CHEMOMETRIC ANALYSIS OF DIFFUSE REFLECTANCE SPECTRAL DATA USING SINGULAR VALUE DECOMPOSITION FOR BLOOD GLUCOSE DETECTION

2018 ◽  
Vol 30 (05) ◽  
pp. 1850027
Author(s):  
S. Vasanthadev Suryakala ◽  
Shanthi Prince
Keyword(s):  
Blood Glucose ◽  
Singular Value Decomposition ◽  
Diffuse Reflectance ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Singular Value ◽  
The Body ◽  
Measuring System ◽  
Clinical Method ◽  
Value Decomposition

Diabetes mellitus is a metabolic disorder that affects the production or usage of insulin by the body. Diabetes prevails in the body as a long-term condition which causes several other disorders if left unnoticed. Proper control of Diabetes needs continuous monitoring. The current measurement technique is invasive in nature and requires the withdrawal of blood from the body. Periodic quantification of blood glucose leads to pain and discomfort for the subject. This paper presents a non-invasive glucose measuring system using near-infrared diffuse reflectance spectroscopy (DRS). This work attempts to determine the blood glucose value from the diffuse reflected spectra in the NIR region. The study is executed with the spectral signatures of 33 diabetic subjects collected non-invasively using diffuse reflectance spectrometer from a diabetic centre. Blood glucose level of the same subjects are also recorded using the clinical method. The spectral information is subjected to standard normal variate (SNV) preprocessing method to remove baseline drift and then dimension reduction using singular value decomposition (SVD) is applied to the preprocessed data. The extracted singular values when compared with the clinically measured blood glucose is found to have a proportional relationship. The proposed study using singular value decomposition paves us the way for estimating the blood glucose value non-invasively with the obtained set of clinical blood glucose and the corresponding singular value table as a standard reference set.

scholarly journals Noninvasive Prediction of Glucose by Near-Infrared Diffuse Reflectance Spectroscopy

1999 ◽  
Vol 45 (9) ◽  
pp. 1651-1658 ◽  
Author(s):  
Stephen F Malin ◽  
Timothy L Ruchti ◽  
Thomas B Blank ◽  
Suresh N Thennadil ◽  
Stephen L Monfre
Keyword(s):  
Blood Glucose ◽  
Wavelength Range ◽  
Standard Error ◽  
Diffuse Reflectance ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Reflectance Spectroscopy ◽  
Calibration Model ◽  
Calibration Models ◽  
Blood Glucose Concentrations

Abstract Background: Self-monitoring of blood glucose by diabetics is crucial in the reduction of complications related to diabetes. Current monitoring techniques are invasive and painful, and discourage regular use. The aim of this study was to demonstrate the use of near-infrared (NIR) diffuse reflectance over the 1050–2450 nm wavelength range for noninvasive monitoring of blood glucose. Methods: Two approaches were used to develop calibration models for predicting the concentration of blood glucose. In the first approach, seven diabetic subjects were studied over a 35-day period with random collection of NIR spectra. Corresponding blood samples were collected for analyte analysis during the collection of each NIR spectrum. The second approach involved three nondiabetic subjects and the use of oral glucose tolerance tests (OGTTs) over multiple days to cause fluctuations in blood glucose concentrations. Twenty NIR spectra were collected over the 3.5-h test, with 16 corresponding blood specimens taken for analyte analysis. Results: Statistically valid calibration models were developed on three of the seven diabetic subjects. The mean standard error of prediction through cross-validation was 1.41 mmol/L (25 mg/dL). The results from the OGTT testing of three nondiabetic subjects yielded a mean standard error of calibration of 1.1 mmol/L (20 mg/dL). Validation of the calibration model with an independent test set produced a mean standard error of prediction equivalent to 1.03 mmol/L (19 mg/dL). Conclusions: These data provide preliminary evidence and allow cautious optimism that NIR diffuse reflectance spectroscopy using the 1050–2450 nm wavelength range can be used to predict blood glucose concentrations noninvasively. Substantial research is still required to validate whether this technology is a viable tool for long-term home diagnostic use by diabetics.

