Application of adaptive filter to noninvasive biochemical examination by near infrared spectroscopy

Qi-peng, 卢启鹏 Lu; Cong, 陈丛 Chen; Zhong-qi, 彭忠琦 Peng

doi:10.3788/ope.20122004.0873

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wavenumbers combination selection of NIR spectroscopy analysis was very important for designing discrete-type NIR spectroscopy instruments. We basically consider selecting at least three wavenumbers for complexity system analysis, more wavenumbers can provide more available information to improve the analytical accuracy, but would reduce models' stability, not vice versa [11]. On the other hand, equidistant discrete wavenumber combination can be pre-processed as the continuous spectrum to improve the accuracy.…”

Section: Resultsmentioning

confidence: 99%

Equidistant Five Wavenumbers Selection for NIR Spectroscopy Analysis of Glucose in Human Serum

Pan¹,

Xie²,

Yu³

et al. 2011

AMR

View full text Add to dashboard Cite

Using Fourier transform near-infrared (FTNIR) transmission spectroscopy and multiple linear regression (MLR) method of the equidistant wavenumbers combination, the quantitative analysis models of human serum glucose were established, and discrete wavenumbers combination was optimized. The optimal models were found in the five equidistant wavenumbers combinations with 7 and 40 gaps.The center wavenumber of the optimal models with 40 gaps in the first overtone region and combination region were 7970 and 5880 cm-1 respectively, and the corresponding RMSEP were 0.371 and 0.389 mmol/L respectively. While the center wavenumber of the optimal models with 7 gaps in the combination region and first overtone region were 5795 and 8041 cm-1 respectively, and the corresponding RMSEP were 0.395 and 0.407 mmol/L respectively. The above four models had a good prediction effect, and could provide basis for designing minitype special NIR spectroscopy instrument.

show abstract

Section: Resultsmentioning

confidence: 99%

Equidistant Five Wavenumbers Selection for NIR Spectroscopy Analysis of Glucose in Human Serum

Pan¹,

Xie²,

Yu³

et al. 2011

AMR

View full text Add to dashboard Cite

show abstract

Research on improving the accuracy of near infrared non-invasive hemoglobin detection

Yuan

Ding

Gao

et al. 2015

Infrared Physics & Technology

View full text Add to dashboard Cite

Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network

Ding¹,

Lu²,

Gao³

et al. 2014

Biomed. Opt. Express

View full text Add to dashboard Cite

To facilitate non-invasive diagnosis of anemia, specific equipment was developed, and non-invasive hemoglobin (HB) detection method based on back propagation artificial neural network (BP-ANN) was studied. In this paper, we combined a broadband light source composed of 9 LEDs with grating spectrograph and Si photodiode array, and then developed a high-performance spectrophotometric system. By using this equipment, fingertip spectra of 109 volunteers were measured. In order to deduct the interference of redundant data, principal component analysis (PCA) was applied to reduce the dimensionality of collected spectra. Then the principal components of the spectra were taken as input of BP-ANN model. On this basis we obtained the optimal network structure, in which node numbers of input layer, hidden layer, and output layer was 9, 11, and 1. Calibration and correction sample sets were used for analyzing the accuracy of non-invasive hemoglobin measurement, and prediction sample set was used for testing the adaptability of the model. The correlation coefficient of network model established by this method is 0.94, standard error of calibration, correction, and prediction are 11.29g/L, 11.47g/L, and 11.01g/L respectively. The result proves that there exist good correlations between spectra of three sample sets and actual hemoglobin level, and the model has a good robustness. It is indicated that the developed spectrophotometric system has potential for the non-invasive detection of HB levels with the method of BP-ANN combined with PCA.

show abstract

Application of adaptive filter to noninvasive biochemical examination by near infrared spectroscopy

Cited by 3 publications

References 0 publications

Equidistant Five Wavenumbers Selection for NIR Spectroscopy Analysis of Glucose in Human Serum

Equidistant Five Wavenumbers Selection for NIR Spectroscopy Analysis of Glucose in Human Serum

Research on improving the accuracy of near infrared non-invasive hemoglobin detection

Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network

Contact Info

Product

Resources

About