Search

Cardio Vascular Diseases (CVD) has become a serious concern for humans as fatalities rate due to CVD are increasing at an alarming pace. With the aid of machine learning techniques, heart illnesses can be predicted much earlier, and therapy or dietary changes can prevent deaths. By combining predictions from various individual models, the machine learning technique known as ensemble learning improves forecasting accuracy and resiliency. In this work, a Super Learner Ensemble Model is used where the base learners are a diverse combination of linear, probabilistic, bagging, boosting and stacking models. To improve the performance of the Super Learner Ensemble Model, an Optimized Super Learner Ensemble Model (OSLEM) is proposed, where optimal selection of base learners in the ensemble is done based on the pairwise disagreement accuracy diversity measure of classifiers in each best fitness whale obtained by different iterations of Whale Optimization Algorithm (WOA). ModifiedBoostARoota (MBAR), a wrapper feature selection technique is used to choose the most significant features of six different heart datasets and the proposed OSLEM modelled on the selected features exhibits high performance compared to other existing ensemble models. [ABSTRACT FROM AUTHOR]

Data categorization is a top concern in medical data to predict and detect illnesses; thus, it is applied in modern healthcare informatics. In modern informatics, machine learning and deep learning models have enjoyed great attention for categorizing medical data and improving illness detection. However, the existing techniques, such as features with high dimensionality, computational complexity, and long-term execution duration, raise fundamental problems. This study presents a novel classification model employing metaheuristic methods to maximize efficient positives on Chronic Kidney Disease diagnosis. The medical data is initially massively pre-processed, where the data is purified with various mechanisms, including missing values resolution, data transformation, and the employment of normalization procedures. The focus of such processes is to leverage the handling of the missing values and prepare the data for deep analysis. We adopt the Binary Grey Wolf Optimization method, a reliable subset selection feature using metaheuristics. This operation is aimed at improving illness prediction accuracy. In the classification step, the model adopts the Extreme Learning Machine with hidden nodes through data optimization to predict the presence of CKD. The complete classifier evaluation employs established measures, including recall, specificity, kappa, F-score, and accuracy, in addition to the feature selection. Data related to the study show that the proposed approach records high levels of accuracy, which is better than the existing models. [ABSTRACT FROM AUTHOR]

With the help of advancements in connected technologies, social media and networking have made a wide open platform to share information via audio, video, text, etc. Due to the invention of smartphones, video contents are being manipulated day-by-day. Videos contain sensitive or personal information which are forged for one's own self pleasures or threatening for money. Video falsification identification plays a most prominent role in case of digital forensics. This paper aims to provide a comprehensive survey on various problems in video falsification, deep learning models utilised for detecting the forgery. This survey provides a deep understanding of various algorithms implemented by various authors and their advantages, limitations thereby providing an insight for future researchers. [ABSTRACT FROM AUTHOR]

Feature selection is becoming a relevant problem within the field of machine learning. The feature selection problem focuses on the selection of the small, necessary, and sufficient subset of features that represent the general set of features, eliminating redundant and irrelevant information. Given the importance of the topic, in recent years there has been a boom in the study of the problem, generating a large number of related investigations. Given this, this work analyzes 161 articles published between 2019 and 2023 (20 April 2023), emphasizing the formulation of the problem and performance measures, and proposing classifications for the objective functions and evaluation metrics. Furthermore, an in-depth description and analysis of metaheuristics, benchmark datasets, and practical real-world applications are presented. Finally, in light of recent advances, this review paper provides future research opportunities. [ABSTRACT FROM AUTHOR]

The continuous advancement of computer networks has given rise to grave concerns regarding security and susceptibility. Network administrators utilize intrusion detection systems (IDS) to deliver essential network security. Current IDS devices produce false alarms in response to routine user activities rather than detecting novel assaults. Neural networks may be used to overcome this problem and increase detection accuracy. In this paper, we propose a hybrid approach based on neural networks and correlation-based feature selection to detect anomalies. Experimental research is done on the standard dataset NSL-KDD for intrusion detection using current attacks. We introduce a novel hybrid crowd search analysis optimization with an artificial neural network (HCSAOANN). The findings demonstrate that it outperforms in high accuracy, precision, F1-Score, and recall. In the proposed HCSAOANN algorithm, to explore the feature space, we merged the crow search optimization (CSO), which can converge into the overall best solution in the search function, with the upgraded version of the crow search analysis method. Some performance criteria were applied in the studies using an artificial neural network (ANN) as a classifier. The HCSAOANN methodology outperformed as compared to the previous fuzzy technique and achieved 98% accuracy and a 98% precision rate, which is 2.2% better than the previous CSO-ANFIS technique and 8.87% superior to the FC-ANN technique. [ABSTRACT FROM AUTHOR]

Feature selection (FS) is a crucial task in machine learning applications, which aims to select the most appropriate feature subset while maintaining high classification accuracy with the minimum number of selected features. Despite the widespread usage of metaheuristics as wrapper-based FS techniques, they show reduced effectiveness and increased computational cost when applied to high-dimensional datasets. This paper presents a novel Binary Object-Oriented Programming Optimization Algorithm (BOOPOA) for FS of high dimensional datasets, where the Object-Oriented Programming Optimization Algorithm (OOPOA) is a novel optimization technique inspired by the inheritance concept of Object-Oriented programming (OOP) languages. The effectiveness of this method in solving high dimensional FS problems is validated by using 26 datasets, most of which are of high dimension (large number of features). Seven existing FS algorithms are compared with the proposed OOPOA using various metrics, including best fitness, average fitness (AVG), selection size, and computational time. The results prove the superiority of the proposed algorithm over the other FS algorithms, having an average performance of %92.5, 0.078, 0.084, %38.9, and 8.6 min for classification accuracy, best fitness, average fitness, size reduction ratio, and computational time. The outcomes demonstrate the proposed FS approach's superiority over currently used methods.

