Motorbike Driving Activity Recognition Using Smartphone Motion Sensors

Motorbike driving activity recognition plays a crucial role in various domains, including rider safety, vehicle diagnostics, and driver behavior analysis. Traditional methods for activity recognition often rely on dedicated sensors or on-board systems, which can be expensive, cumbersome, or limited in terms of availability. In recent years, the widespread use of smartphones with built-in motion sensors has opened up new possibilities for activity recognition in a more cost-effective and accessible manner. This paper presents a novel approach for motorbike driving activity recognition using smartphone motion sensors. Motorcyclist are inquired to take after a predefined way for recording accelerometer and gyroscope data. Twelve factual features are extricated to classify four driving events i.e., right turn, left turn, U-turn, and a straight path. Four machine learning classifiers i.e., Bayes Net, K-nearest neighbor, support vector machine, and random forest is utilized to classify motorbike driving events. The findings indicate that fusing of a gyroscope and accelerometer can significantly improve the detection of bike driving occurrences, achieving a noteworthy precision rate of 92.13%.