Proposed Feature Selection Technique Research Articles

Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection.

The Internet of Medical Things (IoMTs) is a network of connected medical equipment such as pacemakers, prosthetics, and smartwatches. Utilizing the IoMT-based system, a huge amount of data is generated, offering experts a valuable resource for tasks such as prediction, real-time monitoring, and diagnosis. To do so, the patient's health data must be transferred to database storage for processing because of the limitations of the storage and computation capabilities of IoMT devices. Consequently, concerns regarding security and privacy can arise due to the limited control over the transmitted information and reliance on wireless transmission, which leaves the network vulnerable to several kinds of attacks. Motivated by this, in this study, we aim to build and improve an efficient intrusion detection system (IDS) for IoMT networks. The proposed IDS leverages tree-based machine learning classifiers combined with filter-based feature selection techniques to enhance detection accuracy and efficiency. The proposed model is used for monitoring and identifying unauthorized or malicious activities within medical devices and networks. To optimize performance and minimize computation costs, we utilize Mutual Information (MI) and XGBoost as filter-based feature selection methods. Then, to reduce the number of the chosen features selected, we apply a mathematical set (intersection) to extract the common features. The proposed method can detect intruders while data are being transferred, allowing for the accurate and efficient analysis of healthcare data at the network's edge. The system's performance is assessed using the CICIDS2017 dataset. We evaluate the proposed model in terms of accuracy, F1 score, recall, precision, true positive rate, and false positive rate. The proposed model achieves 98.79% accuracy and a low false alarm rate 0.007 FAR on the CICIDS2017 dataset according to the experimental results. While this study focuses on binary classification for intrusion detection, we are planning to build a multi-classification approach for future work which will be able to not only detect the attacks but also categorize them. Additionally, we will consider using our proposed feature selection technique for different ML classifiers and evaluate the model's performance empirically in real-world IoMT scenarios.

Application of Salp Swarm Algorithm and Extended Repository Feature Selection Method in Bearing Fault Diagnosis

Motor fault diagnosis is an important task in the operational monitoring of electrical machines in manufacturing. This study proposes an effective bearing fault diagnosis model for electrical machinery based on machine learning techniques. The proposed model is a combination of three processes: feature extraction of signals collected from the motor based on multi-resolution analysis, fast Fourier transform, and envelope analysis. Next, redundant or irrelevant features are removed using the feature selection technique. A binary salps swarm algorithm combined with an extended repository is the proposed method to remove unnecessary features. As a result, an optimal feature subset is obtained to improve the performance of the classification model. Finally, two classifiers, k-nearest neighbor and support vector machine, are used to classify the fault of the electric motor. There are four input datasets used to evaluate the model performance, and UCI is the benchmark dataset to verify the effectiveness of the proposed feature selection technique. The remaining three datasets include the bearing dataset collected from experiments, with an average classification accuracy of 99.9%, as well as Case Western Reserve University (CWRU) and Machinery Failure Prevention Technology (MFPT), which are public datasets with average classification accuracies of 99.6% and 98.98%, respectively. The experimental results show that this method is more effective in diagnosing bearing faults than other traditional methods and prove its robustness.

Proposed Feature Selection Technique for Pattern Detection in Patients with Pneumonia Records

Pneumonia in Peru is a very serious problem. Its impact in recent years has been aggravated due to the Covid-19 pandemic, generating an increase in infections and deaths without distinguishing the age range, which placed this country on the mortality list due to the pandemic. That is why this research seeks the causes of this problem and evaluates what patterns were detected between the years 2019–2022 in patients with pneumonia in Peru from data set from the Comprehensive Health Insurance (SIS). The data presented values related to age, gender, medication and other significant values to understand the disease. The results of the research were achieved by using the PCA technique where the dimensionality of the data was reduced from 28 to 4 main features (Patient’s year of health care, Age, BMI, Department). Finally, with this processed data set, the K-Means algorithm was used, where it was determined that patients in the 60 to 85 years range are the most affected by J189 pneumonia. In addition, an environmental pattern was found in J189 pneumonia. J128, resulting in a focus on patients on the Peruvian coast in places like Lima or La Libertad.

ONE3A: one-against-all authentication model for smartphone using GAN network and optimization techniques.

This study focuses on addressing computational limits in smartphones by proposing an efficient authentication model that enables implicit authentication without requiring additional hardware and incurring less computational cost. The research explores various wrapper feature selection strategies and classifiers to enhance authentication accuracy while considering smartphone limitations such as hardware constraints, battery life, and memory size. However, the available dataset is small; thus, it cannot support a general conclusion. In this article, a novel implicit authentication model for smartphone users is proposed to address the one-against-all classification problem in smartphone authentication. This model depends on the integration of the conditional tabular generative adversarial network (CTGAN) to generate synthetic data to address the imbalanced dataset and a new proposed feature selection technique based on the Whale Optimization Algorithm (WOA). The model was evaluated using a public dataset (RHU touch mobile keystroke dataset), and the results showed that the WOA with the random forest (RF) classifier achieved the best reduction rate compared to the Harris Hawks Optimization (HHO) algorithm. Additionally, its classification accuracy was found to be the best in mobile user authentication from their touch behavior data. WOA-RF achieved an average accuracy of 99.62±0.40% with a reduction rate averaging 87.85% across ten users, demonstrating its effectiveness in smartphone authentication.

