Discrimination of Armeniacae Semen Amarum from different processed products and various rancidness degrees by electronic nose and support vector machine
(2.Beijing Boda Lvzhou Medical Technology Co., Ltd., Beijing, China 101113)
(3.Beijing University of Chinese Medicine, Beijing, China 102488)
【Abstract】This study was aimed to develop a simple, rapid and reliable method for identifying Armeniacae Semen Amarum from different processed products and various rancidness degrees. The objective odor information of Armeniacae Semen Amarum was obtained by electronic nose. 105 batches of Armeniacae Semen Amarum samples were studied, including three processed products of Armeniacae Semen Amarum, fried Armeniacae Semen Amarum and peeled Armeniacae Semen Amarum, as well as the samples with various rancidness degrees: without rancidness, slight rancidness, and rancidness. The discriminant models of different processed products and rancidness degrees of Armeniacae Semen Amarum were established by Support Vector Machine(SVM), respectively, and the models were verified based on back estimation of blind samples. The results showed that there were differences in the characteristic response radar patterns of the sensor array of different processed products and the samples with different rancidness degrees. The initial identification rate was 95.90% and 92.45%, whilst validation recognition rate was 95.38% and 91.08% in SVM identification models. In conclusion, differentiation in odor of different processed and rancidness degree Armeniacae Semen Amarum was performed by the electronic nose technology, and different processed and rancidness degrees Armeniacae Semen Amarum were successfully discriminated by combining with SVM. This research provides ideas and methods for objective identification of odor of traditional Chinese medicine, conducive to the inheritance and development of traditional experience in odor identification.
【Keywords】 Armeniacae Semen Amarum; rancidness; processed products; electronic nose; odor; support vector machine;
 Chinese Pharmacopoeia Commission. Chinese Pharmacopoeia. Vol. One [S]. Beijing: China Medical Science Press, 2015 (in Chinese).
 GU G G. 神农本草经 [M]. Lanzhou: Lanzhou University Press, 2009: 113 (in Chinese).
 WANG Z, JIANG D F, ZHANG Y, et al. Study on Prescription Characteristics of Chinese Patent Medicines for Antitussive Effect [J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2013, 15 (08): 1759 (in Chinese).
 TANAKA R, NITTA A, NAGATSU A. Application of a quantitative 1H-NMR method for the determination of amygdalin in Persicae Semen, Armeniacae Semen, and Mume Fructus [J]. J Nat Med, 2014, 68 (1): 230.
 GONG J T, ZHAO L Y, RUDOLF B, et al. Rancidness of Armeniacae Semen Amarum involving Bianzhuang Lunzhi [J]. China Journal of Chinese Materia Medica, 2016, 41 (23): 4375 (in Chinese).
 DONG X H. 苦杏仁泛油后有效成分的改变[J]. Chinese Journal of Hospital Pharmacy, 1993, 7 (11): 514 (in Chinese).
 LI Q Y. 论中药材的走油与检验 [C]. Harbin: 2004年全国中药研究暨中药房管理学术研究会, 2004 (in Chinese).
 ZOU H Q, GONG J T, ZHAO L Y, et al. Quality and quantity classification models of Fructus Amomi applying electronic nose with multiple mathematical statistics methods [J]. Journal of International Pharmaceutical Research, 2015, 42 (04): 513 (in Chinese).
 VAPNIK V. Statistical learning theory [M]. New York: Wiley, 1998: 401.
 ZHOU Z H. 机器学习 [M]. Beijing: Tsinghua University Press, 2016: 298 (in Chinese).
 LI H. 统计学习方法 [M]. Beijing: Tsinghua University Press, 2012: 95 (in Chinese).
 ZHANG B Y. Overview of Support Vector Machine Theory and Application Research [J]. Wireless Internet Technology, 2015, (19): 111 (in Chinese).
 ZHAO L Y. 基于电子鼻技术苦杏仁 “走油” 预警模型的建立 [D]. Beijing: Beijing University of Chinese Medicine, 2017 (in Chinese).
 ZHANG J Y, ZHANG Z. 中国果树志·杏卷 [M] Beijing: China Forestry Press, 2003: 38 (in Chinese).
 COSTACHE G N, COLORAN P. Combining PCA-based datasets without retraining of the basis vector set [J]. Pattern Recogn Lett, 2009, 30 (16): 1441.
 TAO M L, GU W T, WANG Z Q, et al. Discrimination of Cotidis Rhizoma from different habitats by support vector machine [J]. Chinese Traditional and Herbal Drugs, 2015, 46 (21): 3173 (in Chinese).
 GONG J T, ZOU H Q, WANG J Y, et al. Rapid identification research on Angelica sinensis from different producing areas based on electronic nose technology [J]. China Medical Herald, 2019, 16 (28): 39 (in Chinese).
 XIONG Y, XIAO X H, ZOU H Q, et al. Quality control of Lonicera japonica stored for different months by electronic nose [J]. J Pharmaceut Biomed, 2014, 91: 68.
 GONG J T, WANG J Y, LI L, et al. Identification of Curcuma herbs using XGBoost algorithm in electronic nose odor fingerprint [J]. China Journal of Chinese Materia Medica, 2019, 44 (24): 5375 (in Chinese).
 ZOU H Q, LI S, YAN Y H, et al. Rapid Identification of Traditional Chinese Medicine Using Electronic Nose Based on RBF-RF Cascade Classifier [J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2013, 15 (09): 1876 (in Chinese).
 LI W L, ZHANG Y, LIU H B, et al. Research progress on quality control methods of traditional Chinese medicine glues [J]. China Journal of Chinese Materia Medica, 2019, 44 (13): 2748 (in Chinese).
 YAO Y F, XIONG Y Y, XIONG W C, et al. Plant Identification of Different Growth Forms of Justicia procumbens and Comparison of Their Chemical Components Content [J]. Chinese Journal of Experimental Traditional Medical Formulae, 2019, 25 (21): 140 (in Chinese).
 PU J Z, ZHANG Y Z, ZHU Y L, et al. Quality Evaluation of Galli Gigerii Endothelium Corneum by Allele-specific PCR Method [J]. Chinese Journal of Experimental Traditional Medical Formulae, 2019, 25 (17): 142 (in Chinese).