Multiple Criteria Target Classification Using Heterogeneous Sensor Data

2019-06-17
Karasakal, Orhan
Atıcı, Bengü
Karasakal, Esra
Radar systems have important roles in both military and civilian applications. As the capabilities increase in terms of range, sensitivity and the number of tracks to be handled, the requirement for automatic target recognition (ATR) increase. 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 the radar data, feature extraction and selection, and processing of features to classify the potential target. In this study, we focus on the classification phase of ATR and develop a novel multiple criteria classification method based on modified Dempster Shafer data fusion algorithm. Ensemble of classifiers are used as a classification algorithm. They are treated as the state of the art technology for classification in which each single classifier is trained separately, and then the results of them are combined through several fusion algorithms. Support vector machine and neural network are employed as probabilistic classifiers in ensemble. Each non-imaginary dataset coming from multiple heterogeneous sensors is classified by both of the classifiers in the ensemble, and the classification result that has higher accuracy ratio is chosen for each of the sensor dataset. After getting probabilistic classification of targets by different sensors, modified Dempster Shafer data fusion algorithm is used to combine the sensors’ results to reach the final classification of the targets. In this talk, a number of classification algorithms are compared with the proposed algorithm and the results will be discussed.
Citation Formats
O. Karasakal, B. Atıcı, and E. Karasakal, “Multiple Criteria Target Classification Using Heterogeneous Sensor Data,” presented at the 25th International Conference on Multiple Criteria Decision Making, (16 June 2019), İstanbul, Türkiye, 2019, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/76172.