Inertial measurement unit-based cricket stroke improviser using polynomial kernel support vector machines

Wearable devices have now become virtual assistants, and the sports industry also aims in technological integration. The objective of this research article is to introduce a wearable device to detect and record the movement of a cricket player during his training session. The designed system collects the displacement and rotational information through a combination of accelerometer and gyroscope placed on the cricket bat. We propose a data-driven machine learning model which takes raw analog data as input for classifying the strokes. The algorithm used is the polynomial support vector machine, a supervised classification algorithm with 300 independent variables to enable accurate and real-time stroke classification. The system has a dedicated user interface for accessing these real-time details. This wearable embedded system does not require any cloud services as the complex analyses are performed in the processor itself. The player and the coach can get visual reference support, and the mistakes can be corrected during the training period itself. The device can detect the arm action of a cricket player with a success rate of 97%. The hardware is powered using a 10,000 mAh rechargeable battery.