Fuzzy System Model for Management of Driver Distractions in Motor Vehicles

Adnan Shaout and Dominic Colella The Electrical and Computer Engineering Department The College of Engineering and Computer Science The University of Michigan Dearborn Dearborn, MI [email protected]; [email protected] -------------------------------------------------------------------------ABSTRACT------------------------------------------------------------------In this paper a low cost and driver’s environment friendly design of a Fuzzy Logic software system to manage driver distractions in a motor vehicle is presented. The system uses four inputs; vehicle speed, radio volume setting, frequency of left or right hand turns per minute and brightness conditions external to the vehicle. The system provides a single output in the form of a Driver Attention Load rating. This rating is used as a parameter to determine the degree to which the driver’s environment needs to be adjusted in terms of radio volume level, brightness of instrument cluster display and reducing the amount of connected phone interruptions per minute. The Fuzzy Inference Software System is modeled and simulated using MATLAB. After simulation, the final system and associated graphical user interface are designed as a standalone application written in Java. An open source Java library called jFuzzyLogic is used to model the Fuzzy Inference System and the Java Swing toolkit is used for the design of the graphical user interface.