Deep-Sea Source Ranging Method Using Modified General Regression Neural Network
- 14 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1032-1037
Abstract
To improve the accuracy of deep-sea source ranging, this study proposes a deep-sea acoustic source localization algorithm based on particle swarm optimization (PSO)–general regression neural network (GRNN). The method optimizes the parameters of the GRNN model using the particle swarm algorithm to reduce the influence of artificially determined parameters on the performance of the GRNN. The normalized sample covariance matrices associated with the acoustic source location are used as the input for the neural network model, and the acoustic source range is the output. The PSO–GRNN method is validated using the results of deep-sea experiments conducted in the South China Sea in 2017 and compares the performance of underwater target range estimation with the results of traditional matched field processing and convolutional neural networks. The validation demonstrates that the PSO–GRNN method has high prediction accuracy and strong stability and is less prone to human error than traditional methods. Therefore, the method proposed in this study is effective for underwater target ranging in deep-sea environments.Keywords
Funding Information
- Youth Innovation Promotion Association
- Chinese Academy of Sciences
- National Natural Science Foundation of China
This publication has 13 references indexed in Scilit:
- Underwater acoustic source localization using generalized regression neural networkThe Journal of the Acoustical Society of America, 2018
- Ship localization in Santa Barbara Channel using machine learning classifiersThe Journal of the Acoustical Society of America, 2017
- Source localization in an ocean waveguide using supervised machine learningThe Journal of the Acoustical Society of America, 2017
- Multi-frequency sparse Bayesian learning for robust matched field processingThe Journal of the Acoustical Society of America, 2017
- Particle swarm optimization2014
- Robust linear matched field processor based on environmental perturbation in shallow water2006
- COMPUTATIONALLY EFFICIENT MONTE CARLO ESTIMATION ALGORITHMS FOR MATCHED FIELD PROCESSING IN UNCERTAIN OCEAN ENVIRONMENTSJournal of Computational Acoustics, 1994
- An overview of matched field methods in ocean acousticsIEEE Journal of Oceanic Engineering, 1993
- A general regression neural networkIEEE Transactions on Neural Networks, 1991
- Environmentally tolerant beamforming for high-resolution matched field processing: Deterministic mismatchThe Journal of the Acoustical Society of America, 1990