Next Article in Journal
Twenty Years of Entropy Research: A Bibliometric Overview
Next Article in Special Issue
Underwater Bearing-Only and Bearing-Doppler Target Tracking Based on Square Root Unscented Kalman Filter
Previous Article in Journal
Why the Tsirelson Bound? Bub’s Question and Fuchs’ Desideratum
Previous Article in Special Issue
A New Feature Extraction Method for Ship-Radiated Noise Based on Improved CEEMDAN, Normalized Mutual Information and Multiscale Improved Permutation Entropy
Open AccessArticle

A Feature Extraction Method of Ship-Radiated Noise Based on Fluctuation-Based Dispersion Entropy and Intrinsic Time-Scale Decomposition

by 1, 1,* and 2
1
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China
2
Department of Computer & Information of Science & Engineering, University of Florida, Gainesville, FL 32611, USA
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(7), 693; https://doi.org/10.3390/e21070693
Received: 20 June 2019 / Revised: 12 July 2019 / Accepted: 13 July 2019 / Published: 15 July 2019
(This article belongs to the Special Issue Entropy and Information Theory in Acoustics)
To improve the feature extraction of ship-radiated noise in a complex ocean environment, fluctuation-based dispersion entropy is used to extract the features of ten types of ship-radiated noise. Since fluctuation-based dispersion entropy only analyzes the ship-radiated noise signal in single scale and it cannot distinguish different types of ship-radiated noise effectively, a new method of ship-radiated noise feature extraction is proposed based on fluctuation-based dispersion entropy (FDispEn) and intrinsic time-scale decomposition (ITD). Firstly, ten types of ship-radiated noise signals are decomposed into a series of proper rotation components (PRCs) by ITD, and the FDispEn of each PRC is calculated. Then, the correlation between each PRC and the original signal are calculated, and the FDispEn of each PRC is analyzed to select the Max-relative PRC fluctuation-based dispersion entropy as the feature parameter. Finally, by comparing the Max-relative PRC fluctuation-based dispersion entropy of a certain number of the above ten types of ship-radiated noise signals with FDispEn, it is discovered that the Max-relative PRC fluctuation-based dispersion entropy is at the same level for similar ship-radiated noise, but is distinct for different types of ship-radiated noise. The Max-relative PRC fluctuation-based dispersion entropy as the feature vector is sent into the support vector machine (SVM) classifier to classify and recognize ten types of ship-radiated noise. The experimental results demonstrate that the recognition rate of the proposed method reaches 95.8763%. Consequently, the proposed method can effectively achieve the classification of ship-radiated noise. View Full-Text
Keywords: ship-radiated noise; fluctuation-based dispersion entropy (FDispEn); instrinsic time-scale decomposition (ITD); proper rotation component (PRC); feature extraction ship-radiated noise; fluctuation-based dispersion entropy (FDispEn); instrinsic time-scale decomposition (ITD); proper rotation component (PRC); feature extraction
Show Figures

Figure 1

MDPI and ACS Style

Li, Z.; Li, Y.; Zhang, K. A Feature Extraction Method of Ship-Radiated Noise Based on Fluctuation-Based Dispersion Entropy and Intrinsic Time-Scale Decomposition. Entropy 2019, 21, 693.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop