|
Identification on Adulteration of Rice Seeds by Terahertz Time- Domain Spectroscopy Based on Multi Feature Algorithm Selection |
|
View Full Text Download reader |
DOI: |
KeyWord:terahertz time-domain spectroscopy pattern recognition rice seeds feature selection adulteration identification |
Author | Institution |
JIE Zhao-wei,ZHOU Shi-rui,WANG Ji-fen,KONG Yi-qing,LI Wen-ping,SHAO Zuo-shan |
1. School of Investigation,People’s Public Security University of China,Beijing ,China; 2. School of Crime,People’s Public Security University of China,Beijing ,China; 3. Anti Doping Center of General Administration of Sport of China,Beijing ,China; 4. Qingdao Qingyuanfengda Terahertz Technology Co.,Ltd.,Qingdao ,China |
|
Hits: 733 |
Download times: 1182 |
Abstract: |
A rice seed pattern recognition method based on terahertz time-domain spectroscopy was proposed in this paper in order to crack down on illegal elements peddling unqualified rice seeds in qualified seeds to obtain illegal profits.Compared with traditional methods,the terahertz time-domain spectroscopy was fast,time-saving and non-destructive,which could meet the needs of front-line law enforcement personnel for rapid detection of samples.In the experiment,10 kinds of rice seeds containing mixed adulteration of different brands were selected as samples,and the terahertz time-domain spectral data of the samples were collected.Meanwhile,relief,random forest(RF),support vector machine recursive feature elimination(SVM-RFE) and maximum relation minimum redundancy(mRMR) models were established to select the spectral wavelengths of the samples,respectively.Finally,a classifier was designed to classify and identify the samples processed by the four feature selection methods.The experimental results showed that the extreme learning machine(ELM) model optimized based on the cuckoo search(CS) algorithm had the best recognition effect on the sample spectral data extracted by the random forest feature selection algorithm,with an accuracy reaching 100%.The experiment is of a certain reference significance for the identification of seed adulteration in the field of forensic science. |
Close |