Near-Infrared Spectroscopy as an Alternative to Biological Testing for Quality Control of Hyaluronan: Comparison of Data Preprocessing Methods for Classification

1995 ◽  
Vol 49 (7) ◽  
pp. 1037-1040 ◽  
Author(s):  
Annika E. Carlsson ◽  
Kjell L.-R. Janné
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Scatter Correction ◽  
Data Preprocessing ◽  
Classification Performance ◽  
Pharmaceutical Product ◽  
Biological Testing ◽  
Class Discrimination ◽  
Leave One Out

An alternative method to biological testing on animals has been studied. The method is based on pattern recognition by combination of near-infrared spectroscopy and multivariate classification. The pharmaceutical product under study is based on a high-molecular-weight carbohydrate, Hyaluronan, used as a medical device for eye surgery. The effect of data preprocessing on classification performance of approved and rejected samples was evaluated by use of principal components models for each class. With the use of multiplicative scatter correction techniques, the class discrimination was enhanced 10 times in comparison to uncorrected data. From a leave-one-out procedure including a total of 29 samples, 80% of the samples were classified in agreement with the biological reference data and the remaining 20% were classified as non-members. With the use of partial least-squares discriminant analysis, 90% of the predicted samples were in accordance with the biological assay.

Identification of Liquor Brands Based on near Infrared Spectroscopy

2013 ◽  
Vol 834-836 ◽  
pp. 935-938
Author(s):  
Lian Shun Zhang ◽  
Chao Guo ◽  
Bao Quan Wang
Keyword(s):  
Principal Component Analysis ◽  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Principal Components ◽  
Near Infrared ◽  
Scatter Correction ◽  
Principal Component ◽  
Component Analysis ◽  
Correction Method ◽  
Variance Contribution

In this paper, the liquor brands were identified based on the near infrared spectroscopy method and the principal component analysis. 60 samples of 6 different brands liquor were measured by the spectrometer of USB4000. Then, in order to eliminate the noise caused by the external factors, the smoothing method and the multiplicative scatter correction method were used. After the preprocessing, we got the revised spectra of the 60 samples. The difference of the spectrum shape of different brands is not much enough to classify them. So the principal component analysis was applied for further analysis. The results showed that the first two principal components variance contribution rate had reached 99.06%, which can effectively represent the information of the spectrums after preprocessing. From the scatter plot of the two principal components, the 6 different brands of liquor were identified more accurate and easier than the spectra curves.

Quantification of protein in wheat using near infrared hyperspectral imaging: Performance comparison with conventional near infrared spectroscopy

2018 ◽  
Vol 26 (3) ◽  
pp. 186-195 ◽  
Author(s):  
Ana Morales-Sillero ◽  
Juan A. Fernández Pierna ◽  
George Sinnaeve ◽  
Pierre Dardenne ◽  
Vincent Baeten
Keyword(s):  
Infrared Spectroscopy ◽  
Least Squares ◽  
Partial Least Squares ◽  
Hyperspectral Imaging ◽  
Wavelength Range ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Performance Comparison ◽  
Imaging Instrument ◽  
Leave One Out

Hyperspectral imaging is a powerful technique that combines the advantages of near infrared spectroscopy and imaging technologies. Most hyperspectral imaging studies focus on qualitative analysis, but there is growing interest in using such technique for the quantitative analysis of agro-food products in order to use them as universal tools. The overall objective of this study was to compare the performance of a hyperspectral imaging instrument with a classical near infrared instrument for predicting chemical composition. The determination of the protein content of wheat flour was selected as example. Spectra acquisition was made in individual sealed cells using two classical near infrared instruments (NIR-DS and NIR-Perstop) and a near infrared hyperspectral line-scan camera (NIR-HSI). In the latter, they were also acquired in open cells in order to study the possibility of accelerating the measurement process. Calibration models were developed using partial least squares for the full wavelength range of each individual instrument and for the common range between instruments (1120–2424 nm). The partial least squares models were validated using the “leave-one-out” cross-validation procedure and an independent validation set. The results showed that the NIR-HSI system worked as well as the classical near infrared spectrometers when a common wavelength range was used, with an r2 of 0.99 for all instruments and Root Mean Square Error in Prediction (RMSEP) values of 0.15% for NIR-HSI and NIR-DS and 0.16% for NIR-Perstop. The high residual predictive deviation values obtained (8.08 for NIR-DS, 7.92 for NIR-HSI, and 7.56 for NIR-Perstop) demonstrate the precision of the models built. In addition, the prediction performance with open cells was almost identical to that obtained with sealed cells.

