Classification of underwater acoustical dataset using neural network trained by Chimp Optimization Algorithm

Due to the variability of the radiated signal of the underwater targets, the classification of the underwater acoustical dataset is a challenging problem in the real world application. In this paper, to classify underwater acoustical targets, first, a new meta-heuristic Chimp Optimization Algorithm...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied acoustics Jg. 157; S. 107005
Hauptverfasser: Khishe, M., Mosavi, M.R.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.01.2020
Schlagworte:
Chimp Optimization Algorithm
Classification
Multi-Layer Perceptron Neural Networks
Underwater acoustical dataset
Multi-Layer Perceptron Neural Networks
Underwater acoustical dataset
Classification
Chimp Optimization Algorithm
ISSN:0003-682X, 1872-910X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Due to the variability of the radiated signal of the underwater targets, the classification of the underwater acoustical dataset is a challenging problem in the real world application. In this paper, to classify underwater acoustical targets, first, a new meta-heuristic Chimp Optimization Algorithm (ChOA) inspired by chimp hunting behaviour is developed for training an Artificial Neural Network (ANN). Second, a new underwater acoustical dataset is developed using passive propeller acoustic data collected in a laboratory. To evaluate the proposed classifier, this algorithm is compared to the Ion Motion Algorithm (IMA), Gray Wolf Optimization (GWO), and a hybrid algorithm. Measured metrics are convergence speed, the possibility of trapping in local minimum and classification accuracy. The results show that the newly proposed algorithm in most cases provides better or comparable performance compared to the other benchmark algorithms.
ISSN:0003-682X
1872-910X
DOI:10.1016/j.apacoust.2019.107005