基于堆栈稀疏自编码融合核极限学习机的近红外光谱药品鉴别

引用本文: 张卫东, 李灵巧, 胡锦泉, 冯艳春, 尹利辉, 胡昌勤, 杨辉华. 基于堆栈稀疏自编码融合核极限学习机的近红外光谱药品鉴别[J]. 分析化学, 2018, 46(9): 1446-1454. doi: 10.11895/j.issn.0253-3820.171343 shu

Citation: ZHANG Wei-Dong, LI Ling-Qiao, HU Jin-Quan, FENG Yan-Chun, YIN Li-Hui, HU Chang-Qin, YANG Hui-Hua. Drug Discrimination by Near Infrared Spectroscopy Based on Stacked Sparse Auto-encoders Combined with Kernel Extreme Learning Machine[J]. Chinese Journal of Analytical Chemistry, 2018, 46(9): 1446-1454. doi: 10.11895/j.issn.0253-3820.171343 shu

基于堆栈稀疏自编码融合核极限学习机的近红外光谱药品鉴别

1.
桂林电子科技大学计算机与信息安全学院, 桂林 541004;
2.
北京邮电大学自动化学院, 北京 100876;
3.
中国食品药品检定研究院, 北京 100050
基金项目:
本文系国家自然科学基金项目（Nos.21365008，61562013）资助

摘要: 提出一种基于堆栈稀疏自编码融合核极限学习机（Stacked sparse auto-encoders combine kernel extreme learning machine，SSAE-KELM）的近红外药品鉴别方法，通过引入核极限学习机代替SSAE的Softmax分类和BP微调阶段，减少了模型的训练步骤、训练参数以及训练时间，提高了深度学习网络的实际应用能力，核函数的引入提高了模型的分类能力。其中，SSAE用于初始化整个网络模型，并且从输入数据中学习到有用的特征，KELM用于实现分类任务。研究了SSAE-KELM模型对不同厂商生产的同一包装形式（铝塑或非铝塑）药品鉴别的预测能力、稳定性及训练时间，以实现药品的二分类和多分类的无损鉴别。同时，与ELM、SSAE、BP、SVM及随机隐退深度信念网络（Dropout-DBN）进行对比。结果表明，无论是二分类还是多分类，SSAE-KELM不仅具有更优的分类能力和稳定性、还减少了训练时间。因此，SSAE-KELM是一种有效的光谱分类建模工具。

关键词:

English

Drug Discrimination by Near Infrared Spectroscopy Based on Stacked Sparse Auto-encoders Combined with Kernel Extreme Learning Machine

1.
College of Computer and Information Security, Guilin University of Electronic Technology, Guilin 541004, China;
2.
College of Automation, Beijing University of Posts & Telecommunications, Beijing 100876, China;
3.
National Institutes for Food and Drug Control, Beijing 100050, China
Received Date: 16 October 2017
Revised Date: 05 June 2018
Fund Project:
This work was supported by the National Natural Science Foundation of China (Nos. 21365008, 61562013).

Abstract: A method for drug discrimination with near infrared spectroscopy based on stacked sparse auto-encoders combined with kernel extreme learning machine (SSAE-KELM) was developed. By introducing the KELM instead of the SSAE's Softmax classification and BP fine-tuning stage, the training steps, training parameters and training time of the SSAE were reduced, and the practical application of the deep learning network was improved, as well the classification ability of the model was improved by introduction of kernel function. Among which SSAE was used to initialize the entire network model and learn useful features from the input data and KELM was used to perform the classification. To identify binary-classification and multi-classification of drugs, the predictability, stability and training time of SSAE-KELM model for the same package (Aluminum-plastic or non-Aluminum-plastic) drug by different manufactures were investigated. At the same time, SSAE-KELM was compared with ELM, SSAE, SVM, BP and Dropout-DBN, and it was found that SSAE-KELM not only reduced the training time but had higher classification accuracy and stability in binary and multi-class classification. Therefore, SSAE-KELM is an effective spectral classification modeling tool.

