Analytic and descriptive approaches to systematic match analysis in table tennis

Exploring the structure of the shot effectiveness model for elite table tennis players

BACKGROUND

Currently, technical and tactical analysis has become an indispensable task for sport in many countries. Many studies analysed players' specific technical and tactical factors, but it is rare to quantitatively analyse the importance of table tennis players' shot effectiveness. This is the first study to propose the new concept of "shot effectiveness model", and the purpose of this study is to explore the structure of the shot effectiveness model for elite table tennis, including the importance degree of shot effectiveness, and the relationship between them.

METHODS

258 matches were selected between the top 50 players in the world from 2019 to 2021 as samples. Multiple regression analysis was used to obtain the standard regression coefficients and game simulation, and the total decision coefficient (TDC) was used to evaluate the importance degrees of shot effectiveness (SE) on match results.

RESULTS

(1) There was little difference in the importance degree of each shot effectiveness between men and women players. (2) The importance degree of the first and third shots (SE1), the second and fourth shots (SE2), the fifth and after shots (SE3), and the sixth and after shots (SE4) for both men and women players account for approximately 25%, 35%, 22%, and 16% respectively. (3) There was little difference in the importance degree of each shot effectiveness between Chinese women players and women players from other countries and regions with the same importance order of SE2 > SE1 > SE3 > SE4. However, the structure of the shot effectiveness model for men players was quite different from that for women players. (4) There is a compensation effect between shot effectiveness of table tennis players, and the total evaluation score of 12 and 13 is the dividing line for success or failure in both men and women matches.

CONCLUSIONS

TDC could well reflect the important degrees of each shot effectiveness in various ways on winning probability in table tennis matches. And this study compared the importance of several types of players' performance on the probability of winning a match. In addition, we found that there is a compensation effect between shot effectiveness of table tennis players, and the magnitude of this effect will vary according to the type and level of shot effectiveness.

Notational Analysis of Wheelchair Paralympic Table Tennis Matches

Paralympic table tennis is the third largest paralympic sport for the number of players. Performance analysis was conducted for the rally duration and interval and impact of serve, whilst none investigated the shots distribution among classes of physical impairment. Therefore, the purpose of this study was to conduct a notational analysis of international competitions in relation to the wheelchair classes. Five matches for each wheelchair class (C1-to-C5) were evaluated from 20 elite male right-handed players. Both players for each match were analyzed for the following performance indicators: strokes type, the area of ball bouncing, and the shots outcome. Backhand shots were the most used technique for all classes. The most used strokes for C1 players were backhand and forehand drive and backhand lob, while for C5 players they were backhand and forehand push and backhand topspin. Similar shots distribution was registered for C2-to-C5 players. The central and far-from-the-net zone was mainly reached by the serve for all classes. Errors shots were similar in all classes, whilst winning shots were more frequent in C1. The current notational analysis provided a meaningful performance modelling of indicators for coaches and athletes that can be used to design training programs for each class.

Application of deep learning in automatic detection of technical and tactical indicators of table tennis

A DCNN-LSTM (Deep Convolutional Neural Network-Long Short Term Memory) model is proposed to recognize and track table tennis's real-time trajectory in complex environments, aiming to help the audiences understand competition details and provide a reference for training enthusiasts using computers. Real-time motion features are extracted via deep reinforcement networks. DCNN tracks the recognized objects, and the LSTM algorithm predicts the ball's trajectory. The model is tested on a self-built video dataset and existing systems and compared with other algorithms to verify its effectiveness. Finally, an overall tactical detection system is built to measure ball rotation and predict ball trajectory. Results demonstrate that in feature extraction, the Deep Deterministic Policy Gradient (DDPG) algorithm has the best performance, with a maximum accuracy rate of 89% and a minimum mean square error of 0.2475. The accuracy of target tracking effect and trajectory prediction is as high as 90%. Compared with traditional methods, the performance of the DCNN-LSTM model based on deep learning is improved by 23.17%. The implemented automatic detection system of table tennis tactical indicators can deal with the problems of table tennis tracking and rotation measurement. It can provide a theoretical foundation and practical value for related research in real-time dynamic detection of balls.

