Sonar Data Classification Using Neural Network Trained by Hybrid Dragonfly and Chimp Optimization Algorithms

This paper proposes a hybrid Dragonfly Algorithm (DA) for training Multi-Layer Perceptron Neural Network (MLP NN) to design the classifier solving complicated problems and distinguishing real target from liars’ targets in sonar applications. Due improve cost computation reducing waste of time, modified low-cost DA is designed evaluation. To assess accuracy technique, some well-known meta-heuristic trainers include Chimp Optimization Algorithm, Gravitational Search (GSA), DA, Particle Swarm (PSO) compared show similar algorithms. ChoA algorithms have remarkable features algorithm them proposed. The proposed has acceptable performance, two standard benchmark datasets are used evaluate performance. results that DA-ChoA 15% less time-consuming 4% better performance rather than original dragonfly method.