Using bidirectional Binary Particle Swarm Optimization for feature selection in feature-level fusion recognition system

In feature-level fusion recognition system, there are two main missions. One is improving the recognition correct rate as soon as possible; the other is optimizing system sensor design to get outstanding cost performance. So feature selection become usually necessary to reduce dimensionality of the combination of multi-sensor features and improve system performance in system design. In general, the optimization is usually applied to feature selection because of its computational feasibility and validity. For further improving recognition accuracy and reducing selected feature dimensions, this paper presents a more rational and accurate optimization, bidirectional binary particle swarm optimization (BBPSO) algorithm for feature selection in feature level fusion target recognition system. In addition, we introduce a new evaluating function as criterion function in BBPSO feature selection method. At the last, we utilized leave-one-out method to validate the proposed method. The experiment results show that the proposed algorithm improves classification accuracy by two percentage points, while the selected feature dimensions are less one dimension than original particle swarm optimization approach with 16 original feature dimensions.