Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Computer Knowledge and Technology》 2018-02
Add to Favorite Get Latest Update

γSpectrum Feature Extraction and Nuclide Identification by K-SVD

LIU Hao-lin;YAO Yuan-cheng;ZHANG Jiang-mei;WANG Kun-peng;Southwest University of Science and Technology,College of Information Engineering of Sichuan Province;  
A method Based on K-SVD to construct a sparse atomic library is proposed in this paper and is used to extract features of radionuclide γ spectrum. A learning sparse dictionary is constructed by using K-SVD algorithm according to the characteristics of γ spectrum signal, and the sparse decomposition coefficient vector is used to characterize γ spectrum to realize feature extraction and nuclide identification. The experiments verify the feature extraction performance by comparing the recognition accuracy with the traditional methods using seven different classification algorithms including KNN algorithm, SVM algorithm and Decision Tree algorithm. The results show that the feature extraction by the method proposed in this paper has higher classification accuracy compared with the traditional methods.
【Fund】: 四川省科技厅项目(2016GZ0210)
【CateGory Index】: TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved