Technical and tactical diagnosis model of table tennis matches based on BP neural network

Huang, Wenwen; Lu, Miaomiao; Zeng, Yuxuan; Hu, Mei-Chih; Xiao, Yi

doi:10.1186/s13102-021-00283-3

Cited by 24 publications

(26 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 The framework of the four-phase evaluation theory Scoring rate (SR) and usage rate (UR) are important indicators for evaluating a table tennis player's performance in each phase of the four-phase evaluation theory [19]. Technique effectiveness (TE) constructs a link between SR and UR for evaluating the effectiveness of each phase [14,40,8,42], and winning probability (WP) is used to assess players' ability to score [20,22]. They are calculated as follows:…”

Section: Notational Analysismentioning

confidence: 99%

“…The four-phase evaluation theory [19], an improvement based on the traditional three-phase evaluation theory, solves the problem of mismatched data between the two sides and is more widely used in the technical and tactical analysis of table tennis today. Related researchers used different algorithms to construct models for diagnosing and analyzing techniques and tactics in table tennis matches through the above-related theories [20,21,22], which has promoted the science of match analysis, further proving the validity of each phase's indicators in the above theories as input features.…”

Section: Introductionmentioning

confidence: 99%

“…Artificial intelligence algorithms are known as "black boxes" due to the complexity of their internal working mechanisms and decisionmaking progress, which are far beyond human understanding [23,24,25,26,27,28]. Therefore, previous studies have used simulation ways to find the key factors in matches [20,21,22], which significantly reduced the reliability of the analytical results. Fortunately, there have been many approaches to increasing models' interpretability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using SHAP to analyze technical and tactical performance in table tennis based on hybrid Catboost-TPE with four-phase evaluation theory

Song,

Li,

Pan

et al. 2023

Preprint

View full text Add to dashboard Cite

This study adopted a novel algorithm, SHapley Additive exPlanation (SHAP), to analyze the table tennis matches based on a hybrid gradient boosting + categorical features-tree-structured parzen estimator (Catboost-TPE) with the four-phase evaluation theory. 110 singles’ matches (9536 rallies) were analyzed, and 59 elite male players’ winning rates from 2018 to 2022 were categorized into three levels (high, medium, low) by k-means cluster analysis. The results showed that Catboost-TPE has the best performance (MSE = 7.5e-05, MAE = 0.006, RMSE = 0.008, \({\text{R}}^{2}\)=0.99 and adjusted \({\text{R}}^{2}\)=0.989) among six hybrid machine learning algorithms. Using Catboost-TPE to calculate the SHAP value of each feature, the global interpretation and multiple local interpretations found that the performance of receive-attack and serve-attack phases have essential impacts on the winning probabilities in current matches. Besides, this study derived the mathematical equations for converting the scoring rate (SR), usage rate (UR) and technique effectiveness (TE) from the four-phase evaluation theory into the new three-phase evaluation theory to further deepen the theoretical and applied value of the four-phase evaluation theory used in this study. These results provided quantitative references to table tennis matches' characteristics and winning phases. These methods used in the study can be widely applied to other sports performance analyses, and the equations derived in this study are also instructive for relative sports.

show abstract

Section: Notational Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using SHAP to analyze technical and tactical performance in table tennis based on hybrid Catboost-TPE with four-phase evaluation theory

Song,

Li,

Pan

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, many researchers also depended on modern information technology and multi-disciplinary integration to study table tennis skills and tactics. At present, the research methods involved in this project mainly include grey correlation theory [12], Deep Convolutional Neural Network-long Short Term Memory (DCNN-LSTM) model analysis [13], Logistic regression model analysis [14], artificial neural network (ANN) [15][16], decision tree [17], particle swarm [18], etc. The intervention of these methods has had a certain effect on the study of table tennis techniques and tactics.…”

Section: Introductionmentioning

confidence: 99%

Contribution Quality Evaluation of Table Tennis Match by Using TOPSIS-RSR Method-------An Empirical Study

