Paper Details

Texting-while-driving (TD) is one of the top dangerous behaviors for drivers. Many interesting systems andmobile phone applications have been designed to help to detect or combat TD. However, for a TD detection system to bepractical, a key property is its capability to distinguish driver’s mobile phone from passengers. Existing solutions to thisproblem generally rely on user’s manual input, or utilize specific localization devices to determine whether a mobilephone is at drivers’ location. In this paper, we propose a method which is able to detect TD automatically without usingAny extra devices. The main idea of our proposed system very straight forward: when a user is composing messages, thesmartphone embedded sensors (i.e. gyroscopes, accelerometers, and GPS) collect the associated information such astouch strokes, holding orientation and vehicle speed. This information will then be analyzed to see whether there existsome specific TD patterns. This type of experiments have been conducted by different persons and in different drivingcases. The results show that our goal can achieve a good detection and accuracy with low Negative rate. Besides beinginfrastructure free and with high accuracy, this method does not access any content of messages and therefore isprivacy-preserving.

Swapnil Birdawade, Rushikesh Kohinkar, Pramod Shinalkar, Rajesh Suryawanshi, Prof. Deepak Gupta, “DRIVE NOW TEXT LATER, DETECTION OF CAB DRIVER ILLIGAL ACTIVITY WHILE DRIVING”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 5, Issue 10, pp. 177-180, October 2018.