Direct measurements of blood glucose concentration in the presence of saccharide interferences using slope and bias orthogonal signal correction and Fourier transform near-infrared spectroscopy

2011 ◽  
Vol 16 (2) ◽  
pp. 027001 ◽  
Author(s):  
David Abookasis ◽  
Jerome J. Workman
Keyword(s):  
Fourier Transform ◽  
Infrared Spectroscopy ◽  
Blood Glucose ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Blood Glucose Concentration ◽  
Orthogonal Signal ◽  
Direct Measurements ◽  
Orthogonal Signal Correction ◽  
Signal Correction

Application of OSC in Sugar Content Evaluation of Chestnut Based on near Infrared Spectroscopy

2014 ◽  
Vol 701-702 ◽  
pp. 577-580
Author(s):  
Jie Liu ◽  
Xiao Yu Li ◽  
Wei Wang ◽  
Jun Zhang ◽  
Wei Zhou
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Sugar Content ◽  
Model Performance ◽  
Nir Spectroscopy ◽  
Orthogonal Signal ◽  
Orthogonal Signal Correction ◽  
Signal Correction ◽  
Validation Set

It is important in chestnut industry to evaluate the sugar content of nuts since sugar content is one of parameters for classifying the fruit to different productions. Previous work had proved the near infrared (NIR) spectroscopy could be used to measuring the sugar content in intact and peeled chestnut nondestructively; however, the performance of the predictive model would need more improvement. In this work, the orthogonal signal correction (OSC) algorithm was employed to optimize the predictive models. The results shown that, for the peeled chestnut sample, OSC could increase the correlation coefficient (R2) of validation set from 0.8649 to 0.8961while decrease the root mean and square error of prediction from 0.739 to 0.626. For the intact chestnut sample, this algorithm did not improve the model performance. The results indicated that the OSC had potential to optimized the prediction accuracy of sugar content in chestnut based on near infrared spectroscopy.

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.

scholarly journals Penerapan Teknologi Visible-Near Infrared Spectroscopy untuk Prediksi Cepat dan Simultan Kadar Air Buah Melon (Cucumis melo L.) Golden

Agroteknika ◽  
2020 ◽  
Vol 3 (2) ◽  
pp. 67-74
Author(s):  
Yuda Hadiwijaya ◽  
Kusumiyati Kusumiyati ◽  
Agus Arip Munawar
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Cucumis Melo ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Principal Component ◽  
Least Squares Regression ◽  
Orthogonal Signal Correction ◽  
Signal Correction ◽  
Cucumis Melo L

Kadar air merupakan salah satu atribut kualitas yang penting pada komoditas hortikultura. Penetapan kadar air buah melon dengan metode konvensional memakan waktu yang lama dan perlu merusak sampel buah. Penelitian ini bertujuan untuk memprediksi kadar air buah melon golden menggunakan teknologi visible-near infrared spectroscopy (Vis-NIRS). Metode koreksi spektra orthogonal signal correction (OSC) diterapkan pada spektra original untuk meningkatkan kehandalan model kalibrasi. Partial least squares regression (PLSR) digunakan sebagai metode pendekatan regresi untuk mengekstraksi data spektra Vis-NIRS. Hasil penelitian membuktikan bahwa Vis-NIRS dapat diandalkan untuk memprediksi kadar air buah melon golden. Metode koreksi spektra OSC mampu memperkecil jumlah principal component (PC) pada spektra original. Linieritas pada model kalibrasi menggunakan spektra OSC tercatat memperoleh nilai tertinggi sebesar 0,92. Ratio of performance to deviation (RPD) pada spektra OSC menampilkan nilai tertinggi pula yaitu 3,63. Model kalibrasi yang diperoleh pada penelitian ini dapat ditransfer ke dalam spektrometer Vis-NIRS untuk prediksi kadar air melon golden secara cepat dan simultan.

Sign in / Sign up

Export Citation Format

Share Document