Dr. Shuang Tu of Jackson State University is leading a STRIDE project that aims to develop a computational pipeline of a near-crash diagnostic system to identify near-crash events. The STRIDE-funded project is titled “Automatic Safety Diagnosis in Connected Vehicle Environment”.

“The system exclusively uses raw Basic Safety Messages (BSMs) in the Connected Vehicle (CV) environment to determine if the driver deviates from their normal driving pattern and then generates reliable warnings when a conflict is identified,” Dr. Tu said.

Dr. Tu hopes to be able to apply Big Data techniques to determine the type of information that can be stored, extracted, and processed from the BSMs for real-time, near-crash diagnosis. He also plans to evaluate individual driver behavior and incorporate that element as an anomaly detection technique into the BSM analysis. He also plans to combine the Traffic Conflict Identification Technology with the BSM real-time traffic safety diagnosis.

It is expected that this project will generate a near-crash diagnostic system that will be able to identify conflicts and generate warnings to drivers by processing BSMs in the connected vehicle environment.

In essence, Dr. Tu’s research will provide valuable benefits to researchers, practitioners, and society at large. Through this research drivers will be alerted to potential crashes in real-time and the rate of false warnings could be reduced. This could also have a significant impact on non-recurrent traffic congestion because the crashes could potentially be avoided by the warnings.

“This research is a significant contribution as more and more CVs are coming online, and there is a strong need for the type of system proposed,” Dr. Tu said.  “The research team has taken a systems approach, going from the collected raw BSM data all the way to the warning messages sent to the individual drivers.”