Noninvasive Blood Glucose Assay by Near-Infrared Diffuse Reflectance Spectroscopy of the Human Inner Lip

1993 ◽  
Vol 47 (7) ◽  
pp. 875-881 ◽  
Author(s):  
R. Marbach ◽  
Th. Koschinsky ◽  
F. A. Gries ◽  
H. M. Heise
Keyword(s):  
Blood Glucose ◽  
Glucose Concentration ◽  
Diffuse Reflectance ◽  
Near Infrared ◽  
Multivariate Calibration ◽  
Diffuse Reflectance Spectroscopy ◽  
Blood Glucose Concentration ◽  
Venous Blood ◽  
Time Lag ◽  
Blood Glucose Concentrations

Near-infrared (NIR) spectra of the human inner lip were obtained by using a special optimized accessory for diffuse reflectance measurements. The partial-least squares (PLS) multivariate calibration algorithm was applied for linear regression of the spectral data between 9000 and 5500 cm−1 (Λ = 1.1–1.8 μm) against blood glucose concentrations determined by a standard clinical enzymatic method. Calibration experiments with a single person were carried out under varying conditions, as well as with a population of 133 different patients, with capillary and venous blood glucose concentration values provided. A genuine correlation between the blood glucose concentrations and the NIR-spectra can be proven. A time lag of about 10 min for the glucose concentration in the spectroscopically probed tissue volume vs. the capillary concentration can be estimated. Mean-square prediction errors obtained by cross-validation were in the range of 45 to 55 mg/dL. An analysis of different variance factors showed that the major contribution to the average prediction uncertainty was due to the reduced measurement reproducibility, i.e., variations in lip position and contact pressure. The results demonstrate the feasibility of using diffuse reflectance NIR-spectroscopy for the noninvasive measurement of blood glucose.

In VivoNoninvasive Measurement of Blood Glucose by Near-Infrared Diffuse-Reflectance Spectroscopy

2003 ◽  
Vol 57 (10) ◽  
pp. 1236-1244 ◽  
Author(s):  
Katsuhiko Maruo ◽  
Mitsuhiro Tsurugi ◽  
Mamoru Tamura ◽  
Yukihiro Ozaki
Keyword(s):  
Blood Glucose ◽  
Diffuse Reflectance ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Reflectance Spectroscopy

scholarly journals Applying singular value decomposition technique for quantifying the insects in commercial Thai Hommali Rice from NIR Spectrum

2017 ◽  
Vol 10 (02) ◽  
pp. 1650047 ◽  
Author(s):  
Puttinun Jarruwat ◽  
Prasan Choomjaihan
Keyword(s):  
Statistical Analysis ◽  
Singular Value Decomposition ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Singular Value ◽  
Economic Losses ◽  
Insect Infestation ◽  
Mathematical Methods ◽  
Rice Samples ◽  
Value Decomposition

Insect infestation in rice stock is a significant issue in rice exporting business, resulting in the loss of product quality, nutrient as well as the economic losses. However, detecting the insect contamination with the traditional sorting techniques were destructive, inaccurate, time consuming and unable to detect the internal insect infestation. This study used near infrared (NIR) spectroscopy for obtaining the absorbent spectra from the insect contamination in two kinds of rice samples, Milled Hommali rice (MHR) and Brown Hommali rice (BHR). The mathematical methods of partial least squares (PLSs) regression and singular value decomposition (SVD) were employed to construct the predicting model. The statistical analysis results, R2, RMSEP, RPD and bias, concluded that the predictive models from PLS for MHR and BHR were 0.95 and 0.90, 0.014 and 0.019, 4.79 and 3.11, as well as [Formula: see text]0.007 and −0.008, respectively; while the statistical analysis results from SVD for MHR and BHR were 0.97 and 0.96, 0.012 and 0.013, 5.71 and 5.39, as well as [Formula: see text]0.003 and 0.002, respectively. It showed that SVD technique performed better than PLS technique which shows that using the advantage of SVD technique required less amounts of wave numbers for predicting and was possible to construct the low cost handheld equipment for detecting the insects in rice samples.

scholarly journals Hybrid EEG-fNIRS BCI Fusion Using Multi-Resolution Singular Value Decomposition (MSVD)

2020 ◽  
Vol 14 ◽  
Author(s):  
Muhammad Umer Khan ◽  
Mustafa A. H. Hasan
Keyword(s):  
Singular Value Decomposition ◽  
Near Infrared ◽  
Hybrid Approach ◽  
Singular Value ◽  
Functional Near Infrared Spectroscopy ◽  
Multiple Datasets ◽  
Novel Approach ◽  
Feature Based ◽  
Value Decomposition ◽  
Bci System

Brain-computer interface (BCI) multi-modal fusion has the potential to generate multiple commands in a highly reliable manner by alleviating the drawbacks associated with single modality. In the present work, a hybrid EEG-fNIRS BCI system—achieved through a fusion of concurrently recorded electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals—is used to overcome the limitations of uni-modality and to achieve higher tasks classification. Although the hybrid approach enhances the performance of the system, the improvements are still modest due to the lack of availability of computational approaches to fuse the two modalities. To overcome this, a novel approach is proposed using Multi-resolution singular value decomposition (MSVD) to achieve system- and feature-based fusion. The two approaches based up different features set are compared using the KNN and Tree classifiers. The results obtained through multiple datasets show that the proposed approach can effectively fuse both modalities with improvement in the classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document