The demand for sports analytics is increasing because it contributes to the victory of competitive sports. Although the technology for automatically measuring tracking data has improved, it is meaningful to systematize analysis using ball touch data because the stadiums that can be used are limited. Moreover, in recent years, analysis using machine learning has been increasing, and it is necessary to accumulate research. With this background, this study aimed to construct measurement items and a model for predicting to shoot in soccer offensive play by applying machine learning. Using the Delphi method, 6 items were deleted from the old measurement item group in the previous study, 11 items were newly created, and 45 items were set as the new measurement item group. A decision tree, random forest, and gradient boosting decision tree were applied to the new measurement item group, and several shot prediction models were constructed. The results indicated that the model using 23 items in the gradient boosting decision tree was the best. Furthermore, a comparison between the old and new measurement item groups revealed that the prediction accuracy of the new measurement item group was higher. In conclusion, 45 measurement items of soccer offensive play were constructed, and the shot prediction model using them was constructed by applying machine learning.

There is limited information about the effect of different levels of competition on the physical fitness of college soccer players. Therefore, we compared the physical fitness of soccer players from different levels of competition within the same college team. We tested 111 male college soccer players from the same college team for high (first), moderate (second), and low (third) competition levels. We used the Yo-Yo Intermittent Recovery Test level 2 (Yo-Yo IR2); 10-, 20-, and 30-m sprints; countermovement jump (CMJ); and 5 rebound jump test (5RJ). The Yo-Yo IR2 and 5RJ results were significantly higher in the first group than in the second and third groups. Further, the CMJ was significantly higher in the first group than in the third group. Between the second and third groups, the Yo-Yo IR2, CMJ, and 5RJ results were significantly higher in the second group than in the third group. However, the third group had a significantly higher 10-m sprint time than the second group. These findings suggest that college soccer players from the high level of competition had superior values for the Yo-Yo IR2, CMJ, and 5RJ tests than the players from the low level of competition within the same team. In contrast, the sprint test did not reveal a superior performance for players from the high level of competition. Therefore, jump tests may serve as an index of anaerobic power that better reflects different levels of competition within the same team compared with sprint tests.

Interpersonal relationships are one of the stressors in sports activities and are considered to be a psychological variable that affects collective efficacy (CE). However, few previous studies on CE in team sports have examined the effect of the stressor of relationships with teammates on CE. The present study examined the differences in psychological stress processes in response to stressors of relationships with teammates and their relationships with CE in young soccer players from the perspective of competition level. High-level youth soccer players (HL) and low-level youth soccer players (LL) were asked to respond to each of the following five scales: CE, athlete-athlete relationship stressor, cognitive appraisal, coping, and stress response. In psychological stress process, based on competition level differences, the HL group showed significantly higher scores on CE and athlete-athlete relationship stressor compared to the LL group. Furthermore, HL also scored significantly higher on challenge and controllability in cognitive appraisal, problem-solving and positive thinking in coping as compared to LL. On the other hand, LL scored significantly higher on avoidance of coping and on helplessness in stress response. Thus, the results suggest that athlete-athlete relationship stressor does not necessarily have a negative effect on CE and that perceptions and behaviours toward stressors by differences of the competition level.

The purpose of this study is to identify the characteristics of the top-ranked teams in the domestic elite rugby union's league competition, by focusing on game performance in the opposition's 22 in their matches. An analysis was performed on 55 matches of the Japan Rugby Top League 2021 season, with six analysis items; scoring profile, form of attack/start of play, playing time, result of play, playing activity and try scoring. The results illustrate that the top-ranked team group played in the opposition's 22 more frequently and scored many tries from a form of attack which enters in the opposition's 22 by running with the ball, in particular, with a shorter playing time before scoring a try. In addition, a higher percentage of ball possession is identified in every type of set play. Other findings of the analysis indicate that tries were scored from various starting situations of play and the tendency to show high performance not only in winning territory by actively using kicks but also winning possession by regaining kicks.

This research aimed to elucidate whether there were differences in physical characteristics and performance across starter and non-starter players in Japanese elite-level female soccer in college. Twenty-four college players (age: 19.8 ± 0.8 years, body height: 160.3 ± 4.0 cm, body mass: 55.2 ± 5.2 kg) participated in this study. We assessed the college players in the field and laboratory on two separate days. We found a significantly low value in the starter players’ group than the nonstarter players’ group in the 10-m sprint and 5 × 10-m shuttle run. For the maximum isokinetic contraction, 300°/s of hip extensor as concentric in the starter players was significantly higher than that of the non-starter players, and we found no statistical differences in the other laboratory-based assessments. This study suggested that although there was no significant difference in maximal muscle strength between starter and non-starter players, non-starter players may be inferior in field tests.

Since it is not easy for analysts in the instruction field to process the performance big data of soccer games, it is necessary to develop models and analysis methods using big data and return them to the instruction field. Game performance data is measured by a quantitative scale, but if it is converted into achievement type binary data, the measurement cost is reduced, and a criterion-referenced evaluation scale with IRT applied can be constructed. However, converting to binary data reduces the amount of information, so it is necessary to reconfirm whether it reflects soccer skills. Therefore, this study’s purpose was to clarify the causal structure of game performance big data with binary data in soccer. To that end, we analyzed the achievement standards for constructing binary data using quantitative game performance big data in J.League offensive plays. The achievement standards were calculated by CART using the Gini impurity, and achievement data converted into a binary scale was constructed. As a result of applying the maximum likelihood method and factor analysis of oblimin rotation to the achievement data and clarifying the factor structure, seven subfactors of offensive skill were extracted. As a result of a path analysis from the variance-covariance matrix of the factor scores estimated by the maximum likelihood method, the causal structure that reflects the attacking style of soccer was clarified in the achievement data. The factor structure and causal structure were superior to the quantitative data.