Gene Expression-Based Cancer Classification for Handling the Class Imbalance Problem and Curse of Dimensionality.

Cancer is a leading cause of death globally. The majority of cancer cases are only diagnosed in the late stages of cancer due to the use of conventional methods. This reduces the chance of survival for cancer patients. Therefore, early detection consequently followed by early diagnoses are important tasks in cancer research. Gene expression microarray technology has been applied to detect and diagnose most types of cancers in their early stages and has gained encouraging results. In this paper, we address the problem of classifying cancer based on gene expression for handling the class imbalance problem and the curse of dimensionality. The oversampling technique is utilized to overcome this problem by adding synthetic samples. Another common issue related to the gene expression dataset addressed in this paper is the curse of dimensionality. This problem is addressed by applying chi-square and information gain feature selection techniques. After applying these techniques individually, we proposed a method to select the most significant genes by combining those two techniques (CHiS and IG). We investigated the effect of these techniques individually and in combination. Four benchmarking biomedical datasets (Leukemia-subtypes, Leukemia-ALLAML, Colon, and CuMiDa) were used. The experimental results reveal that the oversampling techniques improve the results in most cases. Additionally, the performance of the proposed feature selection technique outperforms individual techniques in nearly all cases. In addition, this study provides an empirical study for evaluating several oversampling techniques along with ensemble-based learning. The experimental results also reveal that SVM-SMOTE, along with the random forests classifier, achieved the highest results, with a reporting accuracy of 100%. The obtained results surpass the findings in the existing literature as well.

Dual regularized subspace learning using adaptive graph learning and rank constraint: Unsupervised feature selection on gene expression microarray datasets

High-dimensional problems have increasingly drawn attention in gene selection and analysis. To add insult to injury, usually the number of features is greater than number of samples in microarray gene dataset which leads to an ill-posed underdetermined equation system. Poor performance and high computational time for learning algorithms are consequences of redundant features in high-dimensional data. Feature selection is a noteworthy pre-processing method to ameliorate the curse of dimensionality with aim of maximum relevancy and minimum redundancy information preservation. Likewise, unsupervised feature selection has been important since collecting labels for data is expensive. In this paper, we develop a novel robust unsupervised feature selection to select discriminative subset of features for unlabeled data based on rank constrained and dual regularized nonnegative matrix factorization. The major focus of the proposed technique is to discard redundant features while keeping the informative features. Proposed feature selection technique consists of nonnegative matrix factorization to decompose the data into feature weight matrix and representation matrix, inner product norm as regularization for both feature weight matrix and representation matrix, adaptive structure learning to preserve local information and Schatten-p norm as rank constraint. To demonstrate the effectiveness of the proposed method, numerical studies are conducted on six benchmark microarray datasets. The results show that the proposed technique outperforms eight state-of-art unsupervised feature selection techniques in terms of clustering accuracy and normalized mutual information.

ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework

Autism Spectrum Disorder (ASD) treatment requires accurate diagnosis and effective rehabilitation. Artificial intelligence (AI) techniques in medical diagnosis and rehabilitation can aid doctors in detecting a wide range of diseases more effectively. Nevertheless, due to its highly heterogeneous symptoms and complicated nature, ASD diagnostics continues to be a challenge for researchers. This study introduces an intelligent system based on the Artificial Gorilla Troops Optimizer (GTO) metaheuristic optimizer to detect ASD using Deep Learning and Machine Learning. Kaggle and UCI ML Repository are the data sources used in this study. The first dataset is the Autistic Children Data Set, which contains 3,374 facial images of children divided into Autistic and Non-Autistic categories. The second dataset is a compilation of data from three numerical repositories: (1) Autism Screening Adults, (2) Autistic Spectrum Disorder Screening Data for Adolescents, and (3) Autistic Spectrum Disorder Screening Data for Children. When it comes to image dataset experiments, the most notable results are (1) a TF learning ratio greater than or equal to 50 is recommended, (2) all models recommend data augmentation, and (3) the DenseNet169 model reports the lowest loss value of 0.512. Concerning the numeric dataset, five experiments recommend standardization and the final five attributes are optional in the classification process. The performance metrics demonstrate the worthiness of the proposed feature selection technique using GTO more than counterparts in the literature review.

