Expected passes

Passes are by far football’s (soccer) most frequent event, yet surprisingly little meaningful research has been devoted to quantify them. With the increase in availability of so-called positional data, describing the positioning of players and ball at every moment of the game, our work aims to determine the difficulty of every pass by calculating its success probability based on its surrounding circumstances. As most experts will agree, not all passes are of equal difficulty, however, most traditional metrics count them as such. With our work we can quantify how well players can execute passes, assess their risk profile, and even compute completion probabilities for hypothetical passes by combining physical and machine learning models. Our model uses the first 0.4 seconds of a ball trajectory and the movement vectors of all players to predict the intended target of a pass with an accuracy of $$93.0\%$$ 93.0 % for successful and $$72.0\%$$ 72.0 % for unsuccessful passes much higher than any previously published work. Our extreme gradient boosting model can then quantify the likelihood of a successful pass completion towards the identified target with an area under the curve (AUC) of $$93.4\%$$ 93.4 % . Finally, we discuss several potential applications, like player scouting or evaluating pass decisions.

Comparison of TrackMan Data between Professional and Amateur Golfers at Swinging to Uphill and Downhill Fairways

Background: Golfers face different environmental conditions in each game played under various constraints. Enhancing affordances through training in a constrained outdoor environment is crucial. Objective: To analyze club head behavior at ball impact of a tee shot by 42 professional (PGs) and 25 amateur (AGs) golfers in swinging to uphill and downhill fairway environments using the TrackMan portable launch monitor. Methods: We used TrackMan to compare golf club movement adaptations in 42 PGs and 25 AGs. A 330-m driving range facing both the uphill (+5°) and downhill (-5°) fairways were used. The tee shot area was the only flat ground surface, with the uneven ground between the shot area and the 200-yard fairway. Results: The clubhead speed and attack angle were significantly higher among PGs than among AGs. PGs could adapt their swings to the uphill fairway by increasing the attack angle (3.6°±2.4) by 3.3° compared with the downhill fairway. The attack angle did not correlate with the launch angle among the AGs in the downhill condition, suggesting that they were unable to control the height of the ball based on the far side of the fairway. Conclusion: PGs increased the attack angle in uphill conditions, and their awareness of the affordance, which was different from that of AGs, allowed them to change the optimal ball trajectory to avoid perceived fairway risks. Thus, the more skill a player had, the better he was at recognizing the affordance of the visual field. PGs demonstrated a better ability to adapt to environmental constraints.

Study on the training model of football movement trajectory drop point based on fractional differential equation

To study the landing point of the curved football track, the dynamic differential equations of the football were derived in this paper. The air resistance moment was taken into account, and the rotation axis was no longer confined to the vertical direction. We compare various soccer movement regularity of different initial angular velocity 0, in turn, using standard numerical methods to solve differential equations, the selection of the initial angular velocity of three typical 0s has been carried on the detailed numerical study, and the results show that: in the same velocity V play football, corresponding to different initial angular velocity 0, the movement of football is an obvious difference. Conclusion: For the same V = 5 + 28 + 11 m/s, when no rotation Ω 0 = 0, the trajectory of the football is the usual trajectory of the projectile. When 0 = 2 − 2 + 16 rad/s, the trajectory of the football is a typical banana ball trajectory; When 0 = 13+0+0 rad/s, the trajectory of the football shows the phenomenon of left-right fluttering, similar to the fallen leaf ball.

Serve Ball Trajectory Characteristics of Different Volleyballs and Their Causes

A floater serve in volleyball is a technique of serving a non-rotating or low-rotating ball, which is difficult to return because the flight path of the ball changes irregularly. On the other hand, the randomness of the trajectory makes it difficult for the ball to fall on the target. Players are required to serve taking into account the variability of the trajectory. In previous studies using wind tunnels, it was shown that aerodynamic characteristics such as drag force and lateral force applied to the ball vary depending on the type of ball and the orientation of the panel. Therefore, in order to control the flight trajectory, it is necessary to understand the aerodynamic characteristics of each ball. Since the velocity of the ball and the fluid force applied to the ball changes during flight, it is important to measure not only the fluid force at a steady state in the wind tunnel but also the actual flight distance of the ball. In this study, to provide valuable information for precise control of floater serves, we measured the drag force applied to the ball in a wind tunnel and the flight distance of the ball using an ejection machine, and clarified the effects of the type of ball and the panel face. In the drag force measurement, the drag force on three types of balls, V200W, MVA200, and FLISTATEC, was measured in the wind speed range of 4 m/s to 30 m/s. In the ejection measurement, the ball flight distances were measured while changing the orientation of the panel using an ejection machine. Basically, the FLISTATEC, MVA200, and V200W, in that order, were more likely to increase the distance and the variability, but it was shown that the drop point could be adjusted slightly by selecting the panel face. This result was also obtained when a human player actually served the ball, indicating the tactical importance of the player consciously controlling the direction of the panel. The tactical importance of the player’s conscious control of the direction of the panel was demonstrated. We also proposed receiver positions that would be effective based on the characteristics of each ball.

