Numerous Features Research Articles

In-Flight Sales Prediction Using Machine Learning

This study introduces an advanced machine learning approach for predicting in-flight sales, aiming to transform the airline retail landscape. By harnessing advanced algorithms and historical sales data, the proposed model offers precise predictions of passenger preferences, allowing airlines to optimize their in-flight inventory and tailor product offerings more effectively. This data-driven strategy is designed to enhance inventory management, increase ancillary revenue, and improve passenger satisfaction. The research explores six distinct machine learning models: Linear Regression (LR), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), Multilayer Perceptron Neural Network (MLP), Recurrent Neural Network (RNN), and Deep Neural Network (DNN). Among these, XGBoost has proven to be the most effective model for sales forecasting, demonstrating exceptional accuracy and reliability. The study also highlights key features influencing sales, with ItemCategory_ TOBACCO emerging as the most significant factor among all features, and TotalPassenger as the most influential numerical feature. This research not only advances the field of predictive analytics but also provides practical insights for implementation in the aviation industry. As airlines continue to pursue digital transformation, this machine learning solution offers a strategic opportunity to deliver measurable economic benefits and enhance the in-flight retail experience through personalized and relevant product offerings.

On Multiscaling of Parkinsonian Rest Tremor Signals and Their Classification.

Self-similar stochastic processes and broad probability distributions are ubiquitous in nature and in many man-made systems. The brain is a particularly interesting example of (natural) complex system where those features play a pivotal role. In fact, the controversial yet experimentally validated "criticality hypothesis" explaining the functioning of the brain implies the presence of scaling laws for correlations. Recently, we have analyzed a collection of rest tremor velocity signals recorded from patients affected by Parkinson's disease, with the aim of determining and hence exploiting the presence of scaling laws. Our results show that multiple scaling laws are required in order to describe the dynamics of such signals, stressing the complexity of the underlying generating mechanism. We successively extracted numeric features by using the multifractal detrended fluctuation analysis procedure. We found that such features can be effective for discriminating classes of signals recorded in different experimental conditions. Notably, we show that the use of medication (L-DOPA) can be recognized with high accuracy.

An Extensive Analysis of Feature Selection in Machine Learning

Abstract: Researchers and engineers working in the disciplines of data mining and machine learning have difficulties while analysing high-dimensional data. A dimension reduction method called feature selection is used to pick characteristics that are pertinent to machine learning tasks. Improving the efficiency of machine learning algorithms, hastening the learning process, and creating basic models all depend critically on reducing the size of the dataset by removing superfluous and useless information. Numerous feature selection techniques have been put forth in the literature to find the pertinent feature or feature subsets in order to accomplish the goals of clustering and classification. The purpose of this study is to review the state of the art for these methods.

Regionalne odmienności fonetyczne w świadomości językowej użytkowników Internetu

The article attempts to show what place phonetic phenomena occupy in the linguistic awareness of Poles. One aspect of the issue is analysed, namely how people without linguistic education treat regional pronunciation peculiarities. It is shown which phonetic phenomena are present in the linguistic awareness of non ‑philologists (e.g. intonation, accent, rate of speech, numerous features of dialectal pronunciation, hypercorrect realisations), how internauts write about phonetic regionalisms and dialectisms and how they evaluate these phenomena. The analysis makes use of the metalinguistic comments of Internet users published in various forums and blogs.

Comparison of Machine Learning Algorithms on Classification of Covid-19 Cough Sounds Using MFCC Extraction

Early detection for COVID-19 has now been widely developed. One of the methods used is cough audio detection. This research aims to classify cough audio. Audio feature extraction is performed using MFCC to obtain numerical features. Feature classification is done using SVM, Random Forest, and Naive Bayes methods. Evaluation is done to find the best classification method. The evaluation results in this study show that SVM Kernel RBF produces the best evaluation value with an AUC value of 0.657715.

