Instantaneous velocity estimation for the four swimming strokes using a 3-axis accelerometer: Validation on paralympic athletes

Agreement between an automated video-based system and tethered system to measure instantaneous swimming velocity

Successful performance in competitive swimming requires a swimmer to maximise propulsion and minimise drag, which can be assessed using instantaneous swimming velocity. Many systems exist to quantify velocity, and therefore, it is important to understand the agreement between systems. This study examined the agreement between an automated video-based system and a tethered system to measure instantaneous velocity. Twenty-two competitive swimmers (state level or higher) completed 25 m of each stroke at maximal intensity. The tethered speedometer was attached to the swimmer's waist, while videos of each trial were recorded. The swimmer's head was then automatically tracked using proprietary software, and instantaneous velocity was determined from each system. Bland-Altman plots showed good agreement between the two systems in backstroke (95% Limits of Agreement (LOA): -0.24-0.26 m.s-1) and freestyle (95% LOA: -0.36-0.38 m.s-1) but poorer agreement in butterfly (95% LOA: -0.51-0.53 m.s-1) and breaststroke (95% LOA: -0.88-0.92 m.s-1). The root mean square error was higher in butterfly (0.27 m.s-1) and breaststroke (0.46 m.s-1) compared to backstroke (0.13 m.s-1) and freestyle (0.19 m.s-1). Results demonstrated that the two systems are comparable for measuring instantaneous swimming velocity; however, larger discrepancies are evident for butterfly and breaststroke.

Validation of Automatically Quantified Swim Stroke Mechanics Using an Inertial Measurement Unit in Paralympic Athletes

Biomechanics and training load monitoring are important for performance evaluation and injury prevention in elite swimming. Monitoring of performance and swim stroke parameters is possible with inertial measurement units (IMU) but has not been validated in para-swimmers. The purpose of this study was to validate a single IMU-based system to accurately estimate pool-swam lap time, stroke count (SC), stroke duration, instantaneous stroke rate (ISR), and distance per stroke (DPS). Eight Paralympic athletes completed 4 × 50 m swims with an IMU worn on the sacrum. Strokes cycles were identified using a zero-crossing algorithm on the medio-lateral (freestyle and backstroke) or forward-backward (butterfly and breaststroke) instantaneous velocity data. Video-derived metrics were estimated using Dartfish and Kinovea. Agreement analyses, including Bland-Altman and Intraclass Correlation Coefficient (ICC), were performed on all outcome variables. SC Bland-Altman bias was 0.13 strokes, and ICC was 0.97. ISR Bland-Altman biases were within 1.5 strokes/min, and ICCs ranged from 0.26 to 0.96. DPS Bland-Altman biases were within 0.20 m, and ICCs ranged from 0.39 to 0.93. A single-IMU system can provide highly valid performance and swim stroke monitoring data for elite para-swimmers for the majority of strokes, with the exception of backstroke. Future work should improve bilateral stroke detection algorithms in this population.

Automatic detection of passing and shooting in water polo using machine learning: a feasibility study

There is currently no efficient way to quantify overhead throwing volume in water polo. Therefore, this study aimed to test the feasibility of a method to detect passes and shots in water polo automatically using inertial measurement units (IMU) and machine-learning algorithms. Eight water polo players wore one IMU sensor on the wrist (dominant hand) and one on the sacrum during six practices each. Sessions were filmed with a video camera and manually tagged for individual shots or passes. Data were synchronised between video tagging and IMU sensors using a cross-correlation approach. Support vector machine (SVM) and artificial neural networks (ANN) were compared based on sensitivity and specificity for identifying shots and passes. A total of 7294 actions were identified during the training sessions, including 945 shots and 5361 passes. Using SVM, passes and shots together were identified with 94.4% (95%CI = 91.8-96.4) sensitivity and 93.6% (95%CI = 91.4-95.4) specificity. Using ANN yielded similar sensitivity (93.0% [95%CI = 90.1-95.1]) and specificity (93.4% [95%CI = 91.1 = 95.2]). The results suggest that this method of identifying overhead throwing motions with IMU has potential for future field applications. A set-up with one single sensor at the wrist can suffice to measure these activities in water polo.