Please use this identifier to cite or link to this item:
Title: Soft and evolutionary computation based data association approaches for tracking multiple targets in the presence of ECM
Authors: Satapathi, G.S.
Srihari, P.
Issue Date: 2017
Citation: Expert Systems with Applications, 2017, Vol.77, , pp.83-104
Abstract: This paper proposes two novel soft and evolutionary computing based hybrid data association techniques to track multiple targets in the presence of electronic countermeasures (ECM), clutter and false alarms. Joint probabilistic data association (JPDA) approach is generally used for tracking multiple targets. Fuzzy clustering means (FCM) technique was proposed earlier as an efficient method for data association, but its cluster centers may fall to local minima. Hence, new hybrid data association approaches based on fuzzy particle swarm optimization (Fuzzy-PSO) and fuzzy genetic algorithm (Fuzzy-GA) clustering techniques have been presented as robust methods to overcome local minima problem. The data association matrix is evaluated for all tracks using validated measurements obtained by phased array radar for four different cases applying four data association methods (JPDA, FCM, Fuzzy-PSO, and Fuzzy-GA). Therefore, two hybrid data association approaches are designed and tested for multi-target tracking using intelligent techniques. Experimental results indicate that Fuzzy-GA data association technique provides improved performance compared to all other methods in terms of position and velocity RMSE values (38.69% and 33.19% average improvement for target-1;31.17% and 9.68% average improvement for target-2) respectively for crossing linear targets case. However, FCM technique gives better performance in terms of execution time (94.88% less average execution time) in comparison with other three techniques(JPDA, Fuzzy-GA, and Fuzzy-PSO) for the case of linear crossing targets. Thus accomplishing efficient and alternative multiple target tracking algorithms based on expert systems. The results have been validated with 100 Monte Carlo runs. 2017 Elsevier Ltd
Appears in Collections:1. Journal Articles

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.