Evolution of the French Language System in Ivory Coast

This article examines the current state of the French language in Ivory Coast. The relevance of the study is related to the lack of research on the state of French in Ivory Coast, represented by the following varieties: Ivorian Popular French, Ivorian French and the Nouchi language code. Nouchi, an integral part of Ivory Coast's linguistic system and a crucial factor of Ivorian identity, remains a poorly researched phenomenon today. The aim of the work is to objectively describe the phonetic, morphological, lexical and syntactic changes that take place in French on the territory of Ivory Coast in a situation of interaction with the autochthonous languages under the influence of extralinguistic factors. The scientific novelty lies in the integrated approach to the study of the French language system in Ivory Coast and the differences between each of the varieties of French and standard French. The research uses general scientific (analysis, synthesis, generalization) and special methods (descriptive and comparative methods). The analysis of the French language system shows the distinctive features of the French varieties from the standard French on the phonetic, morphological, lexical and syntactical levels. Ivorian Popular French is characterised by the greatest influence from the autochthonous languages and numerous features at all levels of the language, caused by the lack of education of its speakers. The continuity and interconnectedness of all the varieties of language examined is highlighted: the oldest variant of Ivorian Popular French became the basis for the formation of modern Ivorian French. Nouchi, on the other hand, combines earlier variants of French with borrowings from the autochthonous and European languages. Ivorian French and Nouchi are now widespread in all social strata and contribute to the issue of Ivorian self-determination.

THE CRIMINAL LAW FRAMEWORK FOR COMBATING DOPING IN SPORTS IN SERBIA

This paper deals with the aspects of criminal law as regards the suppression of doping in sports in the law of the Republic of Serbia. The Law on the Prevention of Doping in Sports prescribes two criminal offences, namely Facilitating the Use of Doping Substances and the Unauthorized Production and Circulation of Doping Substances. These are criminal acts that are prescribed by the so-called secondary criminal legislation of the Republic of Serbia. The analysis of these criminal offences is afforded the central place in this paper. At the same time, for the sake of systematicity, numerous common features of these criminal acts were separated and analysed, such as protective object, object of action (doping agent), consequence of the criminal act, guilt, special intention, etc., and then their other features were separately considered. It is noticeable that the criminal offenses from the Law on the Prevention of Doping in Sports have corresponding regulatory shortcomings, above all they do not include certain important aspects related to the suppression of doping in sports, so certain proposals de lege ferenda were made based on the criminal offenses from the Criminal Code. The paper also gives a cursory review of the most important international documents in this area, i.e. the two most important documents ratified by the Republic of Serbia, namely the International Convention against Doping in Sport and the European Convention against Doping in Sport, bearing in mind that these acts were the basis for adoption of a special anti-doping law in our country. Additionally, the paper clarifies what is considered doping in sports according to the provisions of the positive law of Serbia.

A Systematic Evaluation of Feature Encoding Techniques for Gait Analysis Using Multimodal Sensory Data.

This paper addresses the problem of feature encoding for gait analysis using multimodal time series sensory data. In recent years, the dramatic increase in the use of numerous sensors, e.g., inertial measurement unit (IMU), in our daily wearable devices has gained the interest of the research community to collect kinematic and kinetic data to analyze the gait. The most crucial step for gait analysis is to find the set of appropriate features from continuous time series data to accurately represent human locomotion. This paper presents a systematic assessment of numerous feature extraction techniques. In particular, three different feature encoding techniques are presented to encode multimodal time series sensory data. In the first technique, we utilized eighteen different handcrafted features which are extracted directly from the raw sensory data. The second technique follows the Bag-of-Visual-Words model; the raw sensory data are encoded using a pre-computed codebook and a locality-constrained linear encoding (LLC)-based feature encoding technique. We evaluated two different machine learning algorithms to assess the effectiveness of the proposed features in the encoding of raw sensory data. In the third feature encoding technique, we proposed two end-to-end deep learning models to automatically extract the features from raw sensory data. A thorough experimental evaluation is conducted on four large sensory datasets and their outcomes are compared. A comparison of the recognition results with current state-of-the-art methods demonstrates the computational efficiency and high efficacy of the proposed feature encoding method. The robustness of the proposed feature encoding technique is also evaluated to recognize human daily activities. Additionally, this paper also presents a new dataset consisting of the gait patterns of 42 individuals, gathered using IMU sensors.

