By means of factor analysis approach, a method of molecule classification is built based on the measured terahertz absorption spectra of the molecules. A data matrix can be obtained by sampling the absorption spectra at different frequency points. The data matrix is then decomposed into the product of two matrices: a weight matrix and a characteristic matrix. By using the K-means clustering to deal with the weight matrix, these molecules can be classified. A group of samples (spirobenzopyran, indole, styrene derivatives and inorganic salts) has been prepared, and measured via a terahertz time-domain spectrometer. These samples are classified with 75% accuracy compared to that directly classified via their molecular formulas. (C) 2018 Published by Elsevier B.V.
基金：
National Natural Science Foundation of China [11574105, 61475054, 61405063, 61177095]; Hubei Science and Technology Agency Project [2015BCE052]
第一作者单位：[1]Huazhong Univ Sci & Technol, Wuhan Natl Lab Optoelect, Wuhan 430074, Hubei, Peoples R China
通讯作者：
推荐引用方式(GB/T 7714)：
Huang Jianglou,Liu Jinsong,Wang Kejia,et al.Classification and identification of molecules through factor analysis method based on terahertz spectroscopy[J].SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY.2018,198:198-203.doi:10.1016/j.saa.2018.03.017.
APA：
Huang, Jianglou,Liu, Jinsong,Wang, Kejia,Yang, Zhengang&Liu, Xiaming.(2018).Classification and identification of molecules through factor analysis method based on terahertz spectroscopy.SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY,198,
MLA：
Huang, Jianglou,et al."Classification and identification of molecules through factor analysis method based on terahertz spectroscopy".SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 198.(2018):198-203
