AN INTELLIGENT SYSTEM FOR DETECTING SPEED LIMIT VIOLATION IN VEHICULAR AD-HOC NETWORKS

Abstract

Excessive speed is a factor in one third of all fatal crashes. In Nigeria, over speeding is a major contributing factor to fatal crashes. Over the years, traffic authorities such as Federal Road Safety Corps (FRSC) in Nigeria have engaged in visual identification of traffic offenders, which cannot work everywhere and every time. Millions of people are dying in vehicle accidents. In this research, a vehicle speed detection system was designed using the capabilities of an Arduino MEGA Microcontroller board. Other components of this system are IR sensors, batteries, Variable Resistors, Wires, Buzzer, LED (Light Emitting Diodes) and a 2 by 16 LCD Screen. Also, a fuzzy Model for the intelligent detection of a Vehicle Speed limit violation is developed. This model is a rule-based model that determines the vehicle speed violation by considering road and vehicle variable conditions. The output of the vehicle speed detection module is fed as one of the three inputs into the fuzzy logic-based vehicle speed limit system (FVSLS). The main interest has been on building fuzzy relationship models that are expressed by a set of fuzzy linguistic propositions derived from the experience of experts. Simulation was performed with Simulink in Matlab. The model components are linked up in Matlab R2018a using the Simulink interface so that simulation results can be seen and components parameters can be simply varied in order to experiment on different values. Simulation of the system is shown in the obtained outputs. Performance evaluation of the developed system is presented using the following metrics. Precision, Recall, Overall Precision, Overall Recall, Average Precision and Average Recall. The values for Precision and Recall, ranges from 0 to 1, where 0 indicates the worst value and 1 indicates the best value. The obtained precision degree of 0.96 and average recall degree of 0.86 indicates that the developed intelligent speed limit violation detection system has high precision and recall.