Multimodal multiscale dynamic graph convolution networks for stock price prediction

Predicting directional future stock price movements is very challenging due to the complex, stochastic, and evolving nature of the financial markets. Existing literature either neglects other timely and granular alternative data, such as media text data, or fails to extract and distill predictive multimodal features from the data. Moreover, the time-varying cross-sectional relations beyond sequential dependencies of stock prices are informative for forecasting price fluctuations, for which the modelling flexibility, however, is not adequate in most of the previous studies. In this paper, we propose a novel Multiscale Multimodal Dynamic Graph Convolution Network (Melody-GCN) to address these issues in stock price prediction. It contains three core modules: (1) multimodal fusing-diffusing blocks that effectively integrate and align the numerical and textual features; (2) a multiscale architecture that extracts and refines temporal features via a fine-to-coarse descending path and a coarse-to-fine ascending path progressively; and (3) dynamic spatio-temporal graph convolutional layers that learn the complex and evolving stock relations not only in between industries and individual companies but also across time horizons. Extensive experimental results and trading simulations on two real-world datasets demonstrate the superior performance of our proposed approach beyond other state-of-the-art models.

Spectral Modeling of the Supersoft X-Ray Source CAL87 Based on Radiative Transfer Codes

Supersoft X-ray sources (SSSs) are white dwarf (WD) binaries that radiate almost entirely below ∼1 keV. Their X-ray spectra are often complex when viewed with the X-ray grating spectrometers, where numerous emission and absorption features are intermingled and hard to separate. The absorption features are mostly from the WD atmosphere, for which radiative transfer models have been constructed. The emission features are from the corona surrounding the WD atmosphere, in which incident emission from the WD surface is reprocessed. Modeling the corona requires different solvers and assumptions for the radiative transfer, which has yet to be achieved. We chose CAL87, an SSS in the Large Magellanic Cloud, which exhibits emission-dominated spectra from the corona, as the WD atmosphere emission is assumed to be completely blocked by the accretion disk. We constructed a radiative transfer model for the corona using two radiative transfer codes: xstar for a one-dimensional two-stream solver and MONACO for a three-dimensional Monte Carlo solver. We identified their differences and limitations in comparison to the spectra taken with the Reflection Grating Spectrometer on board the XMM-Newton satellite. We finally obtained a sufficiently good spectral model of CAL87 based on the radiative transfer of the corona plus an additional collisionally ionized plasma. In the coming X-ray microcalorimeter era, it will be required to interpret spectra based on radiative transfer in a wider range of sources than what is presented here.

Distinctive approach in brain tumor detection and feature extraction using biologically inspired DWT method and SVM

Brain tumors result from uncontrolled cell growth, potentially leading to fatal consequences if left untreated. While significant efforts have been made with some promising results, the segmentation and classification of brain tumors remain challenging due to their diverse locations, shapes, and sizes. In this study, we employ a combination of Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA) to enhance performance and streamline the medical image segmentation process. Proposed method using Otsu's segmentation method followed by PCA to identify the most informative features. Leveraging the grey-level co-occurrence matrix, we extract numerous valuable texture features. Subsequently, we apply a Support Vector Machine (SVM) with various kernels for classification. We evaluate the proposed method's performance using metrics such as accuracy, sensitivity, specificity, and the Dice Similarity Index coefficient. The experimental results validate the effectiveness of our approach, with recall rates of 86.9%, precision of 95.2%, F-measure of 90.9%, and overall accuracy. Simulation of the results shows improvements in both quality and accuracy compared to existing techniques. In results section, experimental Dice Similarity Index coefficient of 0.82 indicates a strong overlap between the machine-extracted tumor region and the manually delineated tumor region.