The Effect of Judgement Bias on Cue Utilization for Shot Prediction in Basketball Athletes

Background: Concerning the judgments bias and cue utilization in basketball athletes, previous shot anticipation tasks were hard to examine in regards to whether the experts’ judgement bias relies more on the cue of the player’s body or the ball trajectory. Methods: Four types of body–ball cues shots were employed: IN–IN, IN–OUT, OUT–IN, and OUT–OUT. Four temporal stages (i.e., shooting, rising, high point, and falling) were divided during a shot. Forty-two participants predicted the fate of the ball after watching the shot videos. Results: The results suggested that for the shooting, rising, and high point phase, compared to the non-athletes, the experts provided superior predictions for IN–IN condition and OUT–IN condition but fewer accurate predictions for IN–OUT condition and OUT–OUT condition. Moreover, a higher bias toward predicting the shots as “in” for the athletes than the non-athletes under early temporal conditions was confirmed. Conclusions: These findings strengthen the idea that the IN cues from both body information and ball trajectory could elicit the experts’ judgement bias for made shots and then influence their response, thus rendered two distinct (e.g., impeding and facilitating) effects for the incongruent body–ball cues, respectively.

Event-Based Trajectory Prediction Using Spiking Neural Networks

In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory by adding a simple read-out layer composed of polynomial regressions, and trained in a supervised manner. Hence, we show that a SNN receiving inputs from an event-based sensor can extract relevant spatio-temporal patterns to process and predict ball trajectories.

Effects of goal-related statistics on match outcome during the Intercontinental Beach Soccer Cup Dubai 2019

The aim of this study was to investigate the effects of goal-related statistics on match outcome during the Intercontinental Beach Soccer Cup Dubai 2019. The offensive sequences that resulted in goal was analyzed in all 20 matches during the competition (n=138 goals). A set of 35 goal-related statistics were grouped in nine macro-categories: Match-period, Court-zone, Set-play, Open-play, Touches by players before goal, Offensive method, Goalkeeper-line, Number of passes before goal, Ball trajectory. Match outcome in regular time was considered the matches resulting in a loss (n=16), draw (n=8) or win (n=16). The most goals were scored in Open-play (69%), during the 2nd and 3rd periods (36% for each), near to goal (Zone 4; 50%), preceded by 1-touch (67%) and 0-pass (29%), using positional attack (46%), without goalkeeper-line (68%), and with high-ball trajectory (51%). The results of the discriminant function analysis shows the following order of importance to discriminate match outcome, with advantage for winning teams: 4v4 goal-successful (F-Ratio = 12.022), Zone 4, 1-touch, 3rd period, High-ball, Counterattack, Zone 2, Sand-touch (F-Ratio = 4.838). Winning teams scored their goals mainly in open-play situations and without goalkeeper-line, using counterattack to achieve zones near the opponent’s goals, implementing a direct offensive style. Also, goals scored were usually preceded by 1-touch, both through high-ball and sand-touch ball trajectory.

The influence of expertise and experimental paradigms on the visual behavior of tennis athletes in returning a serve

To return a serve, one must pick up information from the server’s kinematics and anticipate the ball trajectory. Although the perceptual requirements are important, the literature diverges in terms of the differences between experts and novices as well as the importance of the experimental paradigm (in-situ vs. video-based) for the results. This study aimed to address both concerns. We compared experts’ (n=7, 20.6±1.1 year of age) and novices’ (n=7, 20.0±0.4 years of age) visual pattern when returning a serve (Experiment 1) and the influence of the experimental paradigm in experts (Experiment 2). Experts fixated more and longer the upper body and ball, while novices showed a more distributed pattern and with longer fixations outside of the server’s body. Also, the pattern was different when comparing in-situ and laboratory settings, differing mainly in fixation frequency. The influence of expertise was observed in qualitative (relative) and quantitative (absolute) measures of visual behavior with the setting having an important influence. Thus, studies should be as close to the actual situation if trying to understand experts’ behavior.

A goalkeeper’s performance in stopping free kicks reduces when the defensive wall blocks their initial view of the ball

Free kicks are an important goal scoring opportunity in football. It is an unwritten rule that the goalkeeper places a wall of defending players with the aim of making scoring harder for the attacking team. However, the defensive wall can occlude the movements of the kicker, as well as the initial part of the ball trajectory. Research on one-handed catching suggests that a ball coming into view later will likely delay movement initiation and possibly affect performance. Here, we used virtual reality to investigate the effect of the visual occlusion of the initial ball trajectory by the wall on the performance of naïve participants and skilled goalkeepers. We showed that movements were initiated significantly later when the wall was present, but not by the same amount as the duration of occlusion (~200ms, versus a movement delay of ~70-90ms); movements were thus initiated sooner after the ball came into view, based on less accumulated information. For both naïve participants and skilled goalkeepers this delayed initiation significantly affected performance (i.e., 3.6cm and 1.5cm larger spatial hand error, respectively, not differing significantly between the groups). These performance reductions were significantly larger for shorter flight times, reaching increased spatial errors of 4.5cm and 2.8cm for both groups, respectively. Further analyses showed that the wall-induced performance reduction did not differ significantly between free kicks with and without sideward curve. The wall influenced early movement biases, but only for free kicks with curve in the same direction as the required movement; these biases were away from the final ball position, thus hampering performance. Our results cannot suggest an all-out removal of the wall–this study only considered one potential downside–but should motivate goalkeepers to continuously evaluate whether placing a wall is their best option. This seems most pertinent when facing expert free kick takers for whom the wall does not act as a block (i.e., whose kicks consistently scale the wall).