Yin

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper aims to evaluate the contribution quality of table tennis matches comprehensively and explore the ranking characteristics of evaluation results and the rationality of grading. Through the application of the documentation method, videos, Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Rank Sum Ratio (RSR), the contribution quality evaluation index system of table tennis matches was established. After then, the technical and tactical performances of 38 matches between Harimoto Tomokazum, the critical table tennis player of the Japanese new generation, and vital worldwide players from 2018 to 2020 were comprehensively evaluated. According to research results, Harimoto had 8 matches with the Ci value > 0.5 in serve rounds, 4 with the Ci value > 0.5 in receive rounds, and 5 with the RSR value > 0.6 in the comprehensive strength. These findings were generally consistent with the final match results. Furthermore, Pearson Correlation showed that the three indicators were significantly correlated with competition performance (CP) (P＜0.01). Each race could be divided into four grades, and there was a very significant difference among them by variance test (F=60.281, P＜0.01). Meanwhile, SNK pairwise comparison between four grades had statistical significance (P＜0.05). Therefore, researchers could conclude that the combination of TOPSIS and RSR could objectively and accurately reflect the contribution quality of table tennis matches. This method could be promoted and applied in the competition performance evaluation of other net games.

show abstract

“…This research will be crucial in understanding the relationship of contributing techniques from the beginning to end of forehand strokes in the tennis [8]. Strategy and tactics directly affect the outcome of the match (performance) [30].…”

Section: Introductionmentioning

confidence: 99%

BOTELI and Interval Training to Improve Tennis Groundstroke Forehand's Rally Skills

Agustiyanta¹,

Hidayatullah²,

Doewes³

et al. 2022

saj

View full text Add to dashboard Cite

This study aims to determine the effect of BOTELI interval training on the groundstroke forehand rally skills of tennis. This research was conducted on the tennis court of the Faculty of Sports Science, Sebelas Maret University, Surakarta. The research method uses experiments. The sample in this study was 24 students of the Faculty of Sports Science, Sebelas Maret University, Surakarta, for the 2021/2022 academic year. The training method in this study uses BOTELI exercises with 1:1 and 1:3 intervals. The measuring instrument is the kemp-vincent rally tennis skill test. The data analysis technique was Paired T-Test at a significance level of = 0.05 using SPSS version 20 software. The results showed that BOTELI interval training could improve forehand groundstroke rally skills in tennis. However, there are differences between the 1:1 interval BOTELI training method with the 1:3 interval BOTELI training method in enhancing the groundstroke rally forehand skills of tennis. For students with a BOTELI interval of 1: 1, the results are better than 1:3 with an average value (1:1 = 63.58 and 1:3 = 48.42). In this study, it was found that the advantages of BOTELI interval training with a dose of 300 strokes per training session and every 20 strokes there is an interval lag, so after making several 1800 strokes, students can play tennis simply. The benefits of using BOTELI tools in doing groundstroke forehand rally techniques are efficiency and function. Efficient in terms of cost, time and number of balls used, its function will result in mastery of the forehand groundstroke rally technique quickly because, in terms of similarities, the training using BOTELI is very similar to the general groundstroke forehand rally exercise, even more, flexible and adaptive. The use of BOTELI aids also functions for implementing exercise programs such as exercise frequency and training intervals will be more easily fulfilled or achieved. This BOTELI tool can be useful for doing groundstroke forehand rally exercises easily, cheaply, and comfortably and can be done independently.

show abstract

Technical and tactical diagnosis model of table tennis matches based on BP neural network

Cited by 24 publications

References 16 publications

Using SHAP to analyze technical and tactical performance in table tennis based on hybrid Catboost-TPE with four-phase evaluation theory

Using SHAP to analyze technical and tactical performance in table tennis based on hybrid Catboost-TPE with four-phase evaluation theory

Contribution Quality Evaluation of Table Tennis Match by Using TOPSIS-RSR Method-------An Empirical Study

BOTELI and Interval Training to Improve Tennis Groundstroke Forehand's Rally Skills

Contact Info

Product

Resources

About