Groundwater for drinking and industrial purposes: A study of water stability and human health risk assessment from black sand mineral rich coastal region of Kerala, India

Tempero-spatial analysis of groundwater to disseminate the level of drinking water quality and industrial suitability to meet the developmental requirement of a region is a significant area of research. Accordingly, groundwater quality and geochemical interactions prevailed in a black sand mineral rich coastal village is systematically presented in appraisal of drinking and industrial uses for economic engineering purposes. The study area focused is Alappad village, Kollam, Kerala, India has numerous ecological features in a sustainable perspective. The region is unique with placer deposits where an alluvial soil aquifer–saline water–freshwater interaction occurs. This dynamics decides the pertinent hydro geochemistry, potable and designated uses of ground water in season wise. Coastal area is hereby presented based on water quality parameters predicted with the health risk assessment model with a view on human health and cancer risk due to ions (Pb, Ni, Cu, Ba, Fe, Al, Mn, Zn) in groundwater.. To ascertain industrial usage, ground water is evaluated by Langelier saturation index (LSI), Ryznar stability index (RSI), Aggressive index (AI), Larson-Skold index (LS) and Puckorius scaling index (PSI) and inferences are complemented. Chemical weathering and evaporation processes are the natural factors controlling hydrochemistry of this aquifer. This complex coastal system has Nemerow pollution index (NPI) of moderate pollution for total dissolved ions of Fe and lesser for Cu, and Cr present in groundwater. LSI indicates, water is scale forming but non corrosive (46% in PRM, 20% in MON and 47% in POM). Water quality index (WQI) in POM (ranged 28.7–79.9) was excellent for drinking, followed by PRM (23.6–218.2) and MON (33.4–202.7) seasons. This groundwater bears temporary hardness with the dominance of Ca–Mg–HCO3 water type. Health risk assessment of non-carcinogenic risk index of trace metals (Fe, Zn, Mn, and Pb) revealed, children are at ‘low risk’ and ‘medium’ risk with Ni and Cu. The carcinogenic risk index indicated 93% of samples were high Ni induced cancer risk for children, and 87% for adults due to long term ingestion (drinking water intake) pathway. Studies specific on placer mineral deposited coastal region of India are not sufficiently reported with a focus on the above perspectives. Growing need of rare earths for material, device and energy applications, placer mineral explorations can destabilise the coastal hydrosphere. Interrelations of mineral soil – water chemistry prevailed and health hazard predicted would kindle a set of sustainable deliberations. This study summarises the drinking and industrial use of coastal groundwater for future development and human well-being on the basis of quality criteria, corrosion proneness, water stability and health risk factors.

Hybrid ML-MDKL feature subset selection and classification technique accompanied with rat swarm optimizer to classify the multidimensional breast cancer mammogram image

Breast cancer is a pathological condition characterized by the abnormal proliferation of cells inside the breast tissue. The biggest challenge at the moment is determining the most optimal subset from large datasets. Numerous methodologies have been presented for the purpose of selecting the most suitable subset from datasets with high dimensions. However, the outcomes have proven to be insufficient in effectively addressing extensive quantities of multidimensional datasets. This publication presents a proposal for an efficient approach of selecting numerous feature subsets and performing classification on Multidimensional Datasets (MDD). In this study, the Moment Invariant Wavelet Feature Extraction (MI-WFE) approach is employed for the purpose of feature extraction. The New Adaptive Hybrid Levy Flight based Cuckoo Search Optimization Algorithm is employed to identify the most pertinent subset of features. This study presents a novel approach, referred to as H-RS-LVCSO, which aims to enhance the local search capability and optimization speed of the algorithm. This is achieved through the hybridization of the Rat Swarm Optimizer with the levy flight based cuckoo search optimization technique. In this study, it is suggested a hybridized approach for classifying breast cancer, utilizing a Multilayer Multiple Deep Kernel Learning (ML-MDKL) Classifier in conjunction with the standard Support Vector Machine (SVM) Classifier. The simulation of the suggested method is conducted using the MATLAB software. The approach under consideration is evaluated in comparison to two pre-existing methods. The suggested method demonstrates an accuracy improvement of 10.58% compared to existing methods. Furthermore, it outperforms these methods by 17.5% in terms of accuracy. The proposed method exhibits a precision improvement of 6.52% and 14.23% compared to the existing methods.

