局域自適應(yīng)子波高斯神經(jīng)網(wǎng)絡(luò)綜合分類系統(tǒng)
A LOCAL ADAPTIVE WAVELET AND GAUSS NEURAL NETWORK SYNTHESIS CLASSIFICATION SYSTEM
-
摘要: 本文提出了一種用于船舶噪聲分類的局域自適應(yīng)子波高斯神經(jīng)網(wǎng)絡(luò)綜合分類系統(tǒng)。該系統(tǒng)融合了兩種特征提取和分類方法,即自適應(yīng)子波神經(jīng)網(wǎng)絡(luò)和自適應(yīng)高斯神經(jīng)網(wǎng)絡(luò)分類器,并利用網(wǎng)絡(luò)局域化使得系統(tǒng)具有追加學(xué)習(xí)的能力。通過對(duì)實(shí)際的三類船舶噪聲進(jìn)行分類識(shí)別,結(jié)果令人滿意,證明了該方法的優(yōu)越性和工程應(yīng)用前景。Abstract: In this paper, an efficient engineering classification of ship noises based on a local adaptive wavelet and Gauss neural network synthesis classification system is presented. The classification systems combine two methods of feature extraction and classification, which are adaptive wavelet neural network and adaptive Gauss neural network. It is capable of learning new types of signals and not destroying the learned network. The classification system is used to extract automatically feature from and classify for noises radiated from actual three types of ships. The classified results are encouraging, and this method is proved to be superior and efficient engineering application in the future.
-
Hassob J C, Chen C H. On constructing an expert system for contact, localization and tracking[J].Pattern Recognition.1985, 18(6):465-473[2]丁東譯.一種基于神經(jīng)網(wǎng)絡(luò)的聲吶目標(biāo)分類系統(tǒng).聲學(xué)技術(shù),1993, 12(2): 42-45.[3]Moore F. Passive sonar target recognition using a back-propagation neural network: [Thesis]. Monterey, California: Naval Post-graduate School, June, 1991.[4]富冬蕾.神經(jīng)網(wǎng)絡(luò)用于被動(dòng)聲吶信號(hào)分類研究:[碩士論文].西安:西北工業(yè)大學(xué),1992年.[5]張艷寧,孫進(jìn)才,等.一種基于自適應(yīng)子波神經(jīng)網(wǎng)絡(luò)的船舶噪聲分類方法.西安:西北工業(yè)大學(xué)學(xué)報(bào),15(1): 120-124.[6]張艷寧,孫進(jìn)才,等.用于船舶噪聲分類的自適應(yīng)局域高斯神經(jīng)網(wǎng)絡(luò)分類器.西安:西北工業(yè)大學(xué)學(xué)報(bào),14(增刊):172-176. -
計(jì)量
- 文章訪問數(shù): 2184
- HTML全文瀏覽量: 123
- PDF下載量: 603
- 被引次數(shù): 0
下載:
