Intellectual Vehicle Safety by Using Data Mining Techniques

Abstract

In the real-world problems, there is large amount of domain knowledge that can provide insights on a variety of features. On the other hand, many machine learning methods used on the data sets for their learning phase and do not take into account openly expressed domain knowledge. There are so many design phases and development of computer controlled automotive applications to improve safety, reduce accidents, increase traffic flow, and enhance comfort for drivers. Automakers are trying to make vehicles more intelligent by using embedding processors that can be used to implement Electronic and Control Software (ECS) for taking smart decisions on the road or supporting the driver in doing the same. These ECS applications are high-integrity, distributed and real-time in nature. Inter-Vehicle Communication and Road-Vehicle Communication (IVC/RVC) mechanisms will only add to this intelligence by enabling distributed implementation of these applications. This work proposes studies a type of application, namely Automatic Merge Control System, which ensures safe vehicle plan in the area where two roads interconnect. We have discussed two approaches for designing this system both aimed at minimizing the Driving-Time-To-Intersection (DTTI) of vehicles, focus to particular constraints for ensuring safety.