A Comparison of CNN and PLSR for Glucose Monitoring Using Mid-Infrared Absorption Spectroscopy  

作　　者：Baorong Fu Yongji Meng Xianwen Zhang Zhushanying Zhang Baorong Fu;Yongji Meng;Xianwen Zhang;Zhushanying Zhang(Wuhan Great Sea Hi-Tech Co., Ltd., Wuhan, China;College of Biomedical Engineering, South-Central Minzu University, Wuhan, China;Linyi Grepo Garden Machinery Co., Ltd., Linyi, China)

机构地区：[1]Wuhan Great Sea Hi-Tech Co., Ltd., Wuhan, China [2]College of Biomedical Engineering, South-Central Minzu University, Wuhan, China [3]Linyi Grepo Garden Machinery Co., Ltd., Linyi, China

出　　处：《Open Journal of Applied Sciences》2023年第3期383-395,共13页应用科学（英文）

摘　　要：With the development of mid-infrared (MIR) photoelectric devices, mid-infrared spectroscopy has become one of the important methods for non-invasive detection of blood glucose. The mid-infrared region (4000 - 400 cm^-1) has the well-known fingerprint region (1200 - 800 cm^-1) of glucose, which has clearer characteristic absorption peaks and better specificity. There is a lot of molecular information about glucose in the MIR. The non-invasive detection of blood glucose by mid-infrared spectroscopy needs to achieve certain accuracy, and the quantitative model is an important factor affecting the accuracy of glucose detection. In this paper, the samples of imitation solution containing only glucose and the samples of imitation mixed solution are taken as the research objects, and the mid-infrared spectral data of the samples are collected. The full spectrum partial least squares Regression (PLSR) model, SNV + Ctr-PLSR model, MSC + Ctr-PLSR model, and convolutional neural networks (CNN) model of 3000 - 900 cm^-1 band were constructed. Full spectrum PLS model and CNN model of 1200 - 900 cm^-1 band were constructed. The experimental results show that the optimal model of the two bands is CNN, then the correlation coefficient of prediction set (Rp) of 3000 - 900 cm^-1 band is 0.95, and the root mean square error of pre-diction set (RMSEP) value is 22.10. The Rp of 1200 - 900 cm^-1 band is 0.95, and the RMSEP value is 22.54. The research results show that CNN is a promising method, which has higher accuracy than PLSR, and is especially suitable for modeling human complex environment. In addition, the study provides a theoretical and practical basis for CNN in feature selection and model interpretation.With the development of mid-infrared (MIR) photoelectric devices, mid-infrared spectroscopy has become one of the important methods for non-invasive detection of blood glucose. The mid-infrared region (4000 - 400 cm^-1) has the well-known fingerprint region (1200 - 800 cm^-1) of glucose, which has clearer characteristic absorption peaks and better specificity. There is a lot of molecular information about glucose in the MIR. The non-invasive detection of blood glucose by mid-infrared spectroscopy needs to achieve certain accuracy, and the quantitative model is an important factor affecting the accuracy of glucose detection. In this paper, the samples of imitation solution containing only glucose and the samples of imitation mixed solution are taken as the research objects, and the mid-infrared spectral data of the samples are collected. The full spectrum partial least squares Regression (PLSR) model, SNV + Ctr-PLSR model, MSC + Ctr-PLSR model, and convolutional neural networks (CNN) model of 3000 - 900 cm^-1 band were constructed. Full spectrum PLS model and CNN model of 1200 - 900 cm^-1 band were constructed. The experimental results show that the optimal model of the two bands is CNN, then the correlation coefficient of prediction set (Rp) of 3000 - 900 cm^-1 band is 0.95, and the root mean square error of pre-diction set (RMSEP) value is 22.10. The Rp of 1200 - 900 cm^-1 band is 0.95, and the RMSEP value is 22.54. The research results show that CNN is a promising method, which has higher accuracy than PLSR, and is especially suitable for modeling human complex environment. In addition, the study provides a theoretical and practical basis for CNN in feature selection and model interpretation.

关 键 词：MID-INFRARED Convolutional Neural Networks (CNN) Partial Least Square Regression (PLSR) GLUCOSE 

分 类 号：TN2[电子电信—物理电子学]