Troxerutin dampened hypothalamic neuroinflammation via microglial IL-22/IL-22R1/IRF3 activation in dihydrotestosterone-induced polycystic ovary syndrome rats

BackgroundPolycystic ovary syndrome (PCOS) is the most common reproductive-endocrine condition in premenopausal women. Troxerutin, a common clinical anti-coagulant agent, was shown to work as a strong IL-22 boosting agent counteracting the hyperactivated gonadotrophin releasing hormone (GnRH) neurons and heightened GnRH release, the neuroendocrine origin of PCOS with unknown mechanism in rats. Exploring the off-label use of troxerutin medication for PCOS is thus sorely needed. MethodsSerum IL-22 content and hypothalamic IL-22 protein were detected. Inflammatory factor levels in hypothalamo-pituitary were evaluated. Immunofluorescence staining was employed to determine the activation and M1/M2-prone polarization of microglia in arcuate hypothalamus and median eminence. RNA-sequencing and transcriptome analysis were applied to explore the potential driver of microglia M2-polarization in response to IL-22 bolstering effect. The function of microglial IL-22/IL-22R1/IRF3 system was further verified using in vivo knockdown of IL-22R1 and a potent IRF3 inhibitor in BV2 microglial cell lines in vitro. ResultsTroxerutin augmented serum IL-22 content, and its consequent spillover into the hypothalamus led to the direct activation of IL-22R1/IRF3 system on microglia, thereby promoted microglia M2 polarization in arcuate hypothalamus and median eminence, dampened hypothalamic neuroinflammation, inhibited hyperactive GnRH and rescued a breadth of PCOS-like traits in dihydrotestosterone (DHT) rats. The salutary effects of troxerutin treatment on hypothalamic neuroinflammation, microglial M1/2 polarization, GnRH secretion and numerous PCOS-like features were blocked by in vivo knockdown of IL-22R1. Moreover, evidence in vitro illustrated that IL-22 supplement to BV-2 microglia cell lines promoted M2 polarization, overproduction of anti-inflammatory marker and limitation of pro-inflammatory factors, whereas these IL-22 effects were blunted by geldanamycin, a potent IRF3 inhibitor. ConclusionHere, the present study reported the potential off-label use of troxerutin medication, a common clinical anti-coagulant agent and an endogenous IL-22 enhancer, for multiple purposes in PCOS. The rational underlying the application of troxerutin as a therapeutic choice in PCOS derived from its activity as an IL-22 memetic agent targeting the neuro-endocrine origin of PCOS, and its promotive impact on microglia M2 polarization via activating microglial IL-22R1/IRF3 system in the arcuate hypothalamus and median eminence of DHT female rats.

EML-PSP: A novel ensemble machine learning-based physical security paradigm using cross-domain ultra-fused feature extraction with hybrid data augmentation scheme

Seismic signals classification has many real-time applications related to monitoring and collecting information for investigations, public safety, and prevention of security breaches. We cross-amalgamated the seismic signals with acoustic data augmentation/feature extraction techniques, keeping the beneficial effects of each domain. In this context, we have identified the human walk from that of an animal by manipulating the seismic response. This work presents a robust automated system for surveillance against noisy environments for the classification of seismic events, which is trained to exploit the collected geo signals, namely the physical security dataset (PSD). In this context, an ensemble machine learning-based integrated physical security paradigm (EML-PSP) framework is proposed for automatically classifying humans and animals on seismic signals through a cross-domain ultra-fused feature extraction (UFFE) module using numerous speech-related feature extraction approaches. For the model to learn considerably, we have introduced a hybrid augmentation module (HAM) to synthesize realistic seismic signals based on multiple acoustic augmentation schemes. The ensemble features with enhanced discrimination power have been used to train ensemble algorithms like light-gradient boosted machine (LGBM), random forest-, and adaptive boosting-models. The exhaustive comparison of the proposed solution has been carried out with other state-of-the-art methods. On exploiting the UFFE-based features, the performance of the LGBM ensemble outnumbered other classifiers with an F1-Score of 0.9961 ± 0.0031. The Matthews correlation coefficient and accuracy were 0.9841 ± 0.0127 and 99.4111 ± 0.0047 percent, respectively. The geo sensor’s PSD results illustrated that the EML-PSP framework has adequate physical security and surveillance prospects.

