Quantifying technical actions in professional soccer using foot-mounted inertial measurement units

Abstract

This study aimed to (i) establish the concurrent validity and intra-unit reliability of a foot-mounted inertial measurement unit for monitoring soccer technical actions, (ii) quantify the within-microcycle inter-positional differences in the technical actions of professional soccer training, and (iii) determine the influence of drill category on the technical actions of professional soccer training. Twenty-one professional soccer players' technical performance data (ball touches, releases, ball touches per minute, releases per minute), collected during training sessions (i.e. match-day (MD) minus day number) throughout twenty-four weekly microcycles, were analysed using general linear modelling. The inertial measurement unit exhibited good concurrent validity (PA = 95.1% -100.0%) and intra-unit reliability (PA = 95.9% -96.9%, CV = 1.4% -2.9%) when compared with retrospective video analyses. The most ball touches (X = 218.0) and releases (X = 110.8) were observed on MD -1, with MD -5 eliciting the highest frequency of ball touches (X = 3.8) and releases (X = 1.7) per minute. Central midfielders performed the most ball touches (X = 221.9), releases (X = 108.3), ball touches per minute (X = 3.4) and releases per minute (X = 1.6). Small-sided games evoked more ball touches (X diff = 1.5) and releases per minute (X diff = 0.1) than previously reported in match-play. The fewest ball touches (X = 1.2) and releases per minute (X = 0.5) were observed during tactical drills. The results of this study provide a novel understanding of the within-microcycle, inter-positional and drill category differences in the technical actions performed by professional players during training.

Automated Classification of Changes of Direction in Soccer Using Inertial Measurement Units

“…Choosing the level at which the classification acceptance threshold is set may require further thought and investigation, or else it may be set at the discretion of practitioners who decide the relative importance of sensitivity and specificity in varying situational circumstance. Furthermore, using additional sensors in alternative locations e.g., the foot [ 22 ], may provide unique data to the trunk-mounted sensor and further improve COD classification.…”

The effect of bio-banding on academy soccer player passing networks: Implications of relative pitch size

“…Recording was initiated 10 minutes before activity. As per previous methods [ 49 ], players wore an IMU on each foot, with each device gathering information via a 2000°/sec tri-axial gyroscope and a 16 g tri-axial accelerometer. The gyroscope measured angular velocity of the shank while the accelerometer identified accelerations of the lower leg in the frontal, sagittal and transverse planes of motion.…”

“…Moreover, IMUs were also able to capture team characteristics including the possession percentage, the number of attempted and successful passes, the mean number of passes per possession, the mean time in possession and the mean time regaining possession. Due to a limitation within the PlayerMaker system when distinguishing between a shot and a pass [ 49 ], all shots at goal were removed from the passing network analysis, with only data that represented when one player released the ball and another received it being included. Using twelve amateur soccer players, who collectively performed 8,640 ball touches and 5,760 releases during a series of technical soccer tasks, repeated over two pre-determined distances, previous research [ 49 ] has shown the concurrent validity (agreement with video analysis) for ball touches and releases to be 95.1% and 97.6% respectively [ 49 ].…”

“…Due to a limitation within the PlayerMaker system when distinguishing between a shot and a pass [ 49 ], all shots at goal were removed from the passing network analysis, with only data that represented when one player released the ball and another received it being included. Using twelve amateur soccer players, who collectively performed 8,640 ball touches and 5,760 releases during a series of technical soccer tasks, repeated over two pre-determined distances, previous research [ 49 ] has shown the concurrent validity (agreement with video analysis) for ball touches and releases to be 95.1% and 97.6% respectively [ 49 ]. With intra-unit reliability possessing 96.9% and 95.9% agreement during soccer activity [ 49 ].…”

“…Using twelve amateur soccer players, who collectively performed 8,640 ball touches and 5,760 releases during a series of technical soccer tasks, repeated over two pre-determined distances, previous research [ 49 ] has shown the concurrent validity (agreement with video analysis) for ball touches and releases to be 95.1% and 97.6% respectively [ 49 ]. With intra-unit reliability possessing 96.9% and 95.9% agreement during soccer activity [ 49 ]. Additionally, the Game Technical Scoring Chart (GTSC) [ 48 ] was used as an alternative means to subjectively quantify the technical performance of players.…”