Wearable Airbag System for Real-Time Bicycle Rider Accident Recognition by Orthogonal Convolutional Neural Network (O-CNN) Model

As demand for bicycles increases, bicycle-related accidents are on the rise. There many items such as helmets and racing suits bicycles, but people do not wear even if they most basic safety protection. To protect rider from accidents, technology is needed to measure rider’s motion condition in real time, determine whether an accident has occurred, cope with accident. This paper describes artificial intelligence airbag. The airbag a system that measures real-time conditions of bicycle using six-axis sensor judges prevent neck injuries. MPU 6050 used understand changes movement normal conditions. angle determined by measured data happened or analyzing acceleration angle. In this paper, similar methods (NN, PNN, CNN, PNN-CNN) compared orthogonal convolutional neural network (O-CNN) method terms performance judgment accuracy situations. networks were applied verified reliability advance.