Near drowning pattern recognition using neural network and wearable pressure and inertial sensors attached at swimmer's chest level

摘要

Drowning incidents occurs even in the presence of professional lifeguards. In this research we aim to detect automatically near drowning pattern using information measured from pressure sensor, accelerometer and gyroscope attached at a swimmer chest level. For this we ask a professional lifeguard to imitate near drowning victims. Then we process the obtained data with neural networks. The obtained results show that the trained neural network succeed to classify automatically swimming and near drowning patterns.