Feature selection (FS) is a crucial task in machine learning applications, which aims to select the most appropriate feature subset while maintaining high classification accuracy with the minimum number of selected features. Despite the widespread usage of metaheuristics as wrapper-based FS techniques, they show reduced effectiveness and increased computational cost when applied to high-dimensional datasets. This paper presents a novel Binary Object-Oriented Programming Optimization Algorithm (BOOPOA) for FS of high dimensional datasets, where the Object-Oriented Programming Optimization Algorithm (OOPOA) is a novel optimization technique inspired by the inheritance concept of Object-Oriented programming (OOP) languages. The effectiveness of this method in solving high dimensional FS problems is validated by using 26 datasets, most of which are of high dimension (large number of features). Seven existing FS algorithms are compared with the proposed OOPOA using various metrics, including best fitness, average fitness (AVG), selection size, and computational time. The results prove the superiority of the proposed algorithm over the other FS algorithms, having an average performance of %92.5, 0.078, 0.084, %38.9, and 8.6 min for classification accuracy, best fitness, average fitness, size reduction ratio, and computational time. The outcomes demonstrate the proposed FS approach's superiority over currently used methods. [Display omitted] [ABSTRACT FROM AUTHOR]

In recent years, indescribable suffering from various kidney diseases has been experienced by people all over the world. The situation has been significantly worse because of chronic kidney disease (CKD). Only through an early diagnosis of CKD may kidney disease be hinder in its early stages from progressing. However, it is easier to detect the chronic kidney disease with the aid of machine learning (ML) classifier algorithms sooner than any other existing methods. The present work proposes an approach for potentially predicting CKD infection while considering patient health dataset information into consideration, employing nine distinct ML algorithms; random forest (RF), Naïve Bayes (NB), support vector machine (SVM), decision tree (DT), logistic regression (LR), extreme gradient boosting (XGB), adaptive boosting (ADB), k-nearest neighbors (KNN), and neural network (NN). Machine learning algorithms had been utilized and conducted in four experiments, then they were compared using five performance measures; F1-score, precision, accuracy, recall and run time are used to evaluate the performance. Results had shown that AdaBoost (ADA) outperformed other techniques with achieved accuracy of 99.17%. [ABSTRACT FROM AUTHOR]

O-glycosylation (Oglyc) plays an important role in various biological processes. The key to understanding the mechanisms of Oglyc is identifying the corresponding glycosylation sites. Two critical steps, feature selection and classifier design, greatly affect the accuracy of computational methods for predicting Oglyc sites. Based on an efficient feature selection algorithm and a classifier capable of handling imbalanced datasets, a new computational method, ChiMIC-based balanced decision table O-glycosylation (CBDT-Oglyc), is proposed. ChiMIC-based balanced decision table for O-glycosylation (CBDT-Oglyc), is proposed to predict Oglyc sites in proteins. Sequence characterization is performed by combining amino acid composition (AAC), undirected composition of k -spaced amino acid pairs (undirected-CKSAAP) and pseudo-position-specific scoring matrix (PsePSSM). Chi-MIC-share algorithm is used for feature selection, which simplifies the model and improves predictive accuracy. For imbalanced classification, a backtracking method based on local chi-square test is designed, and then cost-sensitive learning is incorporated to construct a novel classifier named ChiMIC-based balanced decision table (CBDT). Based on a 1:49 (positives:negatives) training set, the CBDT classifier achieves significantly better prediction performance than traditional classifiers. Moreover, the independent test results on separate human and mouse glycoproteins show that CBDT-Oglyc outperforms previous methods in global accuracy. CBDT-Oglyc shows great promise in predicting Oglyc sites and is expected to facilitate further experimental studies on protein glycosylation. [ABSTRACT FROM AUTHOR]

In cloud computing Resource allocation is a very complex task. Handling the customer demand makes the challenges of on-demand resource allocation. Many challenges are faced by conventional methods for resource allocation in order tomeet the Quality of Service (QoS) requirements of users. For solving the about said problems a new method was implemented with the utility of machine learning framework of resource allocation by utilizing the cloud computing technique was taken in to an account in this research work. The accuracy in the machine learning algorithm can be improved by introducing Bat Algorithm with feature selection (BFS) in the proposed work, this further reduces the inappropriate features from the data. The similarities that were hidden can be demoralized by the Support Vector Machine (SVM) classifier which is also determine the subspace vector and then a new feature vector can be predicted by using SVM. For an unexpected circumstance SVM model can make a resource allocation decision. The efficiency of proposed SVM classifier of resource allocation can be highlighted by using a singlecell multiuser massive Multiple-Input Multiple Output (MIMO) system, with beam allocation problem as an example. The proposed resource allocation based on SVM performs efficiently than the existing conventional methods; this has been proven by analysing its results. [ABSTRACT FROM AUTHOR]

