基于波形結(jié)構(gòu)特征和支持向量機(jī)的水面目標(biāo)識(shí)別
doi: 10.11999/JEIT150139
基金項(xiàng)目:
國(guó)家自然科學(xué)基金(11234002)資助課題
Recognition of Marine Acoustic Target Signals Based on Wave Structure and Support Vector Machine
-
摘要: 借鑒語(yǔ)音聲學(xué)的研究成果,音色可作為區(qū)分不同目標(biāo)的依據(jù)。由于艦船輻射噪聲的音色信息包含在其信號(hào)的波形結(jié)構(gòu)特征中,可以通過(guò)提取艦船輻射噪聲的波形結(jié)構(gòu)特征判斷目標(biāo)類型。該文對(duì)水面目標(biāo)信號(hào)時(shí)域波形結(jié)構(gòu)特征提取進(jìn)行了研究,構(gòu)建了基于信號(hào)統(tǒng)計(jì)特性的特征矢量,包括過(guò)零點(diǎn)波長(zhǎng)、峰峰幅度、過(guò)零點(diǎn)波長(zhǎng)差分以及波列面積等。應(yīng)用支持向量機(jī)(Support Vector Machine, SVM)作為分類器識(shí)別兩類水面目標(biāo)信號(hào),核函數(shù)為徑向基函數(shù)(RBF)。提出了差分進(jìn)化和粒子群算法的混合算法,優(yōu)化了懲罰因子和徑向基函數(shù)參數(shù)的選取,兩類目標(biāo)的識(shí)別率較常規(guī)的網(wǎng)格搜索法有顯著提高。
-
關(guān)鍵詞:
- 信號(hào)處理 /
- 水面目標(biāo)識(shí)別 /
- 波形結(jié)構(gòu)特征 /
- 支持向量機(jī) /
- 優(yōu)化算法
Abstract: According to research findings of speech acoustics, the timbre is applied to identify different types of targets. Since the information of timbre is indicated in the wave structure of time series, the feature of wave structure can be?extracted to classify various marine acoustic targets. The method of feature extraction based on wave structure is studied. The nine-dimension feature vector is constructed on the basis of signal statistical characteristics, including zero-crossing wavelength, peek-to-peek amplitude, zero-crossing-wavelength difference, wave train areas and so on. And the Support Vector Machine (SVM) is applied as a classifier for two kinds of marine acoustic target signals. The kernel function is set Radial Basis Function (RBF). The penalty?factor and parameter of RBF are properly selected by the method of combination of Differential Evolution (DE) and Particle Swarm Optimization (PSO), which helps to obtain better recognition rates than the grid search method. -
王志偉. 水下目標(biāo)被動(dòng)識(shí)別技術(shù)方法研究[D]. [碩士論文], 哈爾濱工程大學(xué), 2002. Wang Zhi-wei. The recognition study of passivity target[D]. [Master dissertation], Harbin Engineering University, 2002. 蔡悅斌, 張明之, 史習(xí)智, 等. 艦船噪聲波形結(jié)構(gòu)特征提取及分類研究[J]. 電子學(xué)報(bào), 1999, 27(6): 129-130. Cai Yue-bin, Zhang Ming-zhi, Shi Xi-zhi, et al.. The feature extraction and classification of ocean acoustic signals based on wave structure[J]. Acta Electronica Sinica, 1999, 27(6): 129-130. 廖明熙, 張小薊, 張歆. 基于稀疏表示的水聲信號(hào)分類識(shí)別[J]. 探測(cè)與控制學(xué)報(bào), 2014, 36(4): 67-70. Liao Ming-xi, Zhang Xiao-ji, and Zhang Xin. Classification and recognition of underwater acoustic signal based on sparse representation[J].Journal of Detection Control, 2014, 36(4): 67-70. 許文海, 續(xù)元君, 董麗麗, 等. 基于水平集和支持向量機(jī)的圖像聲吶目標(biāo)識(shí)別[J]. 儀器儀表學(xué)報(bào), 2012, 33(1): 49-55. Xu Wen-hai, Xu Yuan-jun, Dong Li-li, et al.. Level-set and SVM based target recognition of image sonar[J].Chinese Journal of Scientific Instrument, 2012, 33(1): 49-55. 史亞, 姬紅兵, 朱明哲, 等. 多核融合框架下的雷達(dá)輻射源個(gè)體識(shí)別[J]. 