Abstract:Near infrared (NIR) spectroscopy combined with pattern recognition was attempted to discriminate the freshness of eggs. The algorithm of one-class support vector machine (OC-SVM) was employed to solve the classification problem due to imbalanced number of training samples. In this work, 86 samples of eggs (71 samples of fresh eggs and 15 samples of unfresh eggs) were surveyed by Fourier transform NIR spectroscopy. Firstly, original spectra of eggs in the wave-number range of 10 000-4 000 cm-1 were acquired. And then, principal component analysis (PCA) was employed to extract useful information from original spectral data, and the number of PCs was optimized. Finally, OC-SVM was performed to calibrate discrimination model, and the optimal PCs were used as the input eigenvectors of model. In order to obtain a good performance, the regularization parameter v and parameter σ of the kernel function in OC-SVM model were optimized in building model. The optimal OC-SVM model was obtained with ν=0.5 and σ2=20.3. Experimental result shows that OC-SVM got better performance than conventional two-class SVM model under the same condition. The OC-SVM model was achieved with identification rates of 80 for both fresh eggs and unfresh eggs in the independent prediction set. The identification rates of fresh eggs were 100% in two-class SVM model. However, when the two-class SVM model was used to discriminate the unfresh eggs of, the identification rates were 0% in the independent prediction set. Compared with conventional two-class SVM model, the OC-SVM model showed its superior performance in discrimination of minority unfresh eggs samples. This work shows that it is feasible to identify egg freshness using NIR spectroscopy, and OC-SVM is an excellent choice in solving the problem of imbalanced number of samples in training set.
Key words:Near infrared spectroscopy;One-class support vector machine;Identification;Egg;Freshness
林 颢,赵杰文*,陈全胜,蔡健荣,周 平 . 近红外光谱结合一类支持向量机算法检测鸡蛋的新鲜度 [J]. 光谱学与光谱分析, 2010, 30(04): 929-932.
LIN Hao, ZHAO Jie-wen*, CHEN Quan-sheng, CAI Jian-rong, ZHOU Ping . Identification of Egg Freshness Using Near Infrared Spectroscopy and One Class Support Vector Machine Algorithm . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(04): 929-932.
[1] Suman M, Rianib G, Dalcanale E. Sensors and Actuators B, 2007, 125:40. [2] Dutta R, Hines E L, Gardner J W, et al. Measurement Science and Technology, 2003,14:190. [3] JIN Xiang-jun, ZHANG Yong, XIE Yun-fei, et al(金向军, 张 勇, 谢云飞, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2009, 29(3):656. [4] ZOU Xiao-bo, ZHAO Jie-wen(邹小波, 赵杰文). Chinese Journal of Analytical Chemistry(分析化学), 2006, 34(9):1291. [5] Kemps C J, Bamelis F R, De Ketelaere B, et al. Journal of the Science of food and Agriculture,2006, 86:1399. [6] Giunchi A, Berardinelli A, Ragni L, et al. Journal of Food Engineering, 2008, 89:142. [7] Scholkopf B, Smola A J, Williamson R C. Neural Computation, 2000, 12(5):1207. [8] Wu R S, Chung W S. Expert Systems with Applications, 2009, 36:4451. [9] Bicegoa M, Figueiredo M A T. Pattern Recognition,2009, 42:27. [10] Scholkopf B, Platt J, Shawe-Taylor J, et al. Neural Computation,2001, 13(7):1443. [11] Manevitz L M, Yousef M. Journal of Machine Learning Research,2001, 2:139. [12] O’Farrell M, Lewisa E, Flanagana C, et al. Sensors and Actuators B, 2005, 17:104. [13] Chen Q S, Zhao J W, Fang C H, et al. Spectrochimica Acta Part A, 2007, 66:568. [14] Thissen U, Pepers M, üstün B, et al. Chemometrics and Intelligent Laboratory Systems,2004, 73:169. [15] CHEN Bin, FENG Ai-min, CHEN Song-can, et al(陈 斌, 冯爱民, 陈松灿,等). Chinese Journal of Computers(计算机学报),2007, 30(8):1325. [16] Fang S F, Wang M P, Qi Q H, et al. Computational Materials Science, 2008, 44:647. [17] Twellmanna T, Meyer-Baese A, Lange O, et al. Engineering Applications of Artificial Intelligence, 2008, 21:129. [18] WU C L, CHAU K W, LI H S. Journal of Hydrology, 2008, 358:96. [19] Guo S M, Chen L C, Tsai J S H. Pattern Recognition, 2009, 42:77. [20] YAN Dong-wei, SUN Tian-wen, YANG Yan, et al(燕东渭,孙田文,杨 艳, 等). Journal of Applied Meteorological Science(应用气象学报),2007,18(5):676. [21] HUANG Qian, WANG Zhen, WEI Tao, et al(黄 谦,王 震,韦 韬, 等). Computer Engineering(计算机工程),2006, 32(16):127. [22] Foody G M, Mathur A, Sanchez-Hernandez C, et al. Remote Sensing of Environment,2006, 104:1.