Text classification has been highlighted as the key process to organize online texts for better communication in the Digital Media Age. Text classification establishes classification rules based on text features, so the accuracy of feature selection is the basis of text classification. Facing fast-increasing Chinese electronic documents in the digital environment, scholars have accumulated quite a few algorithms for the feature selection for the automatic classification of Chinese texts in recent years. However, discussion about how to adapt existing feature selection algorithms for various types of Chinese texts is still inadequate. To address this, this study proposes three improved feature selection algorithms and tests their performance on different types of Chinese texts. These include an enhanced CHI square with mutual information (MI) algorithm, which simultaneously introduces word frequency and term adjustment (CHMI); a term frequency–CHI square (TF–CHI) algorithm, which enhances weight calculation; and a term frequency–inverse document frequency (TF–IDF) algorithm enhanced with the extreme gradient boosting (XGBoost) algorithm, which improves the algorithm's ability of word filtering (TF–XGBoost). This study randomly chooses 3000 texts from six different categories of the Sogou news corpus to obtain the confusion matrix and evaluate the performance of the new algorithms with precision and the  F 1 -score. Experimental comparisons are conducted on support vector machine (SVM) and naive Bayes (NB) classifiers. The experimental results demonstrate that the feature selection algorithms proposed in this paper improve performance across various news corpora, although the best feature selection schemes for each type of corpus are different. Further studies of the application of the improved feature selection methods in other languages and the improvement in classifiers are suggested. [ABSTRACT FROM AUTHOR]

Parkinson's Disease and Adductor-type Spasmodic Dysphonia are two neurological disorders that greatly decrease the quality of life of millions of patients worldwide. Despite this great diffusion, the related diagnoses are often performed empirically, while it could be relevant to count on objective measurable biomarkers, among which researchers have been considering features related to voice impairment that can be useful indicators but that can sometimes lead to confusion. Therefore, here, our purpose was aimed at developing a robust Machine Learning approach for multi-class classification based on 6373 voice features extracted from a convenient voice dataset made of the sustained vowel/e/ and an ad hoc selected Italian sentence, performed by 111 healthy subjects, 51 Parkinson's disease patients, and 60 dysphonic patients. Correlation, Information Gain, Gain Ratio, and Genetic Algorithm-based methodologies were compared for feature selection, to build subsets analyzed by means of Naïve Bayes, Random Forest, and Multi-Layer Perceptron classifiers, trained with a 10-fold cross-validation. As a result, spectral, cepstral, prosodic, and voicing-related features were assessed as the most relevant, the Genetic Algorithm performed as the most effective feature selector, while the adopted classifiers performed similarly. In particular, a Genetic Algorithm + Naïve Bayes approach brought one of the highest accuracies in multi-class voice analysis, being 95.70% for a sustained vowel and 99.46% for a sentence. [ABSTRACT FROM AUTHOR]

Earthquakes are cataclysmic events that can harm structures and human existence. The estimation of seismic damage to buildings remains a challenging task due to several environmental uncertainties. The damage grade categorization of a building takes a significant amount of time and work. The early analysis of the damage rate of concrete building structures is essential for addressing the need to repair and avoid accidents. With this motivation, an ANOVA-Statistic-Reduced Deep Fully Connected Neural Network (ASR-DFCNN) model is proposed that can grade damages accurately by considering significant damage features. A dataset containing 26 attributes from 762,106 damaged buildings was used for the model building. This work focused on analyzing the importance of feature selection and enhancing the accuracy of damage grade categorization. Initially, a dataset without primary feature selection was utilized for damage grade categorization using various machine learning (ML) classifiers, and the performance was recorded. Secondly, ANOVA was applied to the original dataset to eliminate the insignificant attributes for determining the damage grade. The selected features were subjected to 10-component principal component analysis (PCA) to scrutinize the top-ten-ranked significant features that contributed to grading the building damage. The 10-component ANOVA PCA-reduced (ASR) dataset was applied to the classifiers for damage grade prediction. The results showed that the Bagging classifier with the reduced dataset produced the greatest accuracy of 83% among all the classifiers considering an 80:20 ratio of data for the training and testing phases. To enhance the performance of prediction, a deep fully connected convolutional neural network (DFCNN) was implemented with a reduced dataset (ASR). The proposed ASR-DFCNN model was designed with the sequential keras model with four dense layers, with the first three dense layers fitted with the ReLU activation function and the final dense layer fitted with a tanh activation function with a dropout of 0.2. The ASR-DFCNN model was compiled with a NADAM optimizer with the weight decay of L2 regularization. The damage grade categorization performance of the ASR-DFCNN model was compared with that of other ML classifiers using precision, recall, F-Scores, and accuracy values. From the results, it is evident that the ASR-DFCNN model performance was better, with 98% accuracy. [ABSTRACT FROM AUTHOR]

