Fault detection using Linear Discriminant Analysis with selection of process variables and time lags

Quality based classification of gasoline samples by ATR-FTIR spectrometry using spectral feature selection with quadratic discriminant analysis

Building selective ensembles of Randomization Based Neural Networks with the successive projections algorithm

Aspects of the successive projections algorithm for variable selection in multivariate calibration applied to plasma emission spectrometry

Interpretability of selected variables and performance comparison of variable selection methods in a polyethylene and polypropylene NIR classification task

Candida auris and Candida haemulonii are two emerging opportunistic pathogens that have caused an increase in clinical cases in the recent years worldwide. The differentiation of some Candida species is highly laborious, difficult, costly, and time-consuming depending on the similarity between the species. Thus, this study aimed to develop a new, faster, and less expensive methodology for differentiating between C. auris and C. haemulonii based on near-infrared (NIR) spectroscopy and multivariate analysis. C. auris CBS10913 and C. haemulonii CH02 were separated in 15 plates per species, and three isolated colonies of each plate were selected for Fourier transform near-infrared (FT-NIR) analysis, totaling 90 spectra. Subsequently, principal component analysis (PCA) and variable selection algorithms, including the successive projections algorithm (SPA) and genetic algorithm (GA) coupled with linear discriminant analysis (LDA), were employed to discern distinctive patterns among the samples. The use of PCA, SPA, and GA algorithms associated with LDA achieved 100% sensitivity and specificity for the discriminations. The SPA-LDA and GA-LDA algorithms were essential in selecting the variables (infrared wavelengths) of most importance for the models, which could be attributed to binding of cell wall structures such as polysaccharides, peptides, proteins, or molecules resulting from yeasts' metabolism. These results show the high potential of combined FT-NIR and multivariate analysis techniques for the classification of Candida-like fungi, which can contribute to faster and more effective diagnosis and treatment of patients affected by these microorganisms.

Hybrid variable selection in visible and near-infrared spectral analysis for non-invasive quality determination of grape juice

Introduction: The early and accurate detection of COVID-19 remains a life-threatening challenge in medical analysis. Machine learning is used for predicting disease outcomes based on clinical parameters. This analysis proposes a comparative analysis of feature selection method and classification techniques to enhance COVID-19 detection accuracy using blood biomarkers. We used a pensourse dataset of 1,724 cases, including 35 features. To improve the model performance data preprocessing process included outlier handling, normalization, and transformation techniques to improve model performance. To identify the relevant features, we employed the three-feature selection methods Chi-Square test, Pearson correlation coefficient, and Random Forest. The model prediction accuracy was enhanced using a stacking ensemble classication techniques. The machine learning based classification models effectively predicted COVID-19 infectious disease using blood biomarkers with optimized feature selection techniques. Objectives: To enhance the accuracy of COVID-19 prediction using machine learning techniques by applying feature selection and classification techniques on blood biomarkers. Methods: The comparative analysis utilized a publicly available dataset containing 1,724 cases with 35 attributes. Data preprocessing involved outlier handling, normalization, and transformation techniques. Employed Chi-Square test, Pearson correlation coefficient, and Random Forest feature selection techniques. Stacking ensemble classification algorithm was utilized for the better performance of a model. Results: The classification models demonstrated efficiency in predicting COVID-19 using blood biomarkers. Optimized feature selection significantly improved predictive accuracy, highlighting the importance of selecting relevant features for model performance enhancement. Conclusions: This study showcases the potential of ML-driven approaches for COVID-19 detection, emphasizing the role of feature selection in improving classification accuracy. The findings contribute to the advancement of diagnostic tools, offering a data-driven solution for rapid and reliable COVID-19 screening.

