Ground Vehicles Classification using Multi Perspective Features in FSR Micro-Sensor Network
Keywords:
Neural Network, Principal Component Analysis, Feature Extraction, Forward Scattering Radar, Classification Accuracy,Abstract
Automatic target classification (ATC) is examined from the viewpoint of improving classification accuracy. The challenge of automatic target classification is the selection of feature extraction (FE) technique, types of features and the type of classifier use. In this paper, the combination of Z-score and neural network (NN) is applied in order to perform the classification process for a ground target. The Z-score is used as a feature extractor where it will extract the significant data contain in the target’s signal and NN acts as a classifier to classify the targets based on their size. Different types of features are used in order to optimize the system performance. Results obtained demonstrate the improvement of classification performance when high number of features in the classification is used.Downloads
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)