Detection of anomalies in cycling behavior with convolutional neural network and deep learning.

Background: Cycling has always been considered a sustainable and healthy mode of transport. With the increasing concerns of greenhouse gases and pollution, policy makers are intended to support cycling as commuter mode of transport. Moreover, during Covid-19 period, cycling was further appreciated by citizens as an individual opportunity of mobility. Unfortunately, bicyclist safety has become a challenge with growing number of bicyclists in the 21st century. When compared to the traditional road safety network screening, availability of suitable data for bicycle based crashes is more difficult. In such framework, new technologies based smart cities may require new opportunities of data collection and analysis. Methods: This research presents bicycle data requirements and treatment to get suitable information by using GPS device. Mainly, this paper proposed a deep learning-based approach "BeST-DAD" to detect anomalies and spot dangerous points on map for bicyclist to avoid a critical safety event (CSE). BeST-DAD follows Convolutional Neural Network and Autoencoder (AE) for anomaly detection. Proposed model optimization is carried out by testing different data features and BeST-DAD parameter settings, while another comparison performance is carried out between BeST-DAD and Principal Component Analysis (PCA). Result: BeST-DAD over perform than traditional PCA statistical approaches for anomaly detection by achieving 77% of the F-score. When the trained model is tested with data from different users, 100% recall is recorded for individual user's trained models. Conclusion: The research results support the notion that proper GPS trajectory data and deep learning classification can be applied to identify anomalies in cycling behavior.