actions and footwork, or in the course of sports, wrong
actions and non-compliance with the rules and requirements of the action may result in
injuries such as ligament injury or muscle strain [
2
]; especially for some more challenging
actions, such as the Loop and Speedo, violating the fundamental laws of the body and the
principles of sports mechanics is more likely to cause different degrees of injury to athletes.
The general public does not have professionals to guide their action in table tennis.
Blind exercise can easily cause damage to their own body. With the development of technol-
ogy, the guidance of table tennis actions does not necessarily require professionals. Informa-
tion and computer auxiliary training has become a hot spot. Chu et al. [
3
] designed a run-
ning assistant training device based on radio frequency technology.
Jiang et al.
[
4
] analyzed
the application of cloud computing technology in sports-assisted training.
Zhou et al.
[
5
]
Sensors 2021, 21, 6685. https://doi.org/10.3390/s21196685 https://www.mdpi.com/journal/sensors
