The paper describes a fuzzy logic based system to predict the number of vehicle flow
based on its noise. The system equipped by a sensor using a microphone an a 8088
microprocessor. The prediction results are displayed on 7-segment display. The fuzzy inference
system used a strategy of MIN-MAX with 3 inputs which are: noise level, the width of road & a
correction factor. A Defuzzification method of COG (Center of Gravity) is depployed in the system
to produce prediction result in number of vehicle per minnute. The experimental results are
presented to figure out the performance of the prediction comparing to the actual number of
vehicle. The result shows that the prediction error of the system is about 7-10% comparing to the
prediction by using human ear resulting the error of 4-5%.