Malware is the term used to describe any malicious software or code that is harmful to systems. From day to day, new malicious programs appear. To classify malware according to its characteristics, machine learning is now being used; this is because most new malware contains patterns that are similar to old ones. This paper proposes two feature selection methods based on Genetic Programming (GP) for predicting malware; the first is called Genetic Programming-Mean (GPM), and the second is called Genetic Programming-Mean Plus (GPMP). The results of these two methods were compared with three state-of-the-art popular feature selection techniques: filter-based, wrapper-based, and Chi-square. In this work, we compare the two proposed methods (GPM and GPMP) with these three widely used feature selection techniques. The results demonstrate that the proposed techniques beat these state-of-the-art ones in terms of accuracy and F-score. The results also revealed that the proposed methods employed less computation time and hence an enhanced performance when compared with filter-based, and wrapper-based feature selection. The proposed methods were evaluated using four datasets. Two classifiers were used to evaluate the proposed feature selection methods: Random Forest and Decision Tree. When a Random Forest classifier is used, our results showed that it outperformed the Decision Tree classifier in indicators, such as F1-score, recall, and precision. The analysis of results using Random Forest and Decision Tree proves that the proposed method is highly efficient. [ABSTRACT FROM AUTHOR]

This research work implements an initial methodology for the assessment of Battery Energy Storage Systems (BESSs) based on Remaining Useful Lifetime (RUL), and its main contribution is the modeling and estimation of Health and Charge indicators through regression algorithms and binary classifiers during the battery's operation. Linear Regression, Ridge Regression, and Lasso Regression are the main algorithms for modeling the State of Health (SOH), while Decision Tree, Naïve Bayes, and Logistic Regression are implemented as binary classifiers to estimate the charge and discharge during battery operation. Additional data science techniques are executed to provide feature selection, validation, and metrics of performance. The results show that binary classifiers achieve a remarkable accuracy, around 95% for charge and discharge predictions, which is supported by experimental battery measurements. Similarly, regression algorithms achieve accuracy results around 97% and provide a basis for determining the Remaining Useful Lifetime (RUL) according to the End-of-Life (EOL) criteria of a BESS. [ABSTRACT FROM AUTHOR]

With the massive development of Internet technologies and e-commerce technology, people rely on the product reviews provided by users through web. Sentiment analysis of online reviews has become a mainstream way for businesses on e-commerce platforms to satisfy the customers. This paper proposes a novel hybrid framework with Black Widow Optimization (BWO) based feature reduction technique which combines the merits of both machine learning and lexicon-based approaches to attain better scalability and accuracy. The scalability problem arises due to noisy, irrelevant and unique features present in the extracted features from proposed approach, which can be eliminated by adopting an effective feature reduction technique. In our proposed BWO approach, without changing the accuracy (90%), the feature-set size is reduced up to 43%. The proposed feature selection technique outperforms other commonly used Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) based feature selection techniques with reduced computation time of 21 sec. Moreover, our sentiment analysis approach is analyzed using performance metrics such as precision, recall, F-measure, and computation time. Many organizations can use these online reviews to make well-informed decisions towards the users' interests and preferences to enhance customer satisfaction, product quality and to find the aspects to improve the products, thereby to generate more profits. [ABSTRACT FROM AUTHOR]

COVID - 19 affected severely worldwide. The pandemic has caused many causalities in a very short span. The IoT-cloud-based healthcare model requirement is utmost in this situation to provide a better decision in the covid-19 pandemic. In this paper, an attempt has been made to perform predictive analytics regarding the disease using a machine learning classifier. This research proposed an enhanced KNN (k NearestNeighbor) algorithm eKNN, which did not randomly choose the value of k. However, it used a mathematical function of the dataset's sample size while determining the k value. The enhanced KNN algorithm eKNN has experimented on 7 benchmark COVID-19 datasets of different size, which has been gathered from standard data cloud of different countries (Brazil, Mexico, etc.). It appeared that the enhanced KNN classifier performs significantly better than ordinary KNN. The second research question augmented the enhanced KNN algorithm with feature selection using ACO (Ant Colony Optimization). Results indicated that the enhanced KNN classifier along with the feature selection mechanism performed way better than enhanced KNN without feature selection. This paper involves proposing an improved KNN attempting to find an optimal value of k and studying IoT-cloud-based COVID - 19 detection. [ABSTRACT FROM AUTHOR]

Classification algorithm selection is an important concern for breast cancer diagnosis. The traditional routine of adopting a unique performance metric for evaluating classifiers is not adequate in the case of micro-array gene expression dataset. This paper introduces an MCDM technique to evaluate classification algorithms in breast cancer forecasting by seeing different performance measure along with feature space. An empirical study is designed to support an overall assessment of classifiers on micro-array datasets using well-known MCDM technique. TOPSIS is used to rank 11 prominent assessment criteria of different classifiers. First, the sequence order of 20 classifiers along with 11 assessment criteria is generated. Further topmost classifiers are grounded on their performances highlighting the role of feature selection in the overall process supporting the genuine assessment of classifiers over any solitary performance criteria. Result indicates that AdaBoostM1 and Iterative Classifier Optimizer are graded as topmost classifiers without and with feature selection, respectively, grounded on their performances on different measures. Furthermore, the proposed MCDM-based model can reconcile distinct or even inconsistent evaluation performance to grasp a group agreement in a complicated decision-making environment. [ABSTRACT FROM AUTHOR]

