Joint Optimization of Savitzky-Golay Smoothing Models and Partial Least Squares Factors for Near-infrared Spectroscopic Analysis of Serum Glucose

Chen

et al. 2014

Self Cite

A new strategy for quantitative analysis of a major clinical biochemical indicator called glycated hemoglobin (HbA1c) was proposed. The technique was based on the simultaneous near-infrared (NIR) spectral determination of hemoglobin (Hb) and absolute HbA1c content (Hb HbA1c) in human hemolysate samples. Wavelength selections were accomplished using the improved moving window partial least square (MWPLS) method for stability. Each model was established using an approach based on randomness, similarity, and stability to obtain objective, stable, and practical models. The optimal wavebands obtained using MWPLS were 958 to 1036 nm for Hb and 1492 to 1858 nm for Hb HbA1c, which were within the NIR overtone region. The validation root mean square error and validation correlation coe±cients of prediction (V -SEP, V -R P ) were 3.4 g L À1 and 0.967 for Hb, respectively, whereas the corresponding values for Hb HbA1c were 0.63 g L À1 and 0.913. The corresponding V -SEP and V -R P were 0.40% and 0.829 for the relative percentage of HbA1c. The experimental results con¯rm the feasibility for the quanti¯cation of HbA1c based on simultaneous NIR spectroscopic analyses of Hb and Hb HbA1c.

Section: Optimization Frame Of the Mwpls Methodsmentioning

confidence: 99%

Quantification of glycated hemoglobin indicator HbA1c through near-infrared spectroscopy

Chen

et al. 2014

Self Cite

“…The selection of a reasonable F is both necessary and di±cult. 16,17 In this paper, F was selected by considering the number of divisions for the calibration and the prediction sets. Thus, the The corresponding parameters were denoted by B Ã , N Ã and F Ã , respectively, and the corresponding M-R P;Ave , M-SEP Std , M-R P;Std and M-SEP þ were determined.…”

Section: Optimization Frame Of the Mwpls Methodsmentioning

confidence: 99%

Selection of stable equivalent wavebands for near-infrared spectroscopic analysis of total nitrogen in soil

Chen

Liu

et al. 2014

Self Cite

The selection of stable wavebands for the near-infrared (NIR) spectroscopic analysis of total nitrogen (TN) in soil was accomplished by using an improved moving window partial least squares (MWPLS) method. A new modeling approach was performed based on randomness, similarity and stability, which produced an objective, stable and practical model. Based on the MWPLS method, a search was in the overall scanning region from 400 to 2498 nm, and the optimal waveband was identi¯ed to be 1424 to 2282 nm. A model space that includes 41 wavebands that are equivalent to the optimal waveband was then proposed. The public range of the 41 equivalent optimal wavebands was 1590 to 1870 nm, which contained su±cient TN information. The wavebands of 1424 to 2282 nm, 1590 to 1870 nm, and the long-NIR region 1100 to 2498 nm all achieved satisfactory validation e®ects. However, the public waveband of 1590 to 1870 nm had only a minimum number of wavelengths, which signi¯cantly reduced the method complexity. Various equivalent wavebands serve as guidelines for designing spectroscopic instruments. These wavebands could address the restrictions of position and the number of wavelengths in instrument design.

“…In the previous study, 13 the SG smoothing mode with¯rst-order derivative, third-degree polynomial Table 2. For the BiCC model with SG smoothing, the P REC was improved to 94.4%.…”

Section: Human Hemolytic Solutions' Datasetmentioning

confidence: 99%

“…On the other hand, Savitzky-Golay (SG) smoothing, 4,9,13,23 which is an e±cient spectral preprocessing method with a wide scope of application and a variety of di®erent smoothing modes, was used¯rst for the pretreatment of di®use re°ectance spectral data.…”

Section: Introductionmentioning

confidence: 99%

“…Near-infrared (NIR) spectroscopy as a simple and quick tool has been e®ectively utilized in various elds for quantitative and qualitative analysis, such as agriculture, [1][2][3][4][5][6] food, 7-9 environment, 10,11 biomedicine, [12][13][14][15][16] petroleum industry, 17 and so on. 18 Spectral discriminant analysis is a methodology that uses computer pattern recognition to identify and classify samples based on the collected spectral data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Moving-window bis-correlation coefficients method for visible and near-infrared spectral discriminant analysis with applications

Yao

et al. 2018

Self Cite

The moving-window bis-correlation coe±cients (MW-BiCC) was proposed and employed for the discriminant analysis of transgenic sugarcane leaves and -thalassemia with visible and nearinfrared (Vis-NIR) spectroscopy. The well-performed moving-window principal component analysis linear discriminant analysis (MW-PCA-LDA) was also conducted for comparison. A total of 306 transgenic (positive) and 150 nontransgenic (negative) leave samples of sugarcane were collected and divided to calibration, prediction, and validation. The di®use re°ection spectra were corrected using Savitzky-Golay (SG) smoothing with¯rst-order derivative (d ¼ 1), third-degree polynomial (p ¼ 3) and 25 smoothing points (m ¼ 25). The selected waveband was 736-1054 nm with MW-BiCC, and the positive and negative validation recognition rates (V REC þ , V REC À Þ were 100%, 98.0%, which achieved the same e®ect as MW-PCA-LDA. Another example, the 93 -thalassemia (positive) and 148 nonthalassemia (negative) of human hemolytic samples were collected. The transmission spectra were corrected using SG smoothing with d ¼ 1, p ¼ 3 and m ¼ 53. Using MW-BiCC, many best wavebands were selected (e.g., 1116-1146, 1794-1848 and 2284-2342 nm). The V REC þ and V REC À were both 100%, which achieved the same e®ect as MW-PCA-LDA. Importantly, the BiCC only required calculating correlation coe±cients between the spectrum of prediction sample and the average spectra of two types of calibration samples. Thus, BiCC was very simple in algorithm, and expected to obtain more applications. The results¯rst con¯rmed the feasibility of distinguishing -thalassemia and normal control samples by NIR spectroscopy, and provided a promising simple tool for large population thalassemia screening.