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

Abstract

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 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 [Formula: see text]-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 pre-processed 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 [Formula: see text]-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.