The number of attacks is growing tremendously in tandem with the growth of internet technologies. As a result, protecting the private data from prying eyes has become a critical and tough undertaking. Many intrusion detection solutions have been offered by researchers in order to decrease the effect of these attacks. For attack detection, the prior system has created an SMSRPF (Stacking Model Significant Rule Power Factor) classifier. To provide creative instance detection, the SMSRPF combines the detection of trained classifiers such as DT (Decision Tree) and RF (Random Forest). Nevertheless, it does not generate any accurate findings that are adequate. The suggested system has built an EWF (Ensemble Wrapper Filter) feature selection with SMSRPF classifier for attack detection so as to overcome this problem. The UNSW-NB15 dataset is used as an input in this proposed research project. Specifically, min–max normalization approach is used to pre-process the incoming data. The feature selection is then carried out using EWF. Based on the selected features, SMSRPF classifiers are utilized to detect the attacks. The SMSRPF is integrated with the trained classifiers such as DT and RF to create creative instance detection. After that, the testing data is classified using MCAR (Multi-Class Classification based on Association Rules). The SRPF judges the rules correctly even when the confidence and the lift measures fail. Regarding accuracy, precision, recall, f-measure, computation time, and error, the experimental findings suggest that the new system outperforms the prior systems. [ABSTRACT FROM AUTHOR]

As per World Health Organization report which was released in the year of 2019, Diabetes claimed the lives of approximately 1.5 million individuals globally in 2019 and around 450 million people are affected by diabetes all over the world. Hence it is inferred that diabetes is rampant across the world with the majority of the world population being affected by it. Among the diabetics, it can be observed that a large number of people had failed to identify their disease in the initial stage itself and hence the disease level moved from Type-1 to Type-2. To avoid this situation, we propose a new fuzzy logic based neural classifier for early detection of diabetes. A set of new neuro-fuzzy rules is introduced with time constraints that are applied for the first level classification. These levels are further refined by using the Fuzzy Cognitive Maps (FCM) with time intervals for making the final decision over the classification process. The main objective of this proposed model is to detect the diabetes level based on the time. Also, the set of neuro-fuzzy rules are used for selecting the most contributing values over the decision-making process in diabetes prediction. The proposed model proved its efficiency in performance after experiments conducted not only from the repository but also by using the standard diabetic detection models that are available in the market. [ABSTRACT FROM AUTHOR]

Clay, earthen elements, powders, and water mixtures are typically manipulated into desired shapes to create ceramics. The ceramic is then dispersed in a blast furnace, which is a high-temperature oven, after it has been molded. Varnishes are paint-like materials that are used to decorate ceramics and are resistant to water. Manually identifying ceramic samples can lead to the discovery of flaws. The chemical composition of the finished ceramic tiles is not visible. Exact identification of ceramic samples is still a difficult task for the user, as it necessitates more hands-on experience. With this overview, this paper focus on designing an effective workflow for classifying the ceramic samples based on chemical composition. The ceramic chemical sample dataset from KAGGLE with the dataset size of 88 with 19 features having 5 classes of ceramic as 0-"FLQ Ceramic", 1- "DYBS Ceramic", 2-"DYNS Ceramic", 3- "DYY Ceramic", 4- "DYMQC Ceramic". The data is preprocessed and normalized for splitting the training and testing dataset. The normalized dataset is fitted to Anova test analysis to extract the significant features. The insignificant features from Anova test is deleted from the original database dataset and anova normalized dataset is fitted to Exhaustive feature selection using KNN, Naive Bayes, Logistic regression, Decision Tree and Random Forest classifier. The exhaustive feature selected dataset is applied to the above-mentioned classifier algorithms to examine the efficiency with the presence and absence of feature scaling. The exhaustive feature selected dataset is again applied to random oversampling in order to improve the classifier performance. The random oversampled exhaustive feature selected dataset is applied to the above mentioned classifier algorithms to compare the performance metrics like precision, accuracy, fscore, recall and run time. Experimental results shows that the decision tree exhibits 49% accuracy with exhaustive feature selected dataset. The same decision tree classifier shows 100% accuracy after applying random oversampling with exhaustive feature selected dataset. [ABSTRACT FROM AUTHOR]

Abstract Background As many complex omics data have been generated during the last two decades, dimensionality reduction problem has been a challenging issue in better mining such data. The omics data typically consists of many features. Accordingly, many feature selection algorithms have been developed. The performance of those feature selection methods often varies by specific data, making the discovery and interpretation of results challenging. Methods and results In this study, we performed a comprehensive comparative study of five widely used supervised feature selection methods (mRMR, INMIFS, DFS, SVM-RFE-CBR and VWMRmR) for multi-omics datasets. Specifically, we used five representative datasets: gene expression (Exp), exon expression (ExpExon), DNA methylation (hMethyl27), copy number variation (Gistic2), and pathway activity dataset (Paradigm IPLs) from a multi-omics study of acute myeloid leukemia (LAML) from The Cancer Genome Atlas (TCGA). The different feature subsets selected by the aforesaid five different feature selection algorithms are assessed using three evaluation criteria: (1) classification accuracy (Acc), (2) representation entropy (RE) and (3) redundancy rate (RR). Four different classifiers, viz., C4.5, NaiveBayes, KNN, and AdaBoost, were used to measure the classification accuary (Acc) for each selected feature subset. The VWMRmR algorithm obtains the best Acc for three datasets (ExpExon, hMethyl27 and Paradigm IPLs). The VWMRmR algorithm offers the best RR (obtained using normalized mutual information) for three datasets (Exp, Gistic2 and Paradigm IPLs), while it gives the best RR (obtained using Pearson correlation coefficient) for two datasets (Gistic2 and Paradigm IPLs). It also obtains the best RE for three datasets (Exp, Gistic2 and Paradigm IPLs). Overall, the VWMRmR algorithm yields best performance for all three evaluation criteria for majority of the datasets. In addition, we identified signature genes using supervised learning collected from the overlapped top feature set among five feature selection methods. We obtained a 7-gene signature (ZMIZ1, ENG, FGFR1, PAWR, KRT17, MPO and LAT2) for EXP, a 9-gene signature for ExpExon, a 7-gene signature for hMethyl27, one single-gene signature (PIK3CG) for Gistic2 and a 3-gene signature for Paradigm IPLs. Conclusion We performed a comprehensive comparison of the performance evaluation of five well-known feature selection methods for mining features from various high-dimensional datasets. We identified signature genes using supervised learning for the specific omic data for the disease. The study will help incorporate higher order dependencies among features.

