Classification of THz Transmission Spectrum Based on Kevnel Function of Convex Combination
WANG Rui-qi1, SHEN Tao1,2*, MA Shuai1, GUO Jian-yi1, YU Zheng-tao1
1. Kunming University of Science and Technology, Faculty of Information and Automation, Kunming 650504, China 2. Kunming University of Science and Technology, Faculty of Materials and Engineering, Kunming 650093, China
Abstract:In the present paper, support vector machine (SVM) based on convex combination kernel function will be used for classification of THz pulse transmission spectra. Wavelet transform is used in data pre-processing. Peaks and valleys are regarded as location features of THz pulse transmission spectra, which are injected into maximum interval features of term frequency-inverse document frequency (TF-IDF). We can conclude weight of each sampling point from the information theory. The weight represents the possibility that sampling point becomes feature. According to the situation that different terahertz-transmission spectra are lack of obvious features, we composed a SVM classification model based on convex combination kernel function. Evaluation function should be used as an evaluation method for obtaining the parameters of optimal convex combination to achieve a better accuracy. When the optimal parameter of kenal founction was determined, we should compose the model for process of classification and prediction. Compared with the single kernel function, the method can be combined with transmission spectroscopic features with classification model iteratively. Thanks to the dimensional mapping process, outstanding margin of features can be gained for the samples of different terahertz transmission spectrum. We carried out experiments using different samples The results demonstrated that the new approach is on par or superior in terms of accuracy and much better in feature fusion than SVM with single kernel function.
[1] LIU Xiao-hong, ZHAO Hong-wei, LIU Gui-feng, et al(刘晓鸿, 赵红卫, 刘桂锋,等). Progress in Chemistry(化学进展), 2010, 22(11): 2191. [2] Zhang C, Mu K. Applications of Terahertz Spectroscopy. Infrared, Millimeter, and Terahertz Waves, 2009. IRMMW-THz 2009. 34th International Conference on. IEEE, 2009: 1-2. [3] Xie L,Yao Y, Ying Y. Applied Spectroscopy Reviews, 2014, 49(6): 448. [4] Naftaly M, Molloy J F, Lanskii G V, et al. Applied Optics, 2013, 52(19): 4433. [5] WANG Gao, XU De-gang, YAO Jian-quan(王 高, 徐德刚, 姚建铨). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2013,33(4): 886. [6] Takeuchi I, Shimakura K, Ohtake H, et al. Journal of Pharmaceutical Sciences, 2014, 103(1): 256. [7] Choi J, Ryu S Y, Kwon W S, et al. Journal of the Optical Society of Korea, 2013, 17(5): 454. [8] Yin X, Ng B W H, Fischer B M, et al. Sensors Journal, IEEE, 2007, 7(12): 1597. [9] ZHAO Shu-sen, CHEN Si-jia, SHEN Jing-ling(赵树森, 陈思嘉, 沈京玲). Chinese Journal of Lasers(中国激光), 2009, 36(3): 752. [10] THz Database Tera-Phtonics Laboratory, RIKEN Sendai, Date of Access: 2013. 5. 29. [11] anculef R, Flaounas I, Cristianini N. Expert Systems with Applications, 2014, 41(11): 5431. [12] Yang Y T, Fishbain B, Hochbaum D S, et al. INFORMS Journal on Computing, 2013, 26(1): 45. [13] Lin C, Chen X, Jian L, et al. Food chemistry, 2014, 162: 10. [14] Sun Z, Wang C, Li D, et al. Geoscience and Remote Sensing Letters, IEEE, 2014, 11(11): 1991. [15] Qian L, Zhou G. Journal of Biomedical Informatics, 2012, 45(3): 535. [16] Niu Y, Otasek D, Jurisica I. Bioinformatics, 2010, 26(1): 111. [17] Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, 2000. [18] Shawe-Taylor N, Kandola A. Advances in Neural Information Processing Systems, 2002, 1(4): 367.