Application of artificial intelligence in the rapid determination of moisture content in medicine food homology substances.

Journal: Food chemistry
PMID: 40112726

Abstract

Moisture content is crucial in quality testing of medicine food homology substances. This study aimed to present a new modeling method for moisture content based on near-infrared spectroscopy. When comparing three methods of partial least squares regression, support vector regression and convolutional neural network (CNN) to build moisture content prediction models of three different substances, it was found that the accuracy was affected by systematic error and was low. Thus, this study integrated moisture characteristic bands data of three substances and established a universal model. The optimal prediction model was SSA-CNN-BiLSTM. The RMSEP value of test set were 0.3568 %, 0.2057 % and 0.0029 %, and RPD value were 10.26, 2.30 and 5.60, respectively. The innovation of this study was that the above method improved modeling accuracy and efficiency. It eliminated systematic errors when each substance was modeled individually, simplified the modeling process, and expanded the scope of model application.

Authors

  • Mengyu Zhang
    School of Pharmacy, Southwest Medical University, Luzhou 646000, China.
  • Boran Lin
    Beijing Fresenius Kabi Pharmaceutical Co.,Ltd, Beijing, 102600, China.
  • Shudi Zhang
    NMPA Key Laboratory for Technology Research and Evaluation of Drug Products, Institute of Biochemical and Biotechnological Drug. School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan 250012, Shandong, China.
  • Cheng Peng
    School of Electrical and Mechanical Engineering, Hefei Technology College, Hefei, China.
  • Chang Li
    Bioengineering College of Chongqing University, Chongqing University Central Hospital (Chongqing Emergency Medical Center), Chongqing, China.
  • Tingting Feng
    NMPA Key Laboratory for Technology Research and Evaluation of Drug Products, School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, 250012, China.
  • Lian LI
  • Aoli Wu
    NMPA Key Laboratory for Technology Research and Evaluation of Drug Products, School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, 250012, China.
  • Chunguo Yang
    Shandong Yifang Pharmaceutical Co. Ltd., Linyi, 276000, Shandong, China.
  • Wentian Wang
    State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, CAMS Key Laboratory of Gene Therapy for Blood Diseases, Tianjin Key Laboratory of Gene Therapy for Blood Diseases, Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Tianjin, China.
  • Shouyao Huang
    Shandong Yifang Pharmaceutical Co. Ltd., Linyi, 276000, Shandong, China.
  • Lei Nie
    NMPA Key Laboratory for Technology Research and Evaluation of Drug Products, School of Pharmaceutical Sciences, Shandong University, Jinan 250012, China.
  • Hengchang Zang
    NMPA Key Laboratory for Technology Research and Evaluation of Drug Products, School of Pharmaceutical Sciences, Shandong University, Jinan 250012, China.

Keywords

External Resources

Popular Topics
Recent Journals