The newly developed computer vision pose estimation technique in artificial intelligence (AI) is an emerging technology with potential advantages, such as high efficiency and contactless detection, for improving competitive advantage in the sports industry. The related literature is currently lacking an integrated and comprehensive discussion about the applications and limitations of using the pose estimation technique. The purpose of this study was to apply AI pose estimation techniques, and to discuss the concepts, possible applications, and limitations of these techniques in table tennis. This study implemented the OpenPose pose algorithm in a real-world video of a table tennis game. The research results show that the pose estimation algorithm performs well in estimating table tennis players’ poses from the video in a graphics processing unit (GPU)-accelerated environment. This study proposes an innovative two-stage AI pose estimation method for effectively addressing the current difficulties in applying AI to table tennis players’ pose estimation. Finally, this study provides several recommendations, benefits, and various perspectives (training vs. tactics) of table tennis and pose estimation limitations for the sports industry.

Research question: Baseball has existed for over 100 years in Taiwan, and it is one of Taiwan's most popular sports. However, there have been frequent match-fixing scandals from the Chinese Professional Baseball League, which has dismayed baseball fans. Is there a pattern of match-fixing among players? Research methods: The concept and methods of ‘efficiency and productivity’ were used to explore players’ efficiency, and a weighted moving average was used to verify whether there was a efficiency change of players over the years. A single week was used as a time point, so there were a total of 342 time points for the fielders involved in three match-fixing scandals and a total of 161 time points for the pitchers involved in two match-fixing scandals. Results and Findings: According to the monitoring system for the efficiency anomalies of the players, the detection accuracy rate for the three match-fixing scandals was 62%, and the overall detection accuracy for the match-fixing scandals in 1996 was 71%. Moreover, the detection accuracy rate for efficiency anomalies of the fielders in match-fixing scandals in 2008 reached 100%. No efficiency anomalies were detected for the fielders in 2005 and for the pitchers in 2008. Implications: An assessment model was established to continuously evaluate and monitor the players’ long-term efficiency trends, and to further implement a monitoring system for the efficiency anomalies of players, hoping to prevent match-fixing scandals from occurring.

The profound impact of deep learning technology is poised to revolutionize various industries, marking the fourth industrial revolution. Thus, we combined efficiency and productivity research (data envelopment analysis, DEA), artificial intelligence and deep learning (artificial neural networks, ANN), a system integrating DEA and ANNs, and simultaneous longitudinal research (time series) to determine comprehensive research trends and create relevant applications. We addressed mega-sports events’ performance assessment systems that predict the efficiency of nations participating in the Asian Games from 1990 to 2023 and analyzed the outcomes, applying them to practical issues of national sports policies and development. Performance assessment systems to diagnose, plan, monitor, and revise the impact of implementing measures in Asian nations represent a step forward. The PAS findings point out future research recommendations by addressing national sports policies and development issues, transforming the predictions of performance assessment systems in mega-sports events into practical management recommendations. In this way, the system for enhanced predictive analytics developed in the study can rapidly analyze large, medium, and small datasets, reveal insights that humans may overlook, and refine the likelihood of predicting future events with greater precision and accuracy.

Offensive or defensive? Which approach has the greater impact on winning professional baseball league games? Because the Chinese Professional Baseball League (CPBL) has only four teams, it offered a limited sample size for relevant studies. In this study, a window analysis was coupled with the sports team performance management model of the network data envelopment analysis (DEA) method to solve the problems of offense efficiency, defense efficiency and integrated efficiency of each of the CPBL teams from 2007 to 2014. Truncated regression was coupled with a bootstrapping method to perform a 2000 times repeated sampling, reduce the sampling error and determine the effect of environmental variables on the value of the efficiencies of the CPBL teams. The results show that the Lamigo Monkeys led in both offense performance and defense performance, whereas the United 7-ELEVEn led in integrated performance. The “total number of players” had a significantly positive impact on the efficiency of the teams. The 7-ELEVEn Lions and the Lamigo Monkeys showed superior performance with regard to the investment in the players and the long-term management of the depth of bench players, which verifies the importance of the depth of bench players in the CPBL. The “total bases gained” also had a significantly positive impact on the efficiency of the teams, which indicates the importance of the offensive capability for winning in the CPBL.

Selection of a qualified pitcher has relied previously on qualitative indices; here, both quantitative and qualitative indices including pitching statistics, defense, mental skills, experience, and managers' recognition were collected, and an analytic hierarchy process was used to rank baseball pitchers. The participants were 8 experts who ranked characteristics and statistics of 15 baseball pitchers who comprised the first round of potential representatives for the Chinese Taipei National Baseball team. The results indicated a selection rate that was 91% consistent with the official national team roster, as 11 pitchers with the highest scores who were recommended as optimal choices to be official members of the Chinese Taipei National Baseball team actually participated in the 2009 Baseball World Cup. An analytic hierarchy can aid in selection of qualified pitchers, depending on situational and practical needs; the method could be extended to other sports and team-selection situations.

This study provides a systematic analysis of sports promotion efficiency in 22 administrative districts in Taiwan from 2011 to 2018. We first considered sports behavior and sports information promotion and connected the multiple intermediate products using network DEA, used the public performance and outputs to measure the total efficiency of sports promotion in the 22 administrative districts, and then established the final input–output indicators. The long-term tracking of sports promotion efficiency shows that, while Taipei and Taoyuan experienced upward trends, the other 20 administrative districts saw declining trends. We also used truncated regression to identify 14 environmental variables that affected the efficiency of sports promotion in the 22 administrative districts from 2016 to 2018, with the results showing that funding, satisfaction with life, and average BMI in each administrative district were significant factors, revealing the latest trends in and measurements of governance in terms of government accessibility.