Classification of dendritic spiking neurons’ shape through clustering and machine learning techniques

A synapse is a specialized region between two adjacent neurons that allows information to be transmitted from one cell to another. The formation of these connections and transfer of signals via electrical impulses is a critical characteristic of neuronal cells. The synapse is formed by the axonal bouton on the axon side and the dendritic spine, a specialized outgrowth of the dendritic membrane, on the dendrite side. Dendritic spines exhibit diverse shapes and sizes, differing significantly across brain regions, cell categories, and animal species. Changes in dendritic spine morphology occur in neurodevelopmental and neurodegenerative ailments while also responding to external stimuli. Although deemed to facilitate synaptic plasticity, further investigation is essential for establishing the correlation between spine construction and its function. To address the issue in modern neurobiology of characterizing synapse morphology on 3D neuron images, the development of effective analytical methods is necessary. Our team has produced an open-source software solution for precise dendritic spine segmentation using 3D dendrite images. This software calculates the 10 most widely used 3D-adapted morphological features [1, 2] and enables classification and clustering of dendritic spine data sets to determine their shape. In addition to numerical features for describing the shape of a dendritic spine, researchers proposed using a histogram of chord lengths, known as the chord length distribution histogram (CLDH). This involves generating a set of random chords within the dendritic spine’s volume, connecting its outer boundaries and forming a histogram. By setting n=30 000, the probabilistic fluctuations of the histogram become insignificant. The derived metrics were then used for clustering and classifying the dataset. Classification based on predetermined morphological groups is a frequently used approach for analyzing the morphology of dendritic spines. This method involves categorizing spines into established groups such as thin, mushroom, and stubby. Experimenters generally perform classification in a semi-automated manner, leading to considerable error. We have created a spine categorization tool using a machine learning algorithm. The tool classifies spines based on a consensus reached by eight experts who manually labeled the training dataset. The accuracy of this method surpasses 77% when using classical morphological features and is comparable to expert labeling. The implementation of this approach reduces classification bias and complexity. Recent studies, including those using live microscopy in vitro and in vivo, indicate that dendritic spine shapes exhibit a continuum rather than distinct categories [3]. Therefore, it is essential to establish a dependable methodology for evaluating and examining the morphology of dendritic spines. We have created a clustering tool that establishes both the number of groups and their content based on data, rather than the experimenter’s discretion. This tool leverages the k-means and DBSCAN algorithms for its representation. Three clustering methods are presented to determine the number of clusters: the silhouette method, the elbow method, and a novel method, developed by the authors, based on the max class divergence criteria. The authors assume that cluster quality improves as clusters differ significantly in the number of mushroom/thin/stubby spine classes, as marked by experts. The benefit of this approach is that it considers the particular data type for clustering. Without this knowledge, assessing the quality of clustering is challenging. The use of the CLDH metric for clustering yielded a consistent and stable number of clusters (n=5) across all three methods described. These clusters contain dendritic spines that share similar shapes and have been validated by experts. In contrast, using classical metrics resulted in a variable cluster count ranging from n=4 to n=14. These findings suggest that the CLDH metric, with its complexity, provides enough information about synapse shape to enable precise clustering.