In a newborn baby, the particular complication is jaundice. Jaundice is due to many reasons. An increase in the bilirubin level denotes the presence of jaundice. Neonatal hyperbilirubinemia is most common in the first postnatal week. Early prediction and classification of jaundice are essential to reduce the mortality rate. Diagnosis of the disease using computer vision techniques helps to achieve accuracy in prediction and classification. Here, I studied and extracted the information from medical data mining and achieved the goal. It involves examining, analyzing, extracting, selecting, and classifying the features. Finally, it provides treatment suggestions. It enables the physician to perform early prediction and provide appropriate jaundice treatment. Computer vision and machine learning techniques make the process easy and simple. The optimized method of classification increases accuracy. The review provides a detailed description of the diagnosis of neonatal jaundice using the skin region. The entire survey is performed based on their processing steps. Examining a huge number of medical images can reduce the risk. However, the medical images incorporate a huge amount of information about the bilirubin level on the baby's skin, and the increase in the number of images makes their accurate assessment a challenging task. This paper reviews various promising methods developed in computer vision to detect and classify neonatal jaundice. It presents a comprehensive analysis of various approaches. The analysis focuses on the advantages and disadvantages of various methods. [ABSTRACT FROM AUTHOR]

Selecting relevant feature subsets is vital in machine learning, and multiclass feature selection is harder to perform since most classifications are binary. The feature selection problem aims at reducing the feature set dimension while maintaining the performance model accuracy. Datasets can be classified using various methods. Nevertheless, metaheuristic algorithms attract substantial attention to solving different problems in optimization. For this reason, this paper presents a systematic survey of literature for solving multiclass feature selection problems utilizing metaheuristic algorithms that can assist classifiers selects optima or near optima features faster and more accurately. Metaheuristic algorithms have also been presented in four primary behavior-based categories, i.e., evolutionary-based, swarm-intelligence-based, physics-based, and human-based, even though some literature works presented more categorization. Further, lists of metaheuristic algorithms were introduced in the categories mentioned. In finding the solution to issues related to multiclass feature selection, only articles on metaheuristic algorithms used for multiclass feature selection problems from the year 2000 to 2022 were reviewed about their different categories and detailed descriptions. We considered some application areas for some of the metaheuristic algorithms applied for multiclass feature selection with their variations. Popular multiclass classifiers for feature selection were also examined. Moreover, we also presented the challenges of metaheuristic algorithms for feature selection, and we identified gaps for further research studies. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common types of cancer around the world. The early‐stage recognition of breast cancer is favourable for the diagnosis and treatment of the affecting patient. Data mining approaches can ease the diagnosis of breast cancer by analysis of the associated dataset for real‐time decision‐making. The present study proposes an effective transformation approach of experimental attributes of a breast cancer dataset using the latent semantic analysis and the fusion of derived features with classification methods for accurate recognition of breast cancer. The proposed approach is validated using the most widely used benchmark and open‐access breast cancer dataset. The transformed features of the original dataset result in 100% recognition efficiency using a multilayer perceptron, support vector machine, multi‐class classifier and functional tree classifiers. Other classifiers, like naïve Bayes, rotation forest, simple linear logistic regression and logistic model tree result in recognition accuracy between 96.85% and 99.30% using a similar feature subset. Besides, the optimal subset of derived features has been affirmed based on the evaluation metrics of classification approaches. [ABSTRACT FROM AUTHOR]

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that severely impairs an individual's cognitive, linguistic, object recognition, communication, and social abilities. This situation is not treatable, although early detection of ASD can assist to diagnose and take proper steps for mitigating its effect. Using various artificial intelligence (AI) techniques, ASD can be detected an at earlier stage than with traditional methods. The aim of this study was to propose a machine learning model that investigates ASD data of different age levels and to identify ASD more accurately. In this work, we gathered ASD datasets of toddlers, children, adolescents, and adults and used several feature selection techniques. Then, different classifiers were applied into these datasets, and we assessed their performance with evaluation metrics including predictive accuracy, kappa statistics, the f1-measure, and AUROC. In addition, we analyzed the performance of individual classifiers using a non-parametric statistical significant test. For the toddler, child, adolescent, and adult datasets, we found that Support Vector Machine (SVM) performed better than other classifiers where we gained 97.82% accuracy for the RIPPER-based toddler subset; 99.61% accuracy for the Correlation-based feature selection (CFS) and Boruta CFS intersect (BIC) method-based child subset; 95.87% accuracy for the Boruta-based adolescent subset; and 96.82% accuracy for the CFS-based adult subset. Then, we applied the Shapley Additive Explanations (SHAP) method into different feature subsets, which gained the highest accuracy and ranked their features based on the analysis. [ABSTRACT FROM AUTHOR]