scholarly journals Decoding Three Different Preference Levels of Consumers Using Convolutional Neural Network: A Functional Near-Infrared Spectroscopy Study

2021 ◽  
Vol 14 ◽  
Author(s):  
Kunqiang Qing ◽  
Ruisen Huang ◽  
Keum-Shik Hong
Keyword(s):  
Neural Network ◽  
Infrared Spectroscopy ◽  
Convolutional Neural Network ◽  
Near Infrared Spectroscopy ◽  
Classification Accuracy ◽  
Near Infrared ◽  
Classification Performance ◽  
Hemodynamic Responses ◽  
Functional Near Infrared Spectroscopy ◽  
Cerebral Hemodynamic

This study decodes consumers' preference levels using a convolutional neural network (CNN) in neuromarketing. The classification accuracy in neuromarketing is a critical factor in evaluating the intentions of the consumers. Functional near-infrared spectroscopy (fNIRS) is utilized as a neuroimaging modality to measure the cerebral hemodynamic responses. In this study, a specific decoding structure, called CNN-based fNIRS-data analysis, was designed to achieve a high classification accuracy. Compared to other methods, the automated characteristics, constant training of the dataset, and learning efficiency of the proposed method are the main advantages. The experimental procedure required eight healthy participants (four female and four male) to view commercial advertisement videos of different durations (15, 30, and 60 s). The cerebral hemodynamic responses of the participants were measured. To compare the preference classification performances, CNN was utilized to extract the most common features, including the mean, peak, variance, kurtosis, and skewness. Considering three video durations, the average classification accuracies of 15, 30, and 60 s videos were 84.3, 87.9, and 86.4%, respectively. Among them, the classification accuracy of 87.9% for 30 s videos was the highest. The average classification accuracies of three preferences in females and males were 86.2 and 86.3%, respectively, showing no difference in each group. By comparing the classification performances in three different combinations (like vs. so-so, like vs. dislike, and so-so vs. dislike) between two groups, male participants were observed to have targeted preferences for commercial advertising, and the classification performance 88.4% between “like” vs. “dislike” out of three categories was the highest. Finally, pairwise classification performance are shown as follows: For female, 86.1% (like vs. so-so), 87.4% (like vs. dislike), 85.2% (so-so vs. dislike), and for male 85.7, 88.4, 85.1%, respectively.

Prediction of Talc Content in Wheat Flour Based on a Near-Infrared Spectroscopy Technique

2019 ◽  
Vol 82 (10) ◽  
pp. 1655-1662
Author(s):  
YI LIU ◽  
LAIJUN SUN ◽  
ZHIYONG RAN ◽  
XUYANG PAN ◽  
SHUANG ZHOU ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Wheat Flour ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Rbf Neural Network ◽  
Scatter Correction ◽  
Set Partitioning ◽  
Characteristic Analysis ◽  
Detection Model ◽  
Infrared Spectral

