Combining prediction methods with cyber information for proactive route recommendation

We propose a proactive route recommendation system based on Cyber-Physical system for vehicles. The system is capable of acquiring and analyzing data obtained from the automobile and the Internet. The system consists of two major technologies, prediction algorithms to estimate the driver's destination and route beforehand, and linkage of cyber information (driving events extracted from the Internet) towards the driver's estimated route. The system combines the two data in order to provide substitute routes information for evading driving events. We have developed prediction algorithms and information linking methods, and conducted evaluation with data obtained from drivers, also implemented a prototype application to validate the recommended routes.