In the field of tumor diagnosis, the AI-assisted diagnosis system can accurately distinguish tumor attributes and malignant tumor stages, thereby prolonging the survival time of patients. Taking breast tumor as an example, this paper proposes an artificial intelligence-assisted diagnosis model based on supervised learning to solve the problem of overfitting caused by the large amount of data in the feature extraction process. When extracting features, effective feature dimensionality reduction is achieved by introducing hierarchical clustering analysis, and the classified feature data is used as the feature input of the artificial neural network model, so as to realize the effective training of the classifier. The experimental results show that the accuracy and AUC value of the proposed algorithm are improved compared with the control algorithm, indicating that the model can not only solve the problem of overfitting caused by the description of massive feature regions, but also enhance the generalization of the artificial intelligence-aided diagnosis system. The ability to achieve high-precision differentiation of mammography-targeted breast tumors. [ABSTRACT FROM AUTHOR]

In this research, we study a new metaheuristic algorithm called Moth–Flame Optimization (MFO) for hyperspectral band selection. With the hundreds of highly correlated narrow spectral bands, the number of training samples required to train a statistical classifier is high. Thus, the problem is to select a subset of bands without compromising the classification accuracy. One of the ways to solve this problem is to model an objective function that measures class separability and utilize it to arrive at a subset of bands. In this research, we studied MFO to select optimal spectral bands for classification. MFO is inspired by the behavior of moths with respect to flames, which is the navigation method of moths in nature called transverse orientation. In MFO, a moth navigates the search space through a process called transverse orientation by keeping a constant angle with the Moon, which is a compelling strategy for traveling long distances in a straight line, considering that the Moon's distance from the moth is considerably long. Our research tested MFO on three benchmark hyperspectral datasets—Indian Pines, University of Pavia, and Salinas. MFO produced an Overall Accuracy (OA) of 88.98%, 94.85%, and 97.17%, respectively, on the three datasets. Our experimental results indicate that MFO produces better OA and Kappa when compared to state-of-the-art band selection algorithms such as particle swarm optimization, grey wolf, cuckoo search, and genetic algorithms. The analysis results prove that the proposed approach effectively addresses the spectral band selection problem and provides a high classification accuracy. [ABSTRACT FROM AUTHOR]

Background: As many complex omics data have been generated during the last two decades, dimensionality reduction problem has been a challenging issue in better mining such data. The omics data typically consists of many features. Accordingly, many feature selection algorithms have been developed. The performance of those feature selection methods often varies by specific data, making the discovery and interpretation of results challenging. Methods and results: In this study, we performed a comprehensive comparative study of five widely used supervised feature selection methods (mRMR, INMIFS, DFS, SVM-RFE-CBR and VWMRmR) for multi-omics datasets. Specifically, we used five representative datasets: gene expression (Exp), exon expression (ExpExon), DNA methylation (hMethyl27), copy number variation (Gistic2), and pathway activity dataset (Paradigm IPLs) from a multi-omics study of acute myeloid leukemia (LAML) from The Cancer Genome Atlas (TCGA). The different feature subsets selected by the aforesaid five different feature selection algorithms are assessed using three evaluation criteria: (1) classification accuracy (Acc), (2) representation entropy (RE) and (3) redundancy rate (RR). Four different classifiers, viz., C4.5, NaiveBayes, KNN, and AdaBoost, were used to measure the classification accuary (Acc) for each selected feature subset. The VWMRmR algorithm obtains the best Acc for three datasets (ExpExon, hMethyl27 and Paradigm IPLs). The VWMRmR algorithm offers the best RR (obtained using normalized mutual information) for three datasets (Exp, Gistic2 and Paradigm IPLs), while it gives the best RR (obtained using Pearson correlation coefficient) for two datasets (Gistic2 and Paradigm IPLs). It also obtains the best RE for three datasets (Exp, Gistic2 and Paradigm IPLs). Overall, the VWMRmR algorithm yields best performance for all three evaluation criteria for majority of the datasets. In addition, we identified signature genes using supervised learning collected from the overlapped top feature set among five feature selection methods. We obtained a 7-gene signature (ZMIZ1, ENG, FGFR1, PAWR, KRT17, MPO and LAT2) for EXP, a 9-gene signature for ExpExon, a 7-gene signature for hMethyl27, one single-gene signature (PIK3CG) for Gistic2 and a 3-gene signature for Paradigm IPLs. Conclusion: We performed a comprehensive comparison of the performance evaluation of five well-known feature selection methods for mining features from various high-dimensional datasets. We identified signature genes using supervised learning for the specific omic data for the disease. The study will help incorporate higher order dependencies among features. [ABSTRACT FROM AUTHOR]

The most important parts of rotating machinery are the rolling bearings. Finding bearing faults in time can avoid affecting the operation of the entire equipment. The data-driven fault diagnosis technology of bearings has recently become a research hotspot, and the starting point of research is often the acquisition of vibration signals. There are many public data sets for rolling bearings. Among them, the most widely used public dataset is Case Western Reserve University bearing center (CWRU). This paper will start from the CWRU data set, compare and analyze some basic methods of machine learning based rolling bearing fault diagnosis, and summarize the characteristics of CWRU. First, we give a comprehensive introduction to CWRU and summarize the results achieved. After that, the basic methods and principles of machine learning based rolling bearing fault diagnosis were summarized. Finally, we conduct experiments and analyze experimental results. This paper will have certain guiding significance for the future use of CWRU for machine learning based rolling bearing fault diagnosis.

