Criterion Validity of a MARG Sensor to Assess Countermovement Jump Performance in Elite Basketballers

Validity and reliability of torso- versus waist-worn inertial measurement units in the assessment of vertical jumps

The aim of the current study was to compare the reliability and validity of jump variables determined from torso- and waist-worn inertial measurement units (IMU) in comparison to force platform measures. Twenty-seven students-athletes completed eight countermovement (CMJ) and squat jumps (SJ) on a force platform with IMUs mounted on the pelvis and torso. Variables including jump height and phase-specific duration, impulse and power were calculated from force platform and both IMUs independently. Considering both IMU locations, the coefficients of variation (CV) observed for all CMJ variables were ≤ 2.5 % larger than the force platform with the exception of concentric impulse with the torso-worn worn IMU (6.9 %). Differences in CVs observed between IMU and force platform variables appeared greater in the SJ. For velocity-derived jump height and concentric impulse from both IMU placements, and torso-worn IMU mean power, CVs were > 2.5 % larger than the force platform. Both IMU placements overestimated jump height determined by flight time (+22 to +35 %) and underestimated jump height determined by take-off velocity (-10 to -18 %). In conclusion, the reliability of IMU metrics was largely comparable to the force platform. However, systematic bias was observed for most metrics. Practitioners should exercise caution if seeking to model jump performance with IMUs.

Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition Using Wrist-Worn Inertial Sensors

We present a benchmark dataset for evaluating physical human activity recognition methods from wrist-worn sensors, for the specific setting of basketball training, drills, and games. Basketball activities lend themselves well for measurement by wrist-worn inertial sensors, and systems that are able to detect such sport-relevant activities could be used in applications of game analysis, guided training, and personal physical activity tracking. The dataset was recorded from two teams in separate countries (USA and Germany) with a total of 24 players who wore an inertial sensor on their wrist, during both a repetitive basketball training session and a game. Particular features of this dataset include an inherent variance through cultural differences in game rules and styles as the data was recorded in two countries, as well as different sport skill levels since the participants were heterogeneous in terms of prior basketball experience. We illustrate the dataset's features in several time-series analyses and report on a baseline classification performance study with two state-of-the-art deep learning architectures.

Residual neuromuscular fatigue influences subsequent on-court activity in basketball

AbstractThe aim of this study was to determine if residual neuromuscular fatigue influenced subsequent match and training activity in professional women's basketball. Prior to matches and training sessions throughout a season, players performed countermovement jumps while wearing a magnetic, angular rate and gravity (acceleration) sensor on their upper back. Flight time to contraction time ratio was used to determine neuromuscular performance and to identify neuromuscular fatigue. Average session intensity and volume, proportion of live time spent in different intensity bands (matches), and absolute and relative time spent in different intensity bands (training) were quantified using accelerometry. Residual neuromuscular fatigue was deemed to be present when the decrement in neuromuscular performance relative to pre-season baseline was greater than the smallest worthwhile change. Players displayed residual neuromuscular fatigue before 16% of matches and 33% of training sessions. When players were fatigued prior to matches, the proportion of live time undertaking supramaximal activity was 5.7% less (p = 0.02) and moderate-vigorous activity was 3.7% more than when not fatigued (p = 0.02). When fatigued prior to training, the players displayed a 2.6% decrement in average intensity (p = 0.02), 2.8% decrement in absolute (p = 0.01) and 5.0% decrement in relative (p = 0.01) maximal activity, as well as 13.3% decrement in absolute (p < 0.01) and 6.8% decrement in relative (p < 0.01) supramaximal activity when compared to not being fatigued. These findings suggest that residual neuromuscular fatigue influences players' ability to perform supramaximal activity, which highlights the importance of monitoring neuromuscular performance throughout a professional season.

Potential of IMU-Based Systems in Measuring Single Rapid Movement Variables in Females with Different Training Backgrounds and Specialization

The aim of this paper is to determine the discriminative potential of the IMU-based system for the measurement of rapid hand movement properties, i.e., relevant kinematic variables in relation to different groups of participants. The measurement of the kinematics of the rapid hand movement was performed using a standard hand tapping test. The sample in this research included a total of 70 female participants and was divided into 3 subsamples. The discriminant analysis has identified two functions, DF₁ and DF₂, that explain 91.1 and 8.1% of the variance, respectively. The differences between the examined subsamples originate from the variables grouped in DF₁, which were statistically significant (p ≤ 0.000). In relation to this function, the national volleyball team centroid position was shifted with -1.108 and -1.968 standard deviation values from the control group and youth volleyball team, respectively. The difference between control and Voll_Youth groups was -0.860 standard deviation value. The factors with the greatest discriminative potential among the groups represent the temporal characteristics of the rapid hand movement, i.e., the time elapsed between the onset of the movement and the first and second tap, as defined by the variables t ₁ and t ₂, respectively. The established findings clearly indicate that IMU sensors are practically applicable in relation to the sensitive measurement of rapid arm movement capability of female athletes.