The Application of Computational Auditory Peripheral Model in Underwater Target Classification

WANG Lei; PEN Yuan; LIN Zheng-qing; JIANG Xing-hai; MU Lin; ZHANG Feng-zhen

doi:10.3969/j.issn.0372-2112.2012.01.033

您当前的位置：

首页 >

文章列表页 >

The Application of Computational Auditory Peripheral Model in Underwater Target Classification

更新时间：2025-07-16

- The Application of Computational Auditory Peripheral Model in Underwater Target Classification
- Acta Electronica Sinica Vol. 40, Issue 1, Pages: 199-203(2012)
- 作者机构：
  
  水下测控技术重点实验室,辽宁,大连,116013
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2012.01.033
  CLC： TN911.7
- Published：2012
- 稿件说明：
移动端阅览
WANG Lei, PEN Yuan, LIN Zheng-qing, et al. The Application of Computational Auditory Peripheral Model in Underwater Target Classification[J]. Acta Electronica Sinica, 2012, 40(1): 199-203.
DOI：

WANG Lei, PEN Yuan, LIN Zheng-qing, et al. The Application of Computational Auditory Peripheral Model in Underwater Target Classification[J]. Acta Electronica Sinica, 2012, 40(1): 199-203. DOI： 10.3969/j.issn.0372-2112.2012.01.033.

摘要

听觉外周的理论和建模已取得长足的发展

并已广泛应用于语音信号处理.本文集成Gammatone听觉滤波器和Meddis内毛细胞模型来模拟耳蜗的处理机制

并根据水中目标辐射噪声信号的特点对Meddis模型的参数进行了修正.提出基于Gammatone-Meddis听觉外周计算模型的水中目标特征提取方法

得到一个23维的特征向量.对大量海上实测数据的分析表明该特征具有以下优点:(1)分类识别效果好

对测试集识别率达到94%以上;(2)抗卷积噪声能力强

对原始信号加入卷积噪声

识别能力没有下降.最后通过实验证明基底膜对频率的非线性选取和内毛细胞都能够很好地抑制噪声.

Abstract

The theory and model of auditory peripheral has made great progress

and has been widely used in speech signal processing.The text combined Gammatone filter and Meddis model to simulate processing mechanism of cochlear

and modified parameters of Meddis model according to the characteristics of underwater acoustic signals.Based on the Gammatone-Meddis auditory peripheral model

an approach to extract features from underwater target signal was presented.Then a twenty-three dimension feature vectors were obtained.With the feature vectors

the training and recognition processes was performed.The real sea experiments show that the features can classify effectively and the recognition ratio may arrive 94% above

that the features are robust and the capability of recognition does not decline when convolution noises are added to original signals.Finally

the experiments prove that both nonlinear selecting frequency by basement membrance and inner hair cells can restrain noise.

关键词

Keywords

references

Views

1662

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Shadow Profile Midline Phase Reconstruction and Its Identification Features Extraction for SISAR

Review on the Application of Metasurface-Based Impedance Matching Layer for Non-Destructive Testing Signal Enhancement

Multi-Angle ISAR Recognition Method for Space Targets Based on Feature Correlation of Key Components

Research on Dynamic Continuous Emotional Recognition of EEG Based on Improved TCNN Algorithm

Research on Lightweight Sensing Technology Based on Single Antenna and Multiple Subcarriers

Related Author

LUO Bin-feng

ZHANG Shou-hong

ZHANG Tao

LUO Yong-jian

HAO Tong

ZHENG Wu-an

LI Xiao-jing

YUAN Hao-xuan

Related Institution

Key Laboratory of Radar Signal Processing,Xidian University

Institute of Electronic,Navy Engineering University,Nanjin

Institute of Computing Technology,Chinese Academy of Sciences

Xi'an Communication Insititute

Key Laboratory of Radar Signal ProcessingXidian UniversityXi'anShaanxi 710071China

⁰