Gnuastro: Estimating the Zero-point Magnitude in Astronomical Imaging

Calibration of pixel values is a fundamental step for accurate measurements in astronomical imaging. In astronomical jargon this is known as estimating zero-point magnitude. Here, we introduce a newly added script in GNU Astronomy Utilities (Gnuastro) version 0.20 for the zero-point magnitude estimation, named: astscript-zero-point. The script offers numerous features, such as the flexibility to use either image(s) or a catalog as the reference data set. Additionally, steps are parallelized to enhance efficiency for big data. Thanks to Gnuastro’s minimal dependencies, the script is both flexible and portable. The figures of this research note are reproducible with Maneage, on the Git commit e31dd15.

Improved binary differential evolution with dimensionality reduction mechanism and binary stochastic search for feature selection

Computer systems store massive amounts of data with numerous features, leading to the need to extract the most important features for better classification in a wide variety of applications. Poor performance of various machine learning algorithms may be caused by unimportant features that increase the time and memory required to build a classifier. Feature selection (FS) is one of the efficient approaches to reducing the unimportant features. This paper, therefore, presents a new FS, named BDE-BSS-DR, that utilizes Binary Differential Evolution (BDE), Binary Stochastic Search (BSS) algorithm, and Dimensionality Reduction (DR) mechanism. The BSS algorithm increases the search capability of the BDE by escaping from local optimal points and exploring the search space. The DR mechanism then reduces the dimensions of the search space gradually. As a result of using DR, the local optima of the search space and the problem of wrong removal of important features before starting the search process are reduced. The algorithm's efficiency is evaluated on 20 different medical datasets. The obtained outcomes indicate that the BDE-BSS-DR outperforms the BDE and BDE-BSS algorithms significantly. Furthermore, the effectiveness of the proposed algorithms in selecting the most important features of the heart disease data, several cancer diseases, and COVID-19 are also compared with several other state-of-the-art methods. Our results show that the BDE-BSS-DR with SVM classifier has a significant advantage over other methods with an average classification accuracy of 95.05% in heart disease and 99.40% in COVID-19 disease. In addition, the comparisons made with KNN and SVM classification prove the efficiency of the DR and BSS in generating a subset of optimal and informative features.

Filter unsupervised spectral feature selection method for mixed data based on a new feature correlation measure

In recent years, Unsupervised Feature Selection (UFS) methods have attracted considerable interest in different research areas due to their wide application in problems where unlabeled data appears. Nevertheless, few UFS methods can process datasets described by both numerical and non-numerical features (mixed data). This paper introduces a new filter UFS method based on a new feature correlation measure for mixed data to select a relevant and non-redundant feature subset. The proposed method addresses the feature selection problem in two stages through a strategy that combines Spectral Feature Selection to identify relevant features and a Pair-wise Redundancy Analysis to remove those features with a high correlation with others. According to our experiments, the proposed feature selection method based on the introduced feature correlation measure provides better quality results than previous filter UFS methods for mixed data reported in the literature.

Strain-controlled creep-fatigue interaction property of Nb521 refractory alloy: Hold time effect and life prediction

Strain-controlled creep-fatigue interaction (CFI) tests were conducted for NbW alloy, i.e., Nb521 alloy, at 900 °C with a strain amplitude of ±0.3% under atmospheric conditions to study the effect of hold time on the CFI failure behaviour, with the results indicating that the creep-fatigue life of the Nb521 alloy decreased with an increase in the hold time. The decline rate gradually flattened, with no saturation effect observed. Furthermore, with an increase in the hold time, the hardening rate of the Nb521 alloy gradually decreased, but the softening rate remained high. Fatigue fractures can be divided into stable propagation, rapid propagation, and final fracture zones according to their morphological characteristics. Compared with the stable propagation zone of the pure fatigue fracture surface, the creep damage caused by the hold time resulted in numerous intergranular fracture features in the stable propagation zone of the CFI fracture surface, indicating that the crack propagation mode changed from a transgranular fracture to a mixed transgranular–intergranular fracture. The strain energy density exhaustion model under nonlinear damage summation better reflects the CFI damage behaviour, with the creep-fatigue life prediction result considered acceptable.