Analysis of defensive playing styles in the professional Chinese Football Super League.

AIM: Describing and measuring different team styles of play during matches is a key step towards a more predictive and prescriptive performance analysis. The current study aimed to identify and measure different defensive playing styles associated with technical-tactical and physical performance indicators in professional football via Principal Component Analysis (PCA). METHODS: The sample comprised all 240 matches played in the Chinese Football Super League (CSL) during the 2018 season. RESULTS: Seventeen key performance indicators (KPIs), 15 defense-related and 2 physical-related were identified from a total of 62 defensive performance indicators, which significantly differed between when teams lost and did not lose (p<0.05, ES=0.03-0.22). Then the PCA model based on 17 KPIs (Kaiser-Meyer-Olkin value being 0.81), outputted 8 factors representing 7 different styles of play (factor 6 and 8 represented one style) and explaining 83.01% of the total variance. Of all styles, defense close to own goal, including clearance, ball gain in the zone 1, deep completion and unsuccessful cross of the opponent, was the most dominant style (31.92% of the total variance). The champion of the league showed better scores in all styles of play, while the last ranked team got the highest score in defense close to the own goal style. CONCLUSION: The study indicated that a team's defensive style could be defined by specific KPIs, and teams are suggested to attune their styles consciously rather than maintaining a consistent strategy so as to achieve better performance. Moreover, such categorization of defensive styles could be used during scouting and match preparation.

Quantifying the Effectiveness of Defensive Playing Styles in the Chinese Football Super League.

Establishing and illustrating a predictive and prescriptive model of playing styles that football teams adopt during matches is a key step toward describing and measuring the effectiveness of styles of play. The current study aimed to identify and measure the effectiveness of different defensive playing styles for professional football teams considering the opponent's expected goal. Event data of all 1,120 matches played in the Chinese Football Super League (CSL) from the 2016 to 2020 seasons were collected, with fifteen defense-related performance variables being extracted. The PCA model (KMO = 0.76) output eight factors that represented 7 different styles of play (factor 6 and 8 represent one style of play) and explained 85.17% of the total variance. An expected goal (xG) model was built using data related to 27,852 shots. Finally, the xG of the opponent was calculated in the multivariate regression model, outputting five factors that (p < 0.05) explained 41.6% of the total variance in the xG of the opponent and receiving a dangerous situation (factor 7) was the most apparent style (31.3%). Finally, the predicted model with defensive styles correlated with actual xG of the opponent at r = 0.62 using the 2020 season as testing data which showed that the predicted xG was correlated moderately with the actual. The result indicated that if the team strengthened the defense closed to the own goal, high intensity confrontation, and defense of goalkeeper, meanwhile making less errors and receiving less dangerous situations, the xG of the opponent would be greatly reduced.

A Lightweight Spatial and Temporal Multi-Feature Fusion Network for Defect Detection.

This article proposes a hybrid multi-dimensional features fusion structure of spatial and temporal segmentation model for automated thermography defects detection. In addition, the newly designed attention block encourages local interaction among the neighboring pixels to recalibrate the feature maps adaptively. A Sequence-PCA layer is embedded in the network to provide enhanced semantic information. The final model results in a lightweight structure with smaller number of parameters and yet yields uncompromising performance after model compression. The proposed model allows better capture of the semantic information to improve the detection rate in an end-to-end procedure. Compared with current state-of-the-art deep semantic segmentation algorithms, the proposed model presents more accurate and robust results. In addition, the proposed attention module has led to improved performance on two classification tasks compared with other prevalent attention blocks. In order to verify the effectiveness and robustness of the proposed model, experimental studies have been carried out for defects detection on four different datasets. The demo code of the proposed method can be linked soon: http://faculty.uestc.edu.cn/gaobin/zh_CN/lwcg/153392/list/index.htm.