Analyzing EEG (electroencephalograph) signal is one of the most important methods of mental fatigue classification. Previous studies mainly describe the EEG features they use, however, the process of selecting features has not been synthetically researched. This study proposes the weighted-normalized mutual information feature selection (W-NMIFS) method to select features. W-NMIFS criterion optimizes the estimation of redundancy information in mutual information algorithm. Considering general features which are used in EEG analysis, several important ones are selected by W-NMIFS criterion. In order to guarantee the rigor of the experiment, the source datasets are collected from 10 volunteers using 10–20 EEG system. 3 different mental tasks are designed to introduce mental fatigue in low, medium and high levels. LDA (Linear discriminant analysis) classifier is used to assess mental fatigue and compare different feature selection algorithms. The results of mental fatigue classification show that the chosen features using W-NMIFS criterion are suitable for LDA algorithm. The classification precision is improved compared with mRMR (minimal-redundancy-maximal-relevance), NMIFS (normalized mutual information feature selection) and N-NMIFS (novel normalized mutual information feature selection) algorithm.

The successive projections algorithm

The competitive adaptive reweighted sampling-successive projections algorithm (CARS-SPA) method was proposed as a novel variable selection approach to process multivariate calibration. The CARS was first used to select informative variables, and then SPA to refine the variables with minimum redundant information. The proposed method was applied to near-infrared (NIR) reflectance data of nicotine in tobacco lamina and NIR transmission data of active ingredient in pesticide formulation. As a result, fewer but more informative variables were selected by CARS-SPA than by direct CARS. In the system of pesticide formulation, a multiple linear regression (MLR) model using variables selected by CARS-SPA provided a better prediction than the full-range partial least-squares (PLS) model, successive projections algorithm (SPA) model and uninformative variables elimination-successive projections algorithm (UVE-SPA) processed model. The variable subsets selected by CARS-SPA included the spectral ranges with sufficient chemical information, whereas the uninformative variables were hardly selected.

Diabetes mellitus is a group of metabolic diseases in which blood sugar levels are too high. About 8.8% of the world was diabetic in 2017. It is projected that this will reach nearly 10% by 2045. The major challenge is that when machine learning-based classifiers are applied to such data sets for risk stratification, leads to lower performance. Thus, our objective is to develop an optimized and robust machine learning (ML) system under the assumption that missing values or outliers if replaced by a median configuration will yield higher risk stratification accuracy. This ML-based risk stratification is designed, optimized and evaluated, where: (i) the features are extracted and optimized from the six feature selection techniques (random forest, logistic regression, mutual information, principal component analysis, analysis of variance, and Fisher discriminant ratio) and combined with ten different types of classifiers (linear discriminant analysis, quadratic discriminant analysis, naïve Bayes, Gaussian process classification, support vector machine, artificial neural network, Adaboost, logistic regression, decision tree, and random forest) under the hypothesis that both missing values and outliers when replaced by computed medians will improve the risk stratification accuracy. Pima Indian diabetic dataset (768 patients: 268 diabetic and 500 controls) was used. Our results demonstrate that on replacing the missing values and outliers by group median and median values, respectively and further using the combination of random forest feature selection and random forest classification technique yields an accuracy, sensitivity, specificity, positive predictive value, negative predictive value and area under the curve as: 92.26%, 95.96%, 79.72%, 91.14%, 91.20%, and 0.93, respectively. This is an improvement of 10% over previously developed techniques published in literature. The system was validated for its stability and reliability. RF-based model showed the best performance when outliers are replaced by median values.

Credit risk analysis forms an important criterion for the endurance of the banking sector. Understanding credit liability of customer enhances the security stability of the banker. This research is aimed at comparing the predictive accuracy of data mining techniques with feature selection and extraction techniques in the default of credit card clients and suggesting the most efficient technique for analyzing credit card default. Customer's default payments in Taiwan were used as the dataset. Machine Learning classification algorithms like K-nearest neighbor(KNN), Naive Bayesian(NB), Decision Tree(DT) and Support Vector Machines(SVM) were applied to the dataset. Feature filter methods like information gain (IG), gain ratio (GR) and chi-square (CS) and Wrapper based methods like Best First search(BFS) and Hill Climbing search (HCS) were used to identify minimum features required. Feature extraction methods such as Principal Component Analysis(PCA) and Linear Discriminant Anal-ysis(LDA) were also applied. The minimum features of feature selection algorithms along with PCA and LDA were then applied to Base classifiers and their accuracies were tabulated and compared. SVM with feature selection and extraction techniques had the best predictive accuracy.

