Feature Reduction Step Research Articles

TSM-CV: Twitter Sentiment Analysis for COVID-19 Vaccines Using Deep Learning

The coronavirus epidemic has imposed a devastating impact on humans around the globe, causing profound anxiety, fear, and complex emotions and feelings. Vaccination against the new coronavirus has started, and people’s feelings are becoming more diverse and complicated. In the presented work, our goal is to use the deep learning (DL) technique to understand and elucidate their feelings. Due to the advancement of IT and internet facilities, people are socially connected to explain their emotions and sentiments. Among all social sites, Twitter is the most used platform among consumers and can assist scientists to comprehend people’s opinions related to anything. The major goal of this work is to understand the audience’s varying sentiments about the vaccination process by using data from Twitter. We have employed both the historic (All COVID-19 Vaccines Tweets Kaggle dataset) and real (tweets) data to analyze the people’s sentiments. Initially, a preprocessing step is applied to the input samples. Then, we use the FastText approach for computing semantically aware features. In the next step, we apply the Valence Aware Dictionary for sentiment Reasoner (VADER) method to assign the labels to the collected features as being positive, negative, or neutral. After this, a feature reduction step using the Non-Negative Matrix Factorization (NMF) approach is utilized to minimize the feature space. Finally, we have used the Random Multimodal Deep Learning (RMDL) classifier for sentiment prediction. We have confirmed through experimentation that our work is effective in examining the emotions of people toward the COVID-19 vaccines. The presented work has acquired an accuracy result of 94.81% which is showing the efficacy of our strategy. Other standard measures like precision, recall, F1-score, AUC, and confusion matrix are also reported to show the significance of our work. The work is aimed to improve public understanding of coronavirus vaccines which can help the health departments to stop the anti-vaccination leagues and motivate people to a booster dose of coronavirus.

Development of a new approach for rapid identification and classification of uranium ore concentrate powders using textural and spectroscopy signatures

Recently, a concept for a new approach for rapid identification of uranium ore concentrate (UOC) powders using colour, textural and spectroscopy signatures was developed using a sample dataset consisting of 79 industrial uranium ore concentrate powders produced by different production routes at different facilities. The samples were first grouped into six different predefined colour categories using a colour-based classification model previously developed. In this study, a machine learning approach was used to develop supervised texture- and spectroscopy-based classification models for each colour category of uranium ore concentrates.Scanning electron microscopy images of the UOC samples were collected at 100x, 250x, 500x/1000× magnifications. A total of 524 texture features describing sample morphology were extracted from each image using First Order Statistics (FOS), Grey Level Co-Occurrence Matrix (GLCM), Grey Level Run Length Matrix (GLRLM), Grey Level Size Zone Matrix (GLSZM), Locally Binary Pattern (LBP) and Angle Measure Technique (AMT) textural feature extraction algorithms. Hyperspectral images of the samples were collected in the wavelength range 900–1700 nm and the mean spectrum of each sample was calculated, giving the spectral features of the UOCs. The texture and spectral features were used as input to the machine learning approach which consisted of a feature reduction step to identify discriminatory features and a classification step to provide the texture- and spectroscopy-based models. An average prediction accuracy of 82% and 97% were obtained for the texture- and spectral-based classification models, respectively, on hold-out test sets. The feature reduction step identified two new nuclear forensics signatures, consisting of 3–7 texture (morphological) characteristics and 2–6 characteristic wavelengths, respectively.This new approach enables rapid classification of unknown uranium ore concentrate powders using only their textural and hyperspectral images. By combining the classification results from the two models, the most probable production process and chemical composition can be identified, and the provenience of the seized sample can be narrowed down to a few matching possibilities. Moreover, after the image acquisition, the models can provide results in less than 2 min speeding up the investigation procedure, a key factor when a nuclear security event occurs.

Machine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suis.

(1) Background: MALDI-TOF mass spectrometry (MS) is the gold standard for microbial fingerprinting, however, for phylogenetically closely related species, the resolution power drops down to the genus level. In this study, we analyzed MALDI-TOF spectra from 44 strains of B. melitensis, B. suis and B. abortus to identify the optimal classification method within popular supervised and unsupervised machine learning (ML) algorithms. (2) Methods: A consensus feature selection strategy was applied to pinpoint from among the 500 MS features those that yielded the best ML model and that may play a role in species differentiation. Unsupervised k-means and hierarchical agglomerative clustering were evaluated using the silhouette coefficient, while the supervised classifiers Random Forest, Support Vector Machine, Neural Network, and Multinomial Logistic Regression were explored in a fine-tuning manner using nested k-fold cross validation (CV) with a feature reduction step between the two CV loops. (3) Results: Sixteen differentially expressed peaks were identified and used to feed ML classifiers. Unsupervised and optimized supervised models displayed excellent predictive performances with 100% accuracy. The suitability of the consensus feature selection strategy for learning system accuracy was shown. (4) Conclusion: A meaningful ML approach is here introduced, to enhance Brucella spp. classification using MALDI-TOF MS data.