Biomechanics of Table Tennis: A Systematic Scoping Review of Playing Levels and Maneuvers

This present study aims to review the available evidence on the biomechanics of table-tennis strokes. Specifically, it summarized current trends, categorized research foci, and biomechanical outcomes regarding various movement maneuvers and playing levels. Databases included were Web of Science, Cochrane Library, Scopus, and PubMed. Twenty-nine articles were identified meeting the inclusion criteria. Most of these articles revealed how executing different maneuvers changed the parameters related to body postures and lines of movement, which included racket face angle, trunk rotation, knee, and elbow joints. It was found that there was a lack of studies that investigated backspin maneuvers, longline maneuvers, strikes against sidespin, and pen-hold players. Meanwhile, higher-level players were found to be able to better utilize the joint power of the shoulder and wrist joints through the full-body kinetic chain. They also increased plantar pressure excursion in the medial-lateral direction, but reduced in anterior-posterior direction to compromise between agility and dynamic stability. This review identified that most published articles investigating the biomechanics of table tennis reported findings comparing the differences among various playing levels and movement tasks (handwork or footwork), using ball/racket speed, joint kinematics/kinetics, electromyography, and plantar pressure distribution. Systematically summarizing these findings can help to improve training regimes in order to attain better table tennis performance.

Методика кількісної оцінки техніко-тактичних дій в змагальній діяльності спортсменів в настільному тенісі

Мета: теоретичне обгрунтування і розробка методики обробки статистичних даних матчу з настільного тенісу. Матеріал і методи. Дослідження проводилось в Харківському клубі настільного тенісу “Імпульс”. Було виконано відеозйомку матчу двох спортсменок звичайною камерою смартфона. Були проаналізовані статистичні дані гри по застосованим технічним прийомам і позиціям тенісисток за гральним столом, на якій відстані і в якому напрямку були виконані  прийоми. Результаты. Розроблено, обґрунтовано і впроваджено в практику автоматизовану обробку інформації з техніко-тактичних дій в змагальній діяльності спортсменів з настільного тенісу. Складено моделі множинної лінійної регресії між ступенем впливу використаних технічних елементів для спортсменки 1  і значенням набраної кількості очок за матч. Показано високу значимість технічних елементів Накат (виграв, %) та Підрізки (виграв, %) в кількості набраних очок за матч. Останні показники  були достовірно не значимі і з дуже маленькими коефіцієнтами. Отримано рівняння регрессій, яке дозволяє зробити передбачення кількісті набраних очок у партії, а також виявити найбільш впливові елементи для гравця.  Висновки. Виконано автоматизований підрахунок статистичних даних відеозйомки матчу, де об'єктивно відображена ефективність та надійність виконання основних ударів, що визначають ефективність змагальної діяльності в настільному тенісі. Виконано відображення у вигляді діаграм кількісних оцінок техніко-тактичних дій в змагальній діяльності спортсменів з настільного тенісу. Воно направлено на підвищення результативності тенісистів, шляхом виявлення їх найбільш слабких і сильних сторін, їх усунення або навпаки більш частого застосування в змаганнях. Розроблена, обґрунтована і впроваджена в практику методика обробки статистичних даних матчу в програмі Excel. Практичне значення методики є в доступності для більшості гравців застосовувати запропоновану методику самостійно.

Table tennis match analysis: a review

In table tennis, many different approaches to scientific founded match analysis have been developed since the first ones in the 1960s. The aim of this paper is to give a review on some of the most acknowledged methods of match analysis in table tennis. The first chapter presents a historical overview of match analysis from all over the world. The second part reviews different approaches to match analysis in more detail, using the performance analysis classification of theoretical and practical performance analysis. The review includes the most actual theoretical performance analysis techniques in table tennis: performance indices, simulative approaches, momentum analysis, footwork analysis, and finally an approach which uses top expert knowledge for a comprehensive technical-tactical analysis. In the section of practical performance analysis, the paper presents two "best practice" examples describing performance analysis procedures of the two most successful countries of the last Olympics: China and Japan. The paper ends with a summary on the impact of the different approaches and gives an outlook on promising new developments.

Mutual point-winning probabilities (MPW): a new performance measure for table tennis

We propose a new performance measure for table tennis players: the mutual point-winning probabilities (MPW) as server and receiver. The MPWs quantify a player's chances to win a point against a given opponent, and hence nicely complement the classical match statistics history between two players. These new quantities are based on a Bradley-Terry-type statistical model taking into account the importance of individual points, since a rally at 8-2 in the first set is less crucial than a rally at the score of 9-9 in the final set. The MPWs hence reveal a player's strength on his/her service against a given opponent as well as his/her capacity of scoring crucial points. We estimate the MPWs by means of maximum likelihood estimation and show via a Monte Carlo simulation study that our estimation procedure works well. In order to illustrate the MPWs' versatile use, we have organized two round-robin tournaments of ten respectively eleven table tennis players from the Belgian table tennis federation. We compare the classical final ranking to the ranking based on MPWs, and we highlight how the MPWs shed new light on strengths and weaknesses of the players.