Moving vehicle identification using artificial neural network

Abstract

Hearing impaired people cannot distinguish the sound from a moving vehicle approaching from their behind. They often face a risky situation while they are in outdoors. In this paper, a simple algorithm is proposed to classify the type and distance of the moving vehicles based on the sound signature recorded from the vehicles. A simple experimental protocol is designed to record the vehicle sound under different environment conditions and velocity of vehicles. The noises emanated from moving vehicles along the roadside were recorded along with the type and distance of the vehicle. Autoregressive modeling algorithm is used for the analysis to extract features from the recorded sound signal. Two simple Multilayer Perceptron (MLP) models are developed and trained using Backpropagation algorithm to classify the vehicle type and its distance. The effectiveness of the network is validated through stimulation.