Multivariety and multimanufacturer drug identification based on near-infrared spectroscopy and recurrent neural network

作     者：Wenjie Zeng Yunqi Qiu Yanting Huang Qingping Sun Zhuoya Luo 

作者机构：School of Pharmaceutical Sciences Guangzhou Medical University 1 Xinzao Road Guangzhou 511436P.R.China NMPA Key Laboratory of Rapid Drug Inspection Technology Guangdong Institute for Drug Control 766 Shenzhou RoadGuangzhou 510663P.R.China 

出 版 物：《Journal of Innovative Optical Health Sciences》 (创新光学健康科学杂志（英文）)

年 卷 期：2022年第15卷第4期

页      面：86-96页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081704[工学-应用化学] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0817[工学-化学工程与技术] 070302[理学-分析化学] 0835[工学-软件工程] 0703[理学-化学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This research was supported by the Science and Technology Planning Project of Guangdong Province(Grant Nos.2017B020221002,2018B020207008 and 2021B1111610005) Science and Technology Planning Project of Guangzhou,Grant No.201707010410 

主　　题：Near-infrared spectroscopy long short-term memory bidirectional long short-term memory gated recurrent unit multiple classifiers. 

摘      要：Near-infrared(NIR)spectral analysis,which has the advantages of rapidness,nondestruction and high-efficiency,is widely used in the detection of feed,food and *** terms of qualitative identification,it can also be used for the discriminant analysis of *** short-term memory(LSTM)neural network,bidirectional long short-term memory(BiLSTM)neural network and gated recurrent unit(GRU)network are variants of the recurrent neural network(RNN).The potential relationship between nonlinear features learned from the sequence by these variants is used to complete the missions infields such as natural language processing,signal classification and video *** the effect of these variants in drug identification is still to be studied,this paper constructs a multiclassifier of these three variants,using compoundα-keto acid tablets produced by four manufacturers and repaglinide tablets produced by five manufacturers as the research ***,the paper analyzes the impacts of seven different preprocessed methods on the drug NIR data by constructing different layers of LSTM,BiLSTM and GRU networks and compares different classification model indicators and training time of each *** the spectrum data are pre-processed by z-score normalization,the GRU-3 model has the best accuracy in all *** BiLSTM models are better for analyzing high coincidence *** method proposed in this paper can be further extended to other NIR spectroscopy data sets.