電子與信息學(xué)報(bào), 2014, 36(10): 2484-2490. Shi Ya, Ji Hong-bing, Zhu Ming-zhe, et al.. Specific radar emitter identification in multiple kernel fusion framework[J]. Journal of Electronics Information Technology, 2014, 36(10): 2484-2490. 丁凱, 方向, 張衛(wèi)平, 等. 基于聲信號(hào)多重分形和支持向量機(jī)的目標(biāo)識(shí)別研究[J]. 兵工學(xué)報(bào), 2012, 33(12): 1521-1526. Ding Kai, Fang Xiang, Zhang Wei-ping, et al.. Target identification of acoustic signals based on multi-fractal analysis and support vector machine[J]. Acta Armamentarii, 2012, 33(12): 1521-1526. 張啟忠, 席旭剛, 羅志增. 基于非線性特征的表面肌電信號(hào)模式識(shí)別方法[J]. 電子與信息學(xué)報(bào), 2013, 35(9): 2054-2058. Zhang Qi-zhong, Xi Xu-gang, and Luo Zhi-zeng. A pattern recognition method for surface electromyography based on nonlinear features[J]. Journal of Electronics Information Technology, 2013, 35(9): 2054-2058. Chen Ping-wei, Wang Yung-ying, and Lee Ming-hahn. Model selection of SVMs using GA approach[C]. Proceedings of 2004 IEEE International Joint Conference on Neural Networks, Pscataway, NJ, 2004: 2035-2040. 周紹磊, 廖劍, 史賢俊. RBF-SVM的核參數(shù)選擇方法及其在故障診斷中的應(yīng)用[J]. 電子測(cè)量與儀器學(xué)報(bào), 2014, 28(3): 240-246. Zhou Shao-lei, Liao Jian, and Shi Xian-jun. Kernel parameter selection of RBM-SVM and its application in fault diagnosis [J]. Journal of Electronic Measurement and Instrumentation, 2014, 28(3): 240-246. 鄭適, 張安學(xué), 岳思橙, 等. 基于改進(jìn)粒子群優(yōu)化的探地雷達(dá)波形反演算法[J]. 電子與信息學(xué)報(bào), 2014, 36(11): 2717-2722. Zheng Shi, Zhang An-xue, Yue Si-cheng, et al.. Ground penetrating radar inversion algorithm based on improved particle swarm optimization[J]. Journal of Electronics Information Technology, 2014, 36(11): 2717-2722. Fernandez P J A, Baeten V, Renier A M, et al.. Combination of support vector machines (SVM) and near-infrared (NIR) imaging spectroscopy for the detection of meat and bone meal (MBM) in compound feeds[J]. Journal of Chemometrics, 2004(18): 341-349. Cristianini N and Taylor J S. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambridge: The Press Syndicate of the University of Cambridge, 2001: 93-94. 廖曉晰. 動(dòng)力系統(tǒng)的穩(wěn)定性理論和應(yīng)用[M]. 北京:國(guó)防工業(yè)出版社, 2000: 169-199. Liao Xiao-xi. Stability Theory and Application of Power System[M]. Beijing: National Defence Industry Press, 2000: 169-199. 楊坤德. 水聲陣列信號(hào)的匹配場(chǎng)處理[M]. 西安: 西北工業(yè)大學(xué)出版社, 2008: 32-39. Yang Kun-de. Matched Field Processing of Underwater Acoustic Array Signals[M]. Xian: Press of Northwestern Polytechnical University, 2008: 32-39. 紀(jì)震,廖惠連,吳青華. 粒子群算法及應(yīng)用[M]. 北京: 科學(xué)出版社,2009: 169-199. Ji Zhen, Liao Hui-lian, and Wu Qing-hua. Application of Particle Swarm Algorithm[M]. Beijing: Science Press, 2009: 169-199. Clerc M. The swarm and the queen: towards a deterministic and adaptive particle swarm optimization[C]. Proceedings of the Congress of Evolutionary Computation. Washington, USA, 1999: 1951-1957. -
計(jì)量
- 文章訪問(wèn)數(shù): 1651
- HTML全文瀏覽量: 215
- PDF下載量: 579
- 被引次數(shù): 0