基于小波包能量谱和SVM的水下目标识别

为了提高舰船辐射噪声信号分类的准确率,即在水下进行舰船目标识别的准确率,采用了小波包提取信号能量谱特征的方法和支持向量机的分类算法.简介了小波包变换及支持向量机的基本原理,然后针对舰船辐射噪声信号进行多层小波包分解,提取各子频段能量谱作为特征量,归一化处理后构建特征向量,最后用支持向量机算法进行分类.仿真实验结果表明,利用对信号的多层小波包分解提取能量谱特征和支持向量机的分类算法能对舰船辐射噪声信号进行有效识别.

Underwater Target Recognition Based on Wavelet Packet Energy Spectrum and Support Vector Machine

To increase the accuracy of classification through signals radiated by ship noise,namely to recognize ship’s type under the water,the feature extraction method of wavelet packets transform(WPT) and classification algorithm of support vector machine(SVM) are adopted in the paper.The basic principles of WPT and SVM are briefly introduced at first.Then the signals of ship radiated are preprocessed and filtered by WPT and the wavelet packets energy spectrum feature parameters are extracted from sub-frequency-bands after WPT.At last,the characteristic vector is established with normalization process and the signals are classified by SVM.The simulation experiment results demonstrate that,the ship radiated signals can be classified or recognized availably based on WPT and SVM.