Comparative Experiments to Evaluate a CHMM-Based Identification Approach to Naval Targets

Abstract

This paper reports a comparative study between two well-known identification engines, continuous hidden Markov model (CHMM) and artificial neural network (ANN) to identify the naval target. Mel frequency cepstral coefficients (MFCCs) are selected as the studied features. The general Gaussian density distribution HMM was developed for CHMM system. Elman network was developed for the ANN system. We studied the effect of speed, distance and direction of the target on the identification process. The results had shown that CHMM gives the best identification rate (IR) at 91.67% while changing range,100% while changing direction and 58.3% while changing the speed which is better than 75%, 83.33% and 41.67% of ANN for the same set of experiments using simulated targets data. Also, when using real target data CHMM achieves 100% IR which is higher than 73.68% of ANN.