How it works
RideSafe needs accelerometer and gyroscope data to detect bikers' falls.
Once the lib installed and configured on your app, this will listen for new accelerometer and gyroscope events, storing them in memory (very tiny footprint) before shipping them to the backend.
Backend & algorithm
The RideSafe backend is in charge of receiving data from clients. It is Spring Boot + Kotlin based application backed by Cassandra database
Fall algorithm detection will be available soon.
Our smartphones have accelerometers to measure gyroscope and acceleration forces of individuals, these data can be used to analyse the behaviour: when walking, running, biking and even falling!
The self learning algorithms are able to improve the detection of a fall by analysing such data.
Thanks to professionals and Nousmotards users we will collect fall data. Data and algorithm will be available under the Apache license, this means that the changes and improvements made will be communicated to the community. Commercial use is unrestricted.
The project is based on the work of Ludwine Probst and Amira Lakhal which detects one type of activity from the accelerometer integrated in smartphones and a self-learning algorithm called machine learning. With data collected we will be able to detect rider's activities and falls.
Mobile networks are not available everywhere, the last step of this project is to embedded algorithm on the mobile and update it regularly from server data.
Senior developer and Speed Triple rider
Senior developer, R1 and Crosstourer rider
Senior DevOps, Z1000 and Hornet rider
I drive a motorbike, so there is the whiff of the grim reaper round every corner, especially in London.
Maybe the bike is more dangerous, but the passion for the car for me is second to the bike.
Software innovation, like almost every other kind of innovation, requires the ability to collaborate and share ideas with other people, and to sit down and talk with customers and get their feedback and understand their needs.