A computer vision system for automatic recognition and classification of five varieties of plant leaves under controlled laboratory imaging conditions, comprising: 1–Cydonia oblonga (quince), 2–Eucalyptus camaldulensis dehn (river red gum), 3–Malus pumila (apple), 4–Pistacia atlantica (mt. Atlas mastic tree) and 5–Prunus armeniaca (apricot), is proposed. 516 tree leaves images were taken and 285 features computed from each object including shape features, color features, texture features based on the gray level co-occurrence matrix, texture descriptors based on histogram and moment invariants. Seven discriminant features were selected and input for classification purposes using three classifiers: hybrid artificial neural network–ant bee colony (ANN–ABC), hybrid artificial neural network–biogeography based optimization (ANN–BBO) and Fisher linear discriminant analysis (LDA). Mean correct classification rates (CCR), resulted in 94.04%, 89.23%, and 93.99%, for hybrid ANN–ABC; hybrid ANN–BBO; and LDA classifiers, respectively. Best classifier mean area under curve (AUC), mean sensitivity, and mean specificity, were computed for the five tree varieties under study, resulting in: 1–Cydonia oblonga (quince) 0.991 (ANN–ABC), 95.89% (ANN–ABC), 95.91% (ANN–ABC); 2–Eucalyptus camaldulensis dehn (river red gum) 1.00 (LDA), 100% (LDA), 100% (LDA); 3–Malus pumila (apple) 0.996 (LDA), 96.63% (LDA), 94.99% (LDA); 4–Pistacia atlantica (mt. Atlas mastic tree) 0.979 (LDA), 91.71% (LDA), 82.57% (LDA); and 5–Prunus armeniaca (apricot) 0.994 (LDA), 88.67% (LDA), 94.65% (LDA), respectively.

PSOLDA: A particle swarm optimization approach for enhancing classification accuracy rate of linear discriminant analysis

Ovarian cancer is a solid tumor and a leading cause of mortality. Diagnostic tools for the detection of early stage (stage I) ovarian cancer are urgently needed. For this purpose, attenuated total reflection Fourier-transform infrared spectroscopy (ATR-FTIR) coupled with variable selection methods, successive projection algorithm or genetic algorithm (GA) combined with linear discriminant analysis (LDA), were employed to identify spectral biomarkers in blood plasma or serum samples for accurate diagnosis of different stages of ovarian cancer, histological type and segregation based on age. Three spectral datasets (stage I vs. stage II-IV; serous vs. non-serous carcinoma; and, ≤60 years vs. >60 years) were processed: sensitivity and specificity required for real-world diagnosis of ovarian cancer was achieved. Toward segregating stage I vs. stage II-IV, sensitivity and specificity (plasma blood) of 100% was achieved using a GA-LDA model with 33 wavenumbers. For serous vs. non-serous category (plasma blood), the sensitivity and specificity levels, using 29 wavenumbers by GA-LDA, were remarkable (up to 94%). For ≤60 years and >60 years categories (plasma blood), the sensitivity and specificity, using 42 wavenumbers by GA-LDA, gave complete accuracy (100%). For serum samples, sensitivity and specificity results gave relatively high accuracy (up to 91.6% stage I vs. stage II-IV; up to 93.0% serous vs. non-serous; and, up to 96.0% ≤60 years vs. >60 years) using several wavenumbers. These findings justify a prospective population-based assessment of biomarkers signatures using ATR-FTIR spectroscopy as a screening tool for stage of ovarian cancer.