Combination of spontaneous regional brain activity and HTR1A/1B DNA methylation to predict early responses to antidepressant treatments in MDD

BackgroundAntidepressant medications are suggested as the first-line treatment in patients with major depressive disorder (MDD). However, the drug therapy outcomes vary from person to person. The functional activity of the brain and DNA methylation levels correlate with the antidepressant efficacy. To predict the early antidepressant responses in MDD and establish the prediction framework, we aimed to apply multidimensional data based on the resting-state activity of the brain and HTR1A/1B methylation. MethodsThe values of Amplitude of Low-Frequency Fluctuations (ALFF) and regional homogeneity (ReHo) were measured as variables in 116 brain regions along with 181 CpG sites in the promoter region of HTR1A/1B and 11 clinical characteristics. After performing the feature reduction step using the least absolute shrinkage and selection operator (LASSO) method, the selected variables were put into Support Vector Machines (SVM), Random Forest (RF), Naïve Bayes (NB), and logistic regression (LR), consecutively, to construct the prediction models. The models’ performance was evaluated by the Leave-One-Out Cross-Validation. ResultsThe LR model composed of the selected multidimensional features reached a maximum performance of 78.57% accuracy and 0.8340 area under the ROC curve (AUC). The prediction accuracies based on multidimensional datasets were found to be higher than those obtained from the data based only on fMRI or methylation. LimitationsA relatively small sample size potentially restricted the usage of our prediction framework in clinical applications. ConclusionOur study revealed that combining the data of brain imaging and DNA methylation could provide a complementary effect in predicting early-stage antidepressant outcomes.

Feature selection using evolutionary algorithms: a data-constrained environment case study to predict tax defaulters

In this paper, a novel method is introduced to predict tax defaulters from the given data using an ensemble of feature reduction in the first step and feeding those features to a proposed neural network. The feature reduction step includes genetic algorithm (GA), particle swarm optimisation (PSO) and ant colony optimisation (ACO) in the performance analysis to determine the best approach. The second stage deals with experiments on the architecture of a neural network for appropriate predictions. The results indicate improvement in tax defaulter prediction on using the feature subset selected by PSO. This research work has also successfully demonstrated the positive influence on the usage of linear discriminant analysis (LDA) to perform dimensionality reduction of the unselected features to preserve the underlying patterns. The best results have been achieved using PSO for feature reduction with an accuracy of 79.2% which is a 5.4% improvement compared to the existing works.

Efficient classification of COVID-19 CT scans by using q-transform model for feature extraction.

The exponential growth in computer technology throughout the past two decades has facilitated the development of advanced image analysis techniques which aid the field of medical imaging. CT is a widely used medical screening method used to obtain high resolution images of the human body. CT has been proven useful in the screening of the virus that is responsible for the COVID-19 pandemic by allowing physicians to rule out suspected infections based on the appearance of the lungs from the CT scan. Based on this, we hereby propose an intelligent yet efficient CT scan-based COVID-19 classification algorithm that is able to discriminate negative from positive cases by evaluating the appearance of lungs. The algorithm is comprised of four main steps: preprocessing, features extraction, features reduction, and classification. In preprocessing, we employ the contrast limited adaptive histogram equalization (CLAHE) to adjust the contrast of the image to enhance the details of the input image. We then apply the q-transform method to extract features from the CT scan. This method measures the grey level intensity of the pixels which reflects the features of the image. In the feature reduction step, we measure the mean, skewness and standard deviation to reduce overhead and improve the efficiency of the algorithm. Finally, "k-nearest neighbor", "decision tree", and "support vector machine" are used as classifiers to classify the cases. The experimental results show accuracy rates of 98%, 98%, and 98.25% for each of the classifiers, respectively. It is therefore concluded that the proposed method is efficient, accurate, and flexible. Overall, we are confident that the proposed algorithm is capable of achieving a high classification accuracy under different scenarios, which makes it suitable for implementation in real-world applications.

