RESULT PAPER: DRIVE NOW TEXT LATER, DETECTION OF CAB DRIVER ACTIVITY WHILE DRIVING

Abstract

Now a day’s use of Mobile Phone is one of the top dangerous behaviour for drivers. There are so many systems and Android applications are Implement to detect such type of behaviour of driver. For identifying this type of behaviour detection our system to be practical, a key property is its capability to distinguish driver’s mobile phone from passengers’. In previous systems the problems generally rely on user’s manual input, or utilize specific localization devices to determine whether a mobile phone is at driver’s location. In this paper, we have proposed a new approach which is able to automatically detect use of Mobile Device without using any extra devices. Our idea is very simple: when a user is trying to composing messages, the sensors (i.e. gyroscopes, accelerometers, and GPS) of smart phone embedded for collecting the associated information such as touch strokes, holding orientation and vehicle speed. After that this information will be analysed to see whether there exist some specific Test and Driving patterns. We will get the results that our approach can achieve good detection accuracy with low false positive rate.