The purpose of this study was to investigate relationship between the results of CHU-Test (a Test to Carry out High-intensity running with Utmost turns, repeatedly) and high-intensity running (HIR) during soccer matches. Twenty-four male soccer players (university students) aged 19.3±0.9 years were participated in the study. To assess intermittent endurance in soccer, participants performed the CHU-Test and soccer matches. They put on global positioning system (GPS) devise in soccer matches to measure total distance covered (TD), distance covered more than 18.0 km/h (HIR), ratio of HIR to TD (HIR/TD) and distance covered more than 24.0 km/h (Sprinting). CHU-Test results of participants were 17.9±2.6 times in first time and 18.0±3.1 times in second time. Between their results, there was a significant reliability coefficient of 0.95 (p < 0.05). Additionally, significant correlation coefficients (r = 0.67 to 0.76) were showed between the CHU-Test results and HIR, HIR/TD and Sprinting at full time (90-minute), peak 5-minute period and final 15-minute period (75 to 90 minute) of soccer matches (p < 0.05). From these results, it was suggested that the CHU-Test was a field test that was relevant to HIR during soccer matches.

The purpose of the present investigation was to clarify the inter-match variability and the determinants of drink break (DB) duration and its contribution to the extra-time added to the end of official matches of the Japan Professional Football League (J-League). The investigation analyzed official matches of the first division of the J-League (J1-League) in 2021. Of the total season, a final sample of 60 matches with complete videos was analyzed; thereafter, the DB durations and the additional time were obtained in the first and second halves, respectively. The results indicated that the horizontal position for restart location contributes 15.3% of the variation in DB duration, and the restart play and the number of substitutions were also selected as significant predictors for the duration of DBs (p < 0.001). The DB duration was not significantly associated with the goals scored, environmental factors, or additional time. The present investigation suggested that the time for the out-of-play associated with the DB was over 1 min, and the DB duration depended on the distance from the bench side to the location of the restarting. Regarding the inter-match variability of the DB duration, the environmental and human-dependent factors remain unclear.

This study examined self-care through neuromuscular electrical stimulation (NMES) and its efficacy on subjective fatigue in collegiate female football players. Fourteen females (age: 20.7±0.8 years) participated in a crossover experimental design. The participants were randomly allocated to group A (n=7, phase Ⅰ: self-care, phase Ⅱ: control) or B (n=7, phase Ⅰ: control, phase Ⅱ: self-care). The study was completed in two phases with a washout period of 21 days set between phases. NMES was used for five nights in self-care but not in the control phase. The subjective fatigue magnitude was measured using the visual analogue scale; Ogri, Shirakawa, Azumi sleep inventory MA version (OSA); and cortisol awakening response (CAR). Subjective fatigue was significantly different between the before self-care and next morning groups (p<0.02). However, the control group showed no significant differences between before sleep and next morning (p=0.113) in phase I. There were no significant differences between both groups (self-care: p=0.6943, control: p=0.1154) in phase Ⅱ. OSA scored significantly higher by self-care in F4 (p<0.002) in phase Ⅰ and F5 (p<0.004) in phase Ⅱ. CAR showed no significant difference between phases Ⅰ (p=0.2642) and Ⅱ (p=0.2275). These results suggest that self-care with NMES has potential to improve fatigue and sleep quality. Further research with a sufficient sample size is required to confirm the efficacy of the present self-care procedure.

This study aims to determine the changes around the effectiveness of ball possession, and ball-winning tactics in seven-a-side rugby kick-off plays. A total of 437 kick-offs in 68 matches in two Olympic Games were analysed in seven categories: kicking area, player positioning, contest method, lifting players to contest for the ball, kick-off outcome, the result of play and opposition territory possession time. Results showed that the try-scoring rate was about 25% in the immediately following play and about 50% at the end of two consecutive attacks when the kicking team retained possession from kick-offs. On the other hand, when the receiving team won possession, the try-scoring rate was about half of the kicking team respectively. The research found the difference in about 6 seconds between the territorial possession when the receiving team retained possession. An increase in short kicks to retain the ball was also found in kick-off tactics. Furthermore, a change in contesting methods created numerical advantages such as indirect ball receipt by dispersing the kicks and choose kicking areas aiming to reduce the lifting advantages. This research found that the kick-off tactics in seven-a-side rugby in recent years have changed more towards winning contested balls.

This study aimed to investigate the factor and causal structures of counter attack skills in soccer. The research procedure comprised three steps: 1) qualitative analysis to construct a qualitative causal structure and criterion-referenced measurement items of counter attack skills, 2) confirmatory factor analysis of counter attack skills in soccer, and 3) causal structure analysis using structural equation modelling (SEM). Counter attacks from 275 plays were collected through video files. Qualitative analysis led to the construction of the causal structure of counter attack skills in soccer, consisting of penetrative dribble, lay off, penetrative pass, pushing down the opponent’s DFL (Defence line), and disrupting the opponent’s defence, along with 17 criterion-referenced measurement items for these skills. The model fit indices of the confirmatory factor structure and the causal structure model were found to be acceptable, thus establishing the validity of the models. The causal structure model revealed significant causal relationships (p < 0.05) between penetrative dribble skill and pushing down the opponent’s DFL skill (0.555), lay off skill and penetrative pass skill (0.588), and penetrative pass skill and disrupting the opponent’s defence skill (0.653). The findings thus reveal the factor structure and the causal relationships among counter attack skills in soccer.