To analyse the technical strength of elite table tennis players more accurately, a model of stroke performance relevance (SPR) was proposed in this study, and 40 matches between Chinese male elite players and players from other countries were selected as samples. Compared with other match analysis methods in table tennis, the main advantage of the SPR model is that a) the calculating the performance relevance of each stroke can more completely reflect the technical and tactical advantage or disadvantage of both players than can the traditional analysis methods. b) In addition to the contribution (score) and responsibility (loss) information, the SPR value includes information on the orders of stroke and scores, which can better reflect the role of various game actions in different game periods. This is the most important difference between the SPR model and traditional match analysis methods. In addition, the SPR analysis showed that the first three strokes, the three techniques (“topspin + attack”, touch short, twist), and the three placements (long backhand, long forehand, long middle) in a table tennis match had an important impact on the game results. The technical strength of Chinese players was significantly better than that of players from other countries.

Stroke evaluation is critical for coaches to evaluate players' performance in table tennis matches. However, current methods highly demand proficient knowledge in table tennis and are time-consuming. We collaborate with the Chinese national table tennis team and propose Tac-Valuer, an automatic stroke evaluation framework for analysts in table tennis teams. In particular, to integrate analysts' knowledge into the machine learning model, we employ the latest effective framework named abductive learning, showing promising performance. Based on abductive learning, Tac-Valuer combines the state-of-the-art computer vision algorithms to extract and embed stroke features for evaluation. We evaluate the design choices of the approach and present Tac-Valuer's usability through use cases that analyze the performance of the top table tennis players in world-class events.

Conventional racket sports training highly relies on coaches' knowledge and experience, leading to biases in the guidance. To solve this problem, smart wearable devices based on Internet of Things technology (IoT) have been extensively investigated to support data-driven training. Considerable studies introduced methods to extract valuable information from the sensor data collected by IoT devices. However, the information cannot provide actionable insights for coaches due to the large data volume and high data dimensions. We proposed an IoT + VA framework, Tac-Trainer, to integrate the sensor data, the information, and coaches' knowledge to facilitate racket sports training. Tac-Trainer consists of four components: device configuration, data interpretation, training optimization, and result visualization. These components collect trainees' kinematic data through IoT devices, transform the data into attributes and indicators, generate training suggestions, and provide an interactive visualization interface for exploration, respectively. We further discuss new research opportunities and challenges inspired by our work from two perspectives, VA for IoT and IoT for VA.

Background: The accuracy of targeted lower limb alignment correction following HTO is closely related to patients’ pain relief and knee joint survival time. How to accurately perform osteotomy and how to obtain the ideal target limb alignment to maximize the curative effect are the difficulty in HTO practice. The purpose of this study is to evaluate the predictive and application value of osteotomy master software (OsteoMaster) in coronal plane preoperative planning of high tibial osteotomy.Method: Sixty-seven patients with medial compartment osteoarthritis and varus deformity treated by medial open-weight high tibial osteotomy were enrolled and divided into observation group (31 cases) and control group (36 cases). The observation group was planned by OsteoMaster, while the control group was planned by Miniaci. The preoperative predicted values of osteotomy depth, open height, correction angle, WBL ratio, and FTA of the observation group were compared with the actual intraoperative values to study their accuracy. The operative time, blood loss, number of fluoroscopy, and WBL ratio were compared between the observation group and the control group to study its application value.Result: There was no significant difference between two groups in preoperative prediction and intraoperative reality of osteotomy depth, open height, correction angle, FTA, and WBL ratio (P> 0.05). The operation time and number of fluoroscopy in the observation group were significantly less than those in the control group (P< 0.05), while the difference in blood loss was not statistically significant (P> 0.05). The good rate of WBL ratio was 87.1% in the observation group and 75% in the control group.Conclusion: OsteoMaster has predictive value in osteotomy depth, open height, correction angle, FTA, and WBL ratio of HTO, which is also helpful to reduce the number of fluoroscopy, shorten the operation time, and improve the accuracy of target limb alignment. The drawback of this approach is 2-dimensional approach in contrast to 3-dimensional preoperative planning that is including the more real study.