A Novel Compound Feature based Driver Identification

In today's world, it is time to identify the driver through technology. At present, possible find out driving style of drivers from every car controller area network (CAN-BUS) sensor data which was not conventional car. Many researchers did their work and main purpose end-to-end analysis CAN-BUS data. So, potential each individually based on driver's style. We propose a novel compound feature-based identification reduce number input attributes some mathematical operation. Now, role machine learning in field any type incomparable significant. The state-of-the-art algorithms have been applied different fields. Occasionally these are tested similar domain. As result, we used prominent learning, show results aspiration model. other goal this study compare conspicuous classification index performance metrics behavior identification. Hence, SVM, Naïve Bayes, Logistic Regression, k-NN, Random Forest, Decision tree, Gradient boosting.