Bayesian multiple response kernel regression model for high dimensional data and its practical applications in near infrared spectroscopy

2012 ◽  
Vol 56 (9) ◽  
pp. 2742-2755 ◽  
Author(s):  
Sounak Chakraborty
Keyword(s):  
Infrared Spectroscopy ◽  
Regression Model ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
High Dimensional Data ◽  
Kernel Regression ◽  
High Dimensional ◽  
Multiple Response ◽  
Practical Applications

Development of non-invasive blood glucose regression based on near-infrared spectroscopy combined with a deep learning method

2021 ◽  
Author(s):  
Zhuyu Wang ◽  
Linhua Zhou ◽  
Tianqing Liu ◽  
Kewei Huan ◽  
Xiaoning Jia
Keyword(s):  
Infrared Spectroscopy ◽  
Blood Glucose ◽  
Near Infrared Spectroscopy ◽  
Prediction Accuracy ◽  
Near Infrared ◽  
Blood Glucose Concentration ◽  
High Dimensional ◽  
Support Vector ◽  
Non Invasive ◽  
Blood Glucose Concentrations

Abstract Extracting micro-scale spectral features from dynamic blood glucose concentrations is extremely difficult when using non-invasive measurement methods. This work proposes a new machine-learning method based on near-infrared spectroscopy, deep belief network (DBN), and support vector machine (SVR), to improve the prediction accuracy. First, the standard oral glucose tolerance test is used to collect near-infrared spectroscopy and actual blood glucose concentration values for specific wavelengths (1200, 1300, 1350, 1450, 1600, 1610, and 1650 nm), and the blood glucose concentrations is within a clinical range of 70mg/dL~220mg/dL. Second, based on the DBN model, high-dimensional deep features of the non-invasive blood glucose spectrum are extracted. These are used to establish a support vector regression (SVR) model and to quantitatively analyze the influence of spectral sample size and corresponding feature dimensions (i.e., DBN network structure) on the prediction accuracy. Finally, based on data from six volunteers, a comparative analysis of the SVR prediction accuracy is performed both before and after using high-dimensional deep features. For volunteer 1, when the DBN-based high-dimensional deep features were used, the root mean square error (RMSE) of support vector regression (SVR) was reduced by 71.67%, the correlation coefficient (R2) and the P value of Clark grid analysis (P) were increased by 13.99% and 6.28%, respectively. Moreover, we have similar results when the proposed method was carried out on the data of other volunteers. The results show that the presented algorithm can play an important role in dynamic non-invasive blood glucose concentration prediction and can effectively improve the accuracy of the SVR model. Further, by applying the algorithm to six independent sets of data, this research also illustrates the high-precision regression and generalization capabilities of the DBN-SVR algorithm.

Sign in / Sign up

Export Citation Format

Share Document