IMOKA: k-mer based software to analyze large collections of sequencing data

iMOKA (interactive multi-objective k-mer analysis) is a software that enables comprehensive analysis of sequencing data from large cohorts to generate robust classification models or explore specific genetic elements associated with disease etiology. iMOKA uses a fast and accurate feature reduction step that combines a Naïve Bayes classifier augmented by an adaptive entropy filter and a graph-based filter to rapidly reduce the search space. By using a flexible file format and distributed indexing, iMOKA can easily integrate data from multiple experiments and also reduces disk space requirements and identifies changes in transcript levels and single nucleotide variants. iMOKA is available at https://github.com/RitchieLabIGH/iMOKA and Zenodo https://doi.org/10.5281/zenodo.4008947.

Degradation Data-Driven Time-To-Failure Prognostics Approach for Rolling Element Bearings in Electrical Machines

Time-to-failure (TTF) prognostic plays a crucial role in predicting remaining lifetime of electrical machines for improving machinery health management. This paper presents a novel three-step degradation data-driven TTF prognostics approach for rolling element bearings (REBs) in electrical machines. In the degradation feature extraction step, multiple degradation features, including statistical features, intrinsic energy features, and fault frequency features, are extracted to detect the degradation phenomenon of REBs using complete ensemble empirical mode decomposition with adaptive noise and Hilbert–Huang transform methods. In degradation feature reduction step, the degradation features, which are monotonic, robust, and correlative to the fault evolution of the REBs, are selected and fused into a principal component Mahalanobis distance health index using dynamic principal component analysis and Mahalanobis distance methods. In TTF prediction step, the degradation process and local TTF of the REBs are observed by an exponential regression-based local degradation model, and the global TTF is predicted by an empirical Bayesian algorithm with a continuous update. A practical case study involving run-to-failure experiments of REBs on PRONOSTIA platform is provided to validate the effectiveness of the proposed approach and to show a more accurate prediction of TTF than the existing major approaches.

A Computer-Aided Pipeline for Automatic Lung Cancer Classification on Computed Tomography Scans.

Lung cancer is one of the most common cancer types. For the survival of the patient, early detection of lung cancer with the best treatment method is crucial. In this study, we propose a novel computer-aided pipeline on computed tomography (CT) scans for early diagnosis of lung cancer thanks to the classification of benign and malignant nodules. The proposed pipeline is composed of four stages. In preprocessing steps, CT images are enhanced, and lung volumes are extracted from the image with the help of a novel method called lung volume extraction method (LUVEM). The significance of the proposed pipeline is using LUVEM for extracting lung region. In nodule detection stage, candidate nodules are determined according to the circular Hough transform- (CHT-) based method. Then, lung nodules are segmented with self-organizing maps (SOM). In feature computation stage, intensity, shape, texture, energy, and combined features are used for feature extraction, and principal component analysis (PCA) is used for feature reduction step. In the final stage, probabilistic neural network (PNN) classifies benign and malign nodules. According to the experiments performed on our dataset, the proposed pipeline system can classify benign and malign nodules with 95.91% accuracy, 97.42% sensitivity, and 94.24% specificity. Even in cases of small-sized nodules (3–10 mm), the proposed system can determine the nodule type with 94.68% accuracy.

SIGNIFICANT FEATURES TO DETECT PULMONARY NODULES FROM CT LUNG IMAGES

Lung cancer causes the most number of deaths worldwide in both men and women. Early detection and diagnosis can minimize the disease mortality rate. Commonly, chest computed tomography (CT) scans are used by clinicians to diagnose lung cancer. The lung cancer diagnosis relies on detection of the pulmonary nodules in CT scans. In this paper, we propose computer-aided diagnostic systems that can define and suggest the most important features that can distinguish lung nodule from nonnodule one. The proposed system can be described through the following six steps: (a) Patch Extraction, (b) Image Preprocessing, (c) Feature Extraction, (d) Normalization, (e) Feature Reduction, and (f) Patch Classification. Feature extraction and selection are the most important steps in any disease classification process. A combination of 132 texture features with three shape-based features has been extracted. Then the normalization step has been done using min–max method followed by the feature reduction step based on the wrapper approach. The feature reduction step resulted in selecting a set of eight features for the classification process. The algorithm was developed and tested using 166 patches of CT images. The selected eight features achieve accuracy 96.5% using [Formula: see text]-nearest neighbor classifier. The results were validated using the cross-validation technique, [Formula: see text]-fold method.

