Table Tennis Tutor: Forehand Strokes Classification Based on Multimodal Data and Neural Networks

Abstract

Beginner table-tennis players require constant real-time feedback while learning the fundamental techniques. However, due to various constraints such as the mentor’s inability to be around all the time, expensive sensors and equipment for sports training, beginners are unable to get the immediate real-time feedback they need during training. Sensors have been widely used to train beginners and novices for various skills development, including psychomotor skills. Sensors enable the collection of multimodal data which can be utilised with machine learning to classify training mistakes, give feedback, and further improve the learning outcomes. In this paper, we introduce the Table Tennis Tutor (T3), a multi-sensor system consisting of a smartphone device with its built-in sensors for collecting motion data and a Microsoft Kinect for tracking body position. We focused on the forehand stroke mistake detection. We collected a dataset recording an experienced table tennis player performing 260 short forehand strokes (correct) and mimicking 250 long forehand strokes (mistake). We analysed and annotated the multimodal data for training a recurrent neural network that classifies correct and incorrect strokes. To investigate the accuracy level of the aforementioned sensors, three combinations were validated in this study: smartphone sensors only, the Kinect only, and both devices combined. The results of the study show that smartphone sensors alone perform sub-par than the Kinect, but similar with better precision together with the Kinect. To further strengthen T3’s potential for training, an expert interview session was held virtually with a table tennis coach to investigate the coach’s perception of having a real-time feedback system to assist beginners during training sessions. The outcome of the interview shows positive expectations and provided more inputs that can be beneficial for the future implementations of the T3.

[Retracted] Application of Multiple Regression Analysis Model in Table Tennis Competition

“…By reviewing the literature, this paper found that only a few scholars have studied table tennis doubles and mixed doubles, most of which are the technical and tactical analysis of pairs of mixed doubles players. Although the evaluation methods of table tennis skills and tactics are increasing in the world [6][7][8][9][10][11][12][13][14], they are all based on the three-stage index evaluation method proposed by the Chinese scholar Wu Huanqun. In addition, there are some documents on the construction of other network projects, such as technical and tactical analysis models such as tennis [15][16][17][18][19].…”

Classification of Human Motion Data Based on Inertial Measurement Units in Sports: A Scoping Review

“…[28] combined acceleration data with GPS and heart rate data, and Ref. [109] combined and compared smartphone IMU data with data from the Microsoft Kinect.…”

From Sensor Data to Educational Insights

“…Then, another group of three articles implemented applications that use data from sensors to potentially improve the learning process. For example, Mat Sanusi et al [ 24 ] designed and implemented the Table Tennis Tutor (T3), a multi-sensor system consisting of a smartphone device with built-in sensors for collecting motion data and a Microsoft Kinect for tracking body position that could be used to perform live coaching and feedback of the table tennis forehand strokes of the trainee. Then, the work of [ 25 ] explored the factors from the physical learning environment (PLE) that can affect distance learning and built a software infrastructure that can measure, collect, and process the identified multimodal data from and about the PLE by utilizing mobile sensing.…”