Near-infrared spectroscopy and variable selection techniques to discriminate Pseudomonas aeruginosa strains in clinical samples

Marques, Aline S.; Castro, Jenielly N.F.; Costa, Fagner James Martins Dantas; Neto, Renato Motta; Lima, Kássio M. G.

doi:10.1016/j.microc.2015.09.006

Cited by 24 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The wavelengths at 1136, 1177 and 1251 nm are attributed to the second overtone of C-H stretching mode [26]. The wavelength at 1386 nm (around 1387 nm) might be attributed to the first overtone of stretching and anti-symmetric O-H bond [27]. The wavelengths at 1440 and 1494 nm are attributed to water [26,28].…”

Section: Spectral Profilesmentioning

confidence: 98%

Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network

et al. 2018

View full text Add to dashboard Cite

Abstract:The feasibility of using hyperspectral imaging with convolutional neural network (CNN) to identify rice seed varieties was studied. Hyperspectral images of 4 rice seed varieties at two different spectral ranges (380-1030 nm and 874-1734 nm) were acquired. The spectral data at the ranges of 441-948 nm (Spectral range 1) and 975-1646 nm (Spectral range 2) were extracted. K nearest neighbors (KNN), support vector machine (SVM) and CNN models were built using different number of training samples (100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1500, 2000, 2500 and 3000). KNN, SVM and CNN models in the Spectral range 2 performed slightly better than those in the Spectral range 1. The model performances improved with the increase in the number of training samples. The improvements were not significant when the number of training samples was large. CNN model performed better than the corresponding KNN and SVM models in most cases, which indicated the effectiveness of using CNN to analyze spectral data. The results of this study showed that CNN could be adopted in spectral data analysis with promising results. More varieties of rice need to be studied in future research to extend the use of CNNs in spectral data analysis.

show abstract

Section: Spectral Profilesmentioning

confidence: 98%

Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Linear discriminant analysis (LDA) is a classical statistical approach for feature extraction and dimension reduction and mostly employed among many supervised pattern recognition methods (Chen et al, 2011;Jia et al, 2016). LDA is used for classifying objects into groups or clusters by determining the similarity of unknown samples (Marques et al, 2016). LDA computes the optimal transformation (projection), which minimizes the ratio of intra-class difference (of the dataset) and maximizes the ratio of inter-class difference simultaneously thereby guaranteeing maximal separability.…”

Section: Linear Discriminant Analysis (Lda) Methodsmentioning

confidence: 99%

Luwak Coffee Classification Using UV-Vis Spectroscopy Data: Comparison of Linear Discriminant Analysis and Support Vector Machine Methods

Suhandy¹,

Yulia²

2018

Aceh Int. J. Sci. Technol

View full text Add to dashboard Cite

UV-Vis spectroscopy has been used as a promising method for coffee quality evaluation including in authentication of several high-economic coffee types. In this paper we have compared the abilities of linear discriminant analysis (LDA) and support vector machines classification (SVMC) methods for Luwak coffee classification. UV-Vis spectral data of 50 samples of pure Luwak coffee and 50 samples of pure non-Luwak coffee were acquired using a UV-Vis spectrometer in transmittance mode. The results show that UV-Vis spectroscopy combined with LDA and SVMC was effective method to classify Luwak and non-Luwak coffee samples. The classification result was acceptable and yielded 100% classification accuracy for both LDA and SVMC methods. However, due to the simplicity and volume of required calculation, in this present study LDA method is superior to SVMC method.

show abstract

“…Although sample preparation, sample size or machine learning techniques across these studies differed, predictive accuracies obtained are comparable to our results. Predictive sensitivity using GA-LDA and SPA-LDA for blaKPC-negative was 100% and 76%, respectively compared to the predictive sensitivity of 66% for blaKPC-2-harbouring K. pneumoniae using either model(25). These data are comparable to our findings where we demonstrated that sensitivity of NIRS for predicting blaNDM-type and blaOXA-48-type-genes harbouring K. pneumoniae was slightly lower (81%) than that of wild-type (92%).A plausible limitation for the differentiation of resistant and susceptible strains in our study is the potential that the organism harbours additional resistance determinants or variations which were not previously characterized resulting in a 'false negative' results.…”

mentioning

confidence: 91%

“…There are only a handful of studies exploring NIRS to differentiate resistant from susceptible strains and one species from another (21)(22)(23)(24)(25). The data so far is encouraging yet limited by sample size or insufficiently characterised sample banks using well-established reference methods.…”

Section: Introductionmentioning

confidence: 99%

Near-infrared Spectroscopy evaluations for rapid differentiation of carbapenem resistant Enterobacteriaceae from susceptible strains

Alharbi

Sikulu-Lord²,

Lord

et al. 2020

Preprint

View full text Add to dashboard Cite

Antimicrobial resistance (AMR) caused by Carbapenem-Resistant Enterobacteriaceae (CRE) is a global threat. Accurate identification of these bacterial species with associated AMR is critical for their management. While highly accurate methods to detect CRE are available, they are costly, timely and require expert skills making their application infeasible in low-resource settings. Here, we investigated the potential of Near-infrared Spectroscopy (NIRS) for a range of applications; i) the detection and differentiation of isolates of two pathogenic Enterobacteriaceae species, Klebsiella pneumoniae and Escherichia coli and, ii) the differentiation of carbapenem resistant and susceptible K. pneumoniae. NIRS has successfully differentiated between K. pneumoniae and E. coli isolates with a predictive accuracy of 89.04% (95% CI; 88.7-89.4%). K. pneumoniae isolates harbouring carbapenem resistance determinants were differentiated from susceptible K. pneumoniae strains with an accuracy of 85% (95% CI; 84.2-86.1%). To our knowledge, this is the largest demonstration of a proof of concept for the utility and feasibility of NIRS for rapidly differentiating between K. pneumoniae from E.coli as well as from carbapenem resistant K. pneumoniae from susceptible strains.

show abstract

Near-infrared spectroscopy and variable selection techniques to discriminate Pseudomonas aeruginosa strains in clinical samples

Cited by 24 publications

References 16 publications

Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network

Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network

Luwak Coffee Classification Using UV-Vis Spectroscopy Data: Comparison of Linear Discriminant Analysis and Support Vector Machine Methods

Near-infrared Spectroscopy evaluations for rapid differentiation of carbapenem resistant Enterobacteriaceae from susceptible strains

Contact Info

Product

Resources

About