ABSTRACT A procedure for the prediction of talc content in wheat flour based on radial basis function (RBF) neural network and near-infrared spectroscopy (NIRS) data is described. In this study, 41 wheat flour samples adulterated with different concentrations of talc were used. The diffuse reflectance spectra of all samples were collected by NIRS analyzer in the spectral range of 400 to 2,500 nm. A sample of outliers was eliminated by Mahalanobis distance based on near-infrared spectral scanning, and the remaining 40 wheat flour samples were used for spectral characteristic analysis. A calibration set of 26 samples and a prediction set of 14 samples of wheat flour were built as a result of sample set partitioning based on joint x–y distances division. A comparison of Savitzky-Golay smoothing, multiplicative scatter correction (MSC), first derivation, second derivation, and standard normal variation in the modeling showed that MSC has the best preprocessing effect. To develop a simpler, more efficient prediction model, the correlation coefficient method (CCM) was used to reduce spectral redundancy and determine the maximum correlation informative wavelength (MIW). From the full 1,050 wavelengths, 59 individual MIWs were finally selected. The optimal combined detection model was CCM-MSC-RBF based on the selected MIWs, with a determination of prediction coefficients of prediction (Rp) of 0.9999, root-mean-square error of prediction of 0.0765, and residual predictive deviation of 65.0909. The study serves as a proof of concept that NIRS technology combined with multivariate analysis has the potential to provide a fast, nondestructive and reliable assay for the prediction of talc content in wheat flour.

A method for highlighting differences between bacteria grown on nutrient agar using near infrared spectroscopy and principal component analysis

2021 ◽  
pp. 096703352110065
Author(s):  
Sylvain Treguier ◽  
Kevin Jacq ◽  
Christel Couderc ◽  
Hicham Ferhout ◽  
Helene Tormo ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Culture Media ◽  
Scatter Correction ◽  
Principal Component ◽  
Diagnostic Tools ◽  
Multiplicative Scatter Correction ◽  
Principal Component Analyses ◽  
Petri Dishes

Fast diagnostic tools such as near infrared spectroscopy have recently gained interest for bacterial identification. To avoid a process involving microbial pellet or suspension preparation from Petri dishes for NIR analysis, direct screening from agar in Petri dishes was explored. This two-step study proposes a new procedure for bacterial screening directly on agar plates with minimal nutrient medium bias. Firstly, principal component analyses showed optimal discrimination between the genera Lactobacillus, Pseudomonas and Brochothrix on different culture media, in transmission mode and with the bottom of Petri dishes facing the light source. The repeatability of spectra in these conditions was assessed with an average coefficient of variation inferior to 5% in the 12,500–3680 cm−1 range. Secondly, 40 strains of Lactococcus and Enterococcus species were grown on Bennett agar and measured over a series of five assays. Principal component analyses highlighted better clustering according to genera and species and lower external bias while retaining the 8790–3680 cm−1 spectral range and applying an extended multiplicative scatter correction with an average agar spectrum as a reference, in comparison to raw data and standard multiplicative scatter correction.

scholarly journals Using near-infrared spectroscopy to discriminate closely related species: A case study of neotropical ferns

2020 ◽  
Author(s):  
Darlem Nikerlly Amaral Paiva ◽  
Ricardo de Oliveira Perdiz ◽  
Thaís Elias Almeida
Keyword(s):  
Infrared Spectroscopy ◽  
Plant Species ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Cross Validation ◽  
Herbarium Specimens ◽  
Correct Identification ◽  
Fern Species ◽  
Identification Of Species ◽  
Leave One Out

ABSTRACTIdentifying plant species requires considerable knowledge and can be difficult without complete specimens. Fourier-transform near-infrared spectroscopy (FT-NIR) is an effective technique for discriminating plant species, especially angiosperms. However, its efficacy has never been tested on ferns. Here we tested the accuracy of FT-NIR at discriminating species of the genus Microgramma. We obtained 16 spectral readings per individual from the adaxial and abaxial surfaces of 100 specimens belonging to 13 species. The analyses included all 1557 spectral variables. We tested different datasets (adaxial+abaxial, adaxial, and abaxial) to compare the correct identification of species through the construction of discriminant models (LDA, PLS) and cross-validation techniques (leave-one-out, K-fold). All analyses recovered an overall high percentage (>90 %) of correct predictions of specimen identifications for all datasets, regardless of the model or cross-validation used. On average, there was > 95 % accuracy when using PLS-DA and both cross-validations. Our results show the high predictive power of FT-NIR at correctly discriminating fern species when using leaves of dried herbarium specimens. The technique is sensitive enough to reflect species delimitation problems and possible hybridization, and it has the potential of helping better delimit and identify fern species.

Sign in / Sign up

Export Citation Format

Share Document