Development of a cycling safety services system and its deep learning bicycle crash model

Abstract

This research developed an Internet of things (IoT) services system for cyclists to keep them safe when cycling — from terminal to back end — called the cycling safety services system. The proposed system consists of wearable devices, a service mobile app, and back-end services, primarily providing three categories of services: (1) The cycling team services, (2) the physiological status services, and (3) the environmental information service, incorporating the technologies of deep learning, IoT end device development, mobile app programming, RESTful API implementation, open data exploitation, etc. The proposed system aims at protecting the cyclists from being left out when cycling as a team, warning them when their physiological status is going to be abnormal or when there is a possibility of a bicycle crash, as well as proactively sending out urgent messages with location information when a crash occurs. Moreover, to enable the mobile app to recognize crash events, this research trained a deep learning bicycle crash model of 87.8049% accuracy and implemented a procedure in the mobile app based on this model to detect bicycle crashes automatically. The proposed system also provides a way for the cyclists to report any false crash alarm so that the crash model can be re-trained to reduce its false alarm ratio after the system is distributed to the consumers in the future. This research confirmed that the proposed system works well, and suggests that the proposed system, the crash model, the data collection method with its associated mobile apps, and the anonymous crash locations collected in the future can be valuable and contribute to the cycling society and relevant researchers in a positive way.