Key words:

1. [1]
  Vlachos N, Skopelitis Y, Psaroudaki M. Anal. Chim. Acta,2015, 573(1):459-465
2. [2]
  Risoluti R, Materazzi S, Gregori A. Talanta,2016, 153:407-413
3. [3]
  JING Tao, DAI Ying, MA Xiao-Juan, HUANG Bai-Biao. Chinese Optic,2016, 9(1):1-15 荆涛, 戴瑛, 马晓娟, 黄柏标.中国光学,2016, 9(1):1-15
4. [4]
  YUAN Jing-Ze, LU Qi-Peng, WANG Jing-Li, DING Hai-Quan, GAO Hong-Zhi, WU Chun-Yang, LI Wan-Xia. Chinese J. Anal. Chem.,2017, 45(9):1291-1296 袁境泽, 卢启鹏, 王静丽, 丁海泉, 高洪智, 吴春阳, 李晚侠.分析化学,2017, 45(9):1291-1296
5. [5]
  Mbinze J K, Sacré P Y, Yemoa A. J. Pharmaceut. Biomed. Anal.,2015, 111(26):21-27
6. [6]
  Storme-Paris I, Rebiere H, Matoga M. Anal. Chim. Acta,2010, 658(2):163-174
7. [7]
  Deconinck E, Sacré P Y, Coomans D. J. Pharmaceut. Biomed. Anal.,2012, 57(1):68-75
8. [8]
  Anzanello M J, Ortiz R S, Limberger R. Forensic Sci. Inter.,2014, 235(2):1-7
9. [9]
  LIU Zhen-Bing, JIANG Shu-Jie, YANG Hui-Hua, ZHANG Xue-Bo. Spectroscopy and Spectral Analysis,2014, 34(10):2815-2820 刘振丙, 蒋淑洁, 杨辉华, 张学博.光谱学与光谱分析,2014, 34(10):2815-2820
10. [10]
  Yang H, Hu B, Pan X, S Yan, Y Feng, Zhang X, Yin L, Hu C. J. Innovt. Opt. Health Sci.,2016,10(2):1630011
11. [11]
  Donahue J, Hendricks L A, Rohrbach M. IEEE Trans. Pattern Anal. Mach. Intell.,2017, 39(4):677-691
12. [12]
  Noda K, Yamaguchi Y, Nakadai K. Appl. Intell.,2015, 42(4):722-737
13. [13]
  Quintana M, Torres J, Menéndez J M. IEEE Transact. Intell. Transp. Syst.,2016,17(3):608-619
14. [14]
  YANG Hui-Hua, LUO Zhi-Chao, JIANG Shu-Jie, ZHANG Xue-Bo. Spectroscopy and Spectral Analysis,2016, 36:2274-2779 杨辉华, 雒志超, 蒋淑杰, 张学博.光谱学光谱分析,2016, 36:2274-2279
15. [15]
  WANG Ru-Jing, CHEN Tian-Jiao, WANG Yu-Bing, WANG Liu-San, XIE Cheng-Jun, ZHANG Jie, LI Rui, CHEN Hong-Bo. Chinese Journal of Luminescence,2017, 38(1):109-116. 王儒敬, 陈天娇, 汪玉冰, 汪六三, 谢成军, 张洁, 李瑞, 陈红波.发光学报,2017, 38(1):109-116.
16. [16]
  Tsinalis O, Matthews P M, Guo Y. Annals Biomed. Engineer.,2016,44(5):1587-1597
17. [17]
  Huang G B, Zhu Q Y, Siew C K. Neurocomputing,2006,70(1):489-501
18. [18]
  Huang G B, Zhou H Ding. IEEE Transact. Syst. Man Cy. B,2012,42(2):513-529
19. [19]
  Xu J, Xiang L, Liu Q. IEEE Transact. Med. Imaging,2016,35(1):119-130
20. [20]
  Zeng Y, Xu X, Shen D, Fang Y, Xiao Z. IEEE Transact. Intell. Transport. Syst.,2017,18(6):1647-1653

扫一扫看文章

计量

PDF下载量: 11
文章访问数: 439
HTML全文浏览量: 49

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于堆栈稀疏自编码融合核极限学习机的近红外光谱药品鉴别

English

Drug Discrimination by Near Infrared Spectroscopy Based on Stacked Sparse Auto-encoders Combined with Kernel Extreme Learning Machine

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

基于堆栈稀疏自编码融合核极限学习机的近红外光谱药品鉴别

English

Drug Discrimination by Near Infrared Spectroscopy Based on Stacked Sparse Auto-encoders Combined with Kernel Extreme Learning Machine

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs