Feature extraction and fusion of acoustic and seismic sensors for target identification

The U.S. Army Research Laboratory (ARL) is developing an acoustic target classifier using a backpropagation neural network algorithm. Various techniques for extracting features have been evaluated to improve the confidence level and probability of correct identification. Some techniques used in the past include simple power spectral estimates (PSEs), split-window peak-picking, harmonic line association (HLA), principal component analysis, wavelet packet analysis, and others. In addition, improved results have been obtained when data are combined from other sensors co- located with the acoustic sensor. A three-axis seismic sensor has been configured as part of an acoustic sensor array that ARL uses on typical field experiments, with data collected and sampled simultaneously. The PSE, HLA, and shape statistic feature data are extracted from a group of vehicles and then split into testing and training files. The training file typically consists of 75 percent of the data set, and the performance of the trained neural network is evaluated with the remaining test data. Cross-validation is performed with vehicle data collected at different times of delay and under various conditions. Results of the neural network from a few of the feature extraction algorithms under evaluation and from the fusion of the acoustic and seismic sensor data are presented.