Abstract
Characterizing risky driving behavior is crucial in a connected vehicle environment, particularly to improve driving experience through enhanced safety features. Artificial intelligence-backed solutions are vital components of the modern transportation. However, such systems require significant volume of driving event data for an acceptable level of performance. To address the issue, this study proposes a novel framework for precise risky driving behavior detection that takes advantage of an attention-based neural network model. The proposed framework aims to recognize five driving events including harsh brake, aggressive acceleration, harsh left turn and harsh right turn alongside the normal driving behavior. Through numerical results, it is shown that the proposed model outperforms the state-of-the-art solutions by reaching an average accuracy of 0.96 and F1-score of 0.92 for all classes of driving events. Thus, it reduces the false positive instances compared to the previous models. Furthermore, through extensive experiments, structural details of the attention-based neural network is investigated to provide the most viable configuration for the analysis of the vehicular sensory data.
Highlights
With the advent of connected and autonomous driving paradigm, detection of risky driving behavior has become an essential component in a connected vehicle setting [1]
Driving event characterization systems as the fundamental basis of accident prevention models coupled with low latency vehicular connectivity provided by 5G and Beyond [2] can be utilized in intelligent transportation systems (ITS) for centralized traffic control systems
A major building block of an intelligent transportation system is the Artificial Intelligence (AI) backbone to detect the behavior of the system entities [4]
Summary
With the advent of connected and autonomous driving paradigm, detection of risky driving behavior (e.g., harsh cornering, harsh braking, aggressive acceleration) has become an essential component in a connected vehicle setting [1]. Neural networks can overcome the shortcomings of the previous issues concerning accuracy and reliability in the detection of various event types from vehicular sensory data, the lack of anomalous driving patterns to properly train a neural network for the task remains a challenge. This article substantially differs from the previous work by proposing a novel solution for the first time to characterize risky driving behavior using limited vehicular sensor data while minimizing the false positives which are the primary factors for low reliability of a detection system. To this end, an attention-based auto-encoder network is proposed to reconstruct and precisely classify driving event data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
