• Journal of Innovative Optical Health Sciences
  • Vol. 15, Issue 4, 2250022 (2022)
[in Chinese]1, [in Chinese]2, [in Chinese]2, [in Chinese]2, and [in Chinese]2、*
Author Affiliations
  • 1School of Pharmaceutical Sciences, Guangzhou Medical University, 1 Xinzao Road Guangzhou 511436, P. R. China
  • 2NMPA Key Laboratory of Rapid Drug Inspection Technology, Guangdong Institute for Drug Control, 766 Shenzhou Road, Guangzhou 510663, P. R. China
  • show less
    DOI: 10.1142/s1793545822500225 Cite this Article
    [in Chinese], [in Chinese], [in Chinese], [in Chinese], [in Chinese]. Multivariety and multimanufacturer drug identification based on near-infrared spectroscopy and recurrent neural network[J]. Journal of Innovative Optical Health Sciences, 2022, 15(4): 2250022 Copy Citation Text show less

    Abstract

    Near-infrared (NIR) spectral analysis, which has the advantages of rapidness, nondestruction and high-e±ciency, is widely used in the detection of feed, food and mineral. In terms of qualitative identification, it can also be used for the discriminant analysis of medicines. Long 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 in fields such as natural language processing, signal classification and video analysis. Since the effect of these variants in drug identification is still to be studied, this paper constructs a multiclassifier of these three variants, using compound α-keto acid tablets produced by four manufacturers and repaglinide tablets produced by five manufacturers as the research object. Then, 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 model. When the spectrum data are pre-processed by z-score normalization, the GRU-3 model has the best accuracy in all models. The BiLSTM models are better for analyzing high coincidence data. The method proposed in this paper can be further extended to other NIR spectroscopy data sets.
    [in Chinese], [in Chinese], [in Chinese], [in Chinese], [in Chinese]. Multivariety and multimanufacturer drug identification based on near-infrared spectroscopy and recurrent neural network[J]. Journal of Innovative Optical Health Sciences, 2022, 15(4): 2250022
    Download Citation