Heterogeneous Sensor Data Fusion for Target Classification Using Adaptive Distance Function


Atıcı B., Karasakal E. , Karasakal O.

in: Multiple Criteria Decision Making: Beyond the Information Age, Y.I. Topcu,Ö. Özaydın,Ö. Kabak,Ş. Önsel Ekici, Editor, Springer, London/Berlin , London, pp.1-35, 2021

  • Publication Type: Book Chapter / Chapter Research Book
  • Publication Date: 2021
  • Publisher: Springer, London/Berlin 
  • City: London
  • Page Numbers: pp.1-35
  • Editors: Y.I. Topcu,Ö. Özaydın,Ö. Kabak,Ş. Önsel Ekici, Editor

Abstract

Automatic Target Recognition (ATR) systems are used as decision 

support systems to classify the potential targets in military applications. These 

systems are composed of four phases, which are selection of sensors, preprocessing 

of radar data, feature extraction and selection, and processing of features to 

classify potential targets. In this study, the classification phase of an ATR system 

having heterogeneous sensors is considered. We propose novel multiple criteria 

classification methods based on the modified Dempster–Shafer theory. Ensemble 

of classifiers is used as the first step probabilistic classification algorithm. Artificial 

neural network and support vector machine are employed in the ensemble. Each 

non-imaginary dataset coming from heterogeneous sensors is classified by both 

classifiers in the ensemble, and the classification result that has a higher accuracy 

ratio is chosen for each of the sensors. The proposed data fusion algorithms are 

used to combine the sensors’ results to reach the final class of the target.We present 

extensive computational results that show the merits of the proposed algorithms.