Diabetes, a metabolic disease in which the blood glucose level rises over time, is one of the most common chronic diseases at present. It is critical to accurately predict and classify diabetes to reduce the severity of the disease and treat it early. One of the difficulties that researchers face is that diabetes datasets are limited and contain outliers and missing data. Additionally, there is a trade-off between classification accuracy and operational law for detecting diabetes. In this paper, an algorithm for diabetes classification is proposed for pregnant women using the Pima Indians Diabetes Dataset (PIDD). First, a preprocessing step in the proposed algorithm includes outlier rejection, imputing missing values, the standardization process, and feature selection of the attributes, which enhance the dataset's quality. Second, the classifier uses the fuzzy KNN method and modifies the membership function based on the uncertainty theory. Third, a grid search method is applied to achieve the best values for tuning the fuzzy KNN method based on uncertainty membership, as there are hyperparameters that affect the performance of the proposed classifier. In turn, the proposed tuned fuzzy KNN based on uncertainty classifiers (TFKNN) deals with the belief degree, handles membership functions and operation law, and avoids making the wrong categorization. The proposed algorithm performs better than other classifiers that have been trained and evaluated, including KNN, fuzzy KNN, naïve Bayes (NB), and decision tree (DT). The results of different classifiers in an ensemble could significantly improve classification precision. The TFKNN has time complexity O(kn2d), and space complexity O(n2d). The TFKNN model has high performance and outperformed the others in all tests in terms of accuracy, specificity, precision, and average AUC, with values of 90.63, 85.00, 93.18, and 94.13, respectively. Additionally, results of empirical analysis of TFKNN compared to fuzzy KNN, KNN, NB, and DT demonstrate the global superiority of TFKNN in precision, accuracy, and specificity. [ABSTRACT FROM AUTHOR]

This paper suggests a Naive Bayes classifier technique for identifying and categorizing gestational diabetes mellitus (GDM), GDM is a kind of diabetes mellitus that affects a small proportion of pregnant women but recovers to normal once the baby is born. The Pima Indians Diabetes Dataset was chosen for a comprehensive analysis of this critical and pervasive health disease because it contains 768 patient characteristics acquired from a machine learning source at the University of California, Irvine. The goal of the study is to apply smart technology to categorize diseases with high accuracy and precision, practically free of conceivable and potential faults, to provide satisfying findings. The approach is based on eight major characteristics that are present in the operations that are required to establish a precise and reliable categorization system. This approach involves training and testing on real data, as well as for deciding whether or not to construct a categorization model. The work was compared to earlier work and had a 96% accuracy rating. [ABSTRACT FROM AUTHOR]

The term "malicious software," which is commonly referred to as malware, describes malicious software that affects or harms computers, servers, or networks. While the numbers and complexity of malware have rapidly increased, developing a malware detection system is required to detect malware in the world of cybersecurity and test the behavior of its new features. While traditional techniques provide less efficiency in detecting new malware, machine learning techniques are used to achieve rapid malware detection in an intelligent way to improve detection performance, as malware and its application in the industry are constantly increasing. In this study, we developed a malware detection model by detecting malware using machine learning classifiers, after passing a new feature selection technique using genetic programming. We also compared the performance of all classifiers using the most recent feature selection techniques. Results show that Random Forest, Random Forest (4), and Random Tree give the best value in all experiments, while Hoeffding Tree and Decision Stump give lower values for F1-score and accuracy in all experiments. The feature selection method that proposed GPMP gives a better value than Filter-based with little differences. The accuracy and F1-score have the values of 0.881066 and 0.867546 for GPMP, and the values of 0.877624 and 0.862894 for Filter-based, respectively. The experimental results reveal that GPMP used fewer features than Filter-based, and this affected the computation and complexity of the model [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Science & Technology (JCS&T) is the property of Journal of Computer Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Among all the forms of psychological and mental disorders, depression is the most common form. Nowadays a large number of youths and adults around the world suffer from depression. Depression can cause severe problems in case of failing to detect it at an early stage or failing to ensure the timely counseling of a depressed person. It is one of the major reasons to raise suicidal cases. But ironically, our society still does not want to acknowledge depression as a mental disorder causing a significant number of depressed persons to remain unidentified and untreated. This study has investigated six different machine learning classifiers using various socio-demographic and psychosocial information to detect whether a person is depressed or not. Besides, three different feature selection methods, such as Select K-Best Features (SelectKBest), Minimum Redundancy and Maximum Relevance (mRMR), and Boruta feature selection algorithm have been used for extracting the most relevant features from the dataset. To achieve better accuracy in predicting depression, Synthetic Minority Oversampling Technique (SMOTE) has been used that reduces the class imbalance of the training data. The AdaBoost classifier with the SelectKBest feature selection technique has outperformed all other approaches with an accuracy of 92.56%. Moreover, other evaluation metrics, namely sensitivity, specificity, precision, F1-score, and area under the curve (AUC) of different models have been calculated to identify the most efficient model for predicting depression.