Computer Aided Diagnosis tool for Alzheimer’s Disease based on Mann–Whitney–Wilcoxon U-Test

An accurate and early diagnosis of the Alzheimer’s Disease (AD) is of fundamental importance for the development of effective treatments to palliate the effects of the disease. Computer Aided Diagnosis (CAD) allows physicians to detect early stages of the disease, and functional brain images have been proved to be very useful in this task. This paper presents a new CAD system that consists of three stages: voxel selection, feature extraction and classification. Voxels are selected in terms of their significance, by using Mann–Whitney–Wilcoxon U-Test. Then, Factor Analysis is proposed to carry out the feature reduction step, by extracting common factors and factor loadings from the selected voxels. Finally, a Linear Support Vector Machine (SVM) classifier is trained to perform clustering of the input images. Two different databases are considered for testing the proposed methods: the first one, consists of 96 Single Photon Emission Computed Tomography (SPECT) images from the “Virgen de las Nieves” Hospital in Granada, Spain, and a 196 Positron Emission Tomography (PET) database from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The proposed method achieves accuracy results of up to 93.7% and 92.9% for SPECT and PET images respectively, and reports benefits over recently reported methods.

Segmented canonical discriminant analysis of in situ hyperspectral data for identifying 13 urban tree species

A total of 458 in situ hyperspectral data were collected from 13 urban tree species in the City of Tampa, FL, USA using a spectrometer. The 13 species include 11 broadleaf and two conifer species. Three different techniques, segmented canonical discriminant analysis (CDA), segmented principal component analysis (PCA) and segmented stepwise discriminate analysis (SDA), were applied and compared for dimension reduction and feature extraction. With each of the three techniques, 10 features were extracted or selected from four spectral regions, visible (VIS: 1412–1797 nm), near-infrared (NIR: 707–1352 nm), mid-infrared 1 (MIR1: 1412–1797 nm) and mid-infrared 2 (MIR2: 1942–2400 nm), and used to discriminate the 13 urban tree species with a linear discriminate analysis (LDA) method. The cross-validation results, based on training samples that were used in the feature reduction step, and the results calculated from the test samples were used for evaluating the ability of the in situ hyperspectral data and performance of the segmented CDA, PCA and SDA to identify the 13 tree species. The experimental results indicate that a satisfactory discrimination of the 13 tree species was achieved using the segmented CDA technique (average accuracy (AA) = 96%, overall accuracy (OAA) = 96% and kappa = 0.958 from the cross-validation results; AA = 90%, OAA = 90% and kappa = 0.896 from the test samples) compared to the segmented PCA and SDA techniques, respectively (AA = 76% and 86%, OAA = 78% and 87%, and kappa = 0.763 and 0.857 from the cross-validation results; AA = 79% and 88%, OAA = 80% and 89%, and kappa = 0.782 and 0.879 from the test samples). In this study, the segmented CDA transformation is effective for dimension reduction and feature extraction for species discrimination with a relatively limited number of training samples. It outperformed the segmented PCA and SDA methods and produced the highest accuracies. The NIR and MIR1 regions have greater power for identifying the 13 species compared to the VIS and MIR2 spectral regions. The results indicate that CDA or segmented CDA could be applied broadly in mapping forest cover types, species identification and/or other land use/land cover classification practices with hyperspectral remote sensing data.

Effect of feature extraction for brain tumor classification based on short echo time 1H MR spectra

This study examines the effect of feature extraction methods prior to automated pattern recognition based on magnetic resonance spectroscopy (MRS) for brain tumor diagnosis. Since individual inspection of spectra is time-consuming and requires specific spectroscopic expertise, the introduction of clinical decision support systems (DSSs) is expected to strongly promote the clinical use of MRS. This study focuses on the feature extraction step in the preprocessing protocol of MRS when using a DSS. On two independent data sets, encompassing single-voxel and multi-voxel data, it is observed that the use of the full spectra together with a kernel-based technique, handling high dimensional data, or using an automated pattern recognition method based on independent component analysis or Relief-F achieves accurate performances. In addition, these approaches have low cost and are easy to automate. When sophisticated quantification methods are used in a DSS, user interaction should be minimized. The computationally intensive quantification techniques do not tend to increase the performance in these circumstances. The results suggest to simplify the feature reduction step in the preprocessing protocol when using a DSS purely for classification purposes. This can greatly speed up the execution of classifiers and DSSs and may accelerate their introduction into clinical practice.