Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning.

Cricket fast bowlers are at a high risk of injury occurrence, which has previously been shown to be correlated to bowling workloads. This study aimed to develop and test an algorithm that can automatically, reliably and accurately detect bowling deliveries. Inertial sensor data from a Catapult OptimEye S5 wearable device was collected from both national and international level fast bowlers (n = 35) in both training and matches, at various intensities. A machine-learning based approach was used to develop the algorithm. Outputs were compared with over 20,000 manually recorded events. A high Matthews correlation coefficient (r = 0.945) showed very good agreement between the automatically detected bowling deliveries and manually recorded ones. The algorithm was found to be both sensitive and specific in training (96.3%, 98.3%) and matches (99.6%, 96.9%), respectively. Rare falsely classified events were typically warm-up deliveries or throws preceded by a run. Inertial sensors data processed by a machine-learning based algorithm provide a valid tool to automatically detect bowling events, whilst also providing the opportunity to look at performance metrics associated with fast bowling. This offers the possibility to better monitor bowling workloads across a range of intensities to mitigate injury risk potential and maximise performance.

The Response to and Recovery From Maximum-Strength and -Power Training in Elite Track and Field Athletes.

UNLABELLED: There is a great deal of research on the responses to resistance training; however, information on the responses to strength and power training conducted by elite strength and power athletes is sparse. PURPOSE: To establish the acute and 24-h neuromuscular and kinematic responses to Olympic-style barbell strength and power exercise in elite athletes. METHODS: Ten elite track and field athletes completed a series of 3 back-squat exercises each consisting of 4 × 5 repetitions. These were done as either strength or power sessions on separate days. Surface electromyography (sEMG), bar velocity, and knee angle were monitored throughout these exercises and maximal voluntary contraction (MVC), jump height, central activation ratio (CAR), and lactate were measured pre, post, and 24 h thereafter. RESULTS: Repetition duration, impulse, and total work were greater (P < .01) during strength sessions, with mean power being greater (P < .01) after the power sessions. Lactate increased (P < .01) after strength but not power sessions. sEMG increased (P < .01) across sets for both sessions, with the strength session increasing at a faster rate (P < .01) and with greater activation (P < .01) by the end of the final set. MVC declined (P < .01) after the strength and not the power session, which remained suppressed (P < .05) 24 h later, whereas CAR and jump height remained unchanged. CONCLUSION: A greater neuromuscular and metabolic demand after the strength and not power session is evident in elite athletes, which impaired maximal-force production for up to 24 h. This is an important consideration for planning concurrent athlete training.

Reliability of a combined biomechanical and surface electromyographical analysis system during dynamic barbell squat exercise.

An analysis system for barbell weightlifting exercises is proposed to record reliable performance and neuromuscular responses. The system consists of surface electromyography (sEMG) synchronized with electrogoniometry and a barbell position transducer. The purpose of this study was to establish the reliability of the three components of the system. Nine males (age 28.9 ± 4.8 years, mass 85.7 ± 15.1 kg) performed squat exercise at three loads on three separate trial days. A data acquisition and software system processed maximal knee angle (flexion), mean power for the concentric phase of squat exercise, and normalized root mean square of the vastus lateralis. Inter-trial coefficients of variation for each variable were calculated as 5.3%, 7.8%, and 7.5% respectively. In addition, knee joint motion and barbell displacement were significantly related to each other (bar displacement (m) = 1.39-0.0057 × knee angle (degress), with goodness-of-fit value, r² = 0.817), suggesting knee goniometry alone can represent the kinematics of a multi-joint squat exercise. The proven reliability of the three components of this system allows for real-time monitoring of resistance exercise using the preferred training methods of athletes, which could be valuable in the understanding of the neuromuscular response of elite strength training methods.