Processing biometric data of game players using body sensors

Biometric data processing resting on sensor systems has been a growing field with a plethora of applications. However, to the best of our knowledge, a system of such kind based on random finite set theory and body sensor networks has not been developed and analyzed. For instance, there are many moments in basketball that when the game is either on the line or in a crucial situation, teams often succumb to pressure and this manifests itself in poor shot attempts, turnovers, and shot-clock violations. The severe movement of players introduces a fast changing channel that affects data transmission of body sensors. Data may be lost at the receiving side due to degenerated channel conditions. In this paper, we describe a system used to monitor stress and exhaustion of game (e.g. basketball) players in realtime during a game. Stress and exhaustion will be quantified and encapsulated within an equation that symbolizes player “readiness” and will include factors such as player talent, and player importance. Furthermore, a formal Bayesian toolkit, namely Random Finite Set Theory, is considered and enabled to process biometric data. Here ‘data’ is a generalized concept that encompasses ‘empty state’ indicating failed data reception. Using this system, a coach can decide to alter his strategy, personnel and the game flow based on the individual readiness of his players. A coach will receive these metrics from the sensors on the players' themselves wirelessly transmitted.