Nature-inspired intrusion detection system for protecting software-defined networks controller

Software Defined Networks (SDN) is a new emerging networking architecture facilitated by a separate controller. It has a centralized architecture that serves network management and demand fulfillment from a single point. Architecturally, SDN provides lofty benefits, but security measures are a severe concern that prevents universal adoption. If the SDN controller gets compromised, the intruders could ensign the route of network traffic based on their requirements which causes damage to the entire network. These security limitations of SDN get rectified by employing the network intrusion detection system (NIDS). Deploying ML techniques for NIDS helps us to detect the anomalies within SDN. Selecting a minimal number of features is important as it decreases the computation overhead and accelerates the NIDS performances. For feature selection, a combination of k optimal features is selected using the hit-and-trial approach. As a result, it influences the system's durability for intrusion detection and pushes the model toward poor performance. In this study, we present a new hybrid framework for feature selection using Whale Optimisation Algorithm (WOA), Fisher Score (FS), and Information gain (IG), named Whale Optimization Algorithm-Fisher Feature Importance (WOA-F2I). WOA-F2I addresses the challenge of selecting the k number of an optimal subset of features. The evaluation result manifests the WOA-F2I feature selection technique that enhances the performance of the NIDS model, which backs the input for various classifiers- support vector machine, Naive Bayes, logistic regression, and stochastic gradient descent. The proposed feature selection technique also provides better performance for binary class and multi-class attack detection.

A novel hybrid hunger games algorithm for intrusion detection systems based on nonlinear regression modeling.

Along with the advancement of online platforms and significant growth in Internet usage, various threats and cyber-attacks have been emerging and become more complicated and perilous in a day-by-day base. Anomaly-based intrusion detection systems (AIDSs) are lucrative techniques for dealing with cybercrimes. As a relief, AIDS can be equipped with artificial intelligence techniques to validate traffic contents and tackle diverse illicit activities. A variety of methods have been proposed in the literature in recent years. Nevertheless, several important challenges like high false alarm rates, antiquated datasets, imbalanced data, insufficient preprocessing, lack of optimal feature subset, and low detection accuracy in different types of attacks have still remained to be solved. In order to alleviate these shortcomings, in this research a novel intrusion detection system that efficiently detects various types of attacks is proposed. In preprocessing, Smote-Tomek link algorithm is utilized to create balanced classes and produce a standard CICIDS dataset. The proposed system is based on gray wolf and Hunger Games Search (HGS) meta-heuristic algorithms to select feature subsets and detect different attacks such as distributed denial of services, Brute force, Infiltration, Botnet, and Port Scan. Also, to improve exploration and exploitation and boost the convergence speed, genetic algorithm operators are combined with standard algorithms. Using the proposed feature selection technique, more than 80 percent of irrelevant features are removed from the dataset. The behavior of the network is modeled using nonlinear quadratic regression and optimized utilizing the proposed hybrid HGS algorithm. The results show the superior performance of the hybrid algorithm of HGS compared to the baseline algorithms and the well-known research. As shown in the analogy, the proposed model obtained an average test accuracy rate of 99.17%, which has better performance than the baseline algorithm with 94.61% average accuracy.

A novel feature selection algorithm using decomposition based multi-objective guided honey badger algorithm (MO-GHBA) and NSGA-III

In solving two or more objective problems, multi-objective evolutionary algorithms (MOEAs) have proven their effective performance. In most of the MOEAs based feature selection algorithms, more optimal solutions are obtained around the Pareto front's center because of the deficiency in selection features. With the complicated Pareto fronts, it is difficult to select features using the penalty boundary intersection decomposition approach that can provide stable selection pressures. With the adaptive penalty boundary intersection (APBI) decomposition approach, a novel wrapper based feature selection technique named MOGHBNS3/D is proposed in this paper based on the hybrid of Multi Objective Guided Honey Badger Algorithm and Non-dominated sorting genetic algorithm III. Classification accuracy improvement and removal of redundant features are considered to be the multi-objective optimization functions of the proposed multi-objective feature selection technique. An external archive is employed as a repository for storing the non-dominated solutions in the MOGHBNS3/D. To enhance the selection pressures of the external archive, the penalty values are adjusted adaptively using the APBI mechanism. The Wavelet kernel Extreme Learning Machine is used to classify the selected features. To analyze the performance of the proposed feature selection technique, eighteen benchmark datasets are utilized and results are compared with the four well known multi-objective techniques in terms of accuracy, precision, recall, F1 score, coverage error, hamming loss, ranking loss and training time. The experimental results show that the proposed method can select optimal features with improved classification accuracy, diversity and convergence while the removal of redundancy.

An Intelligent Disaster Prediction in Communication Network Using OAN-ANFIS Technique Based on TEM Feature Selection Approach

Abstract: Due to facility damage and a lack of power, natural disasters disrupt vital services. When the main nodes of a hierarchical network, such as a cellular communication system, are compromised or overloaded, major communication failures frequently happen over a large geographic area. High throughput satellite (HTS) is one of the best options for disaster management as an alternate communication capability since it offers effective communication for a large area regardless of the availability of conventional terrestrial infrastructures. Conventional HTS, on the other hand, uses fixed beam bandwidth and connections for relaying data, making it ineffective when communication demand spikes in a disaster area. Therefore, the work has developed an Intelligent Disaster prediction in a communication network that alters and empowers the decision-making process to avoid a False alarm rate toward transmitting data to the digital world in a better way using the OAN-ANFIS technique based on the TEM Feature selection approach. To limit the likelihood of inaccuracy, the suggested framework first preprocesses the data by transforming unstructured data into arranged manner. The preprocessing technique handles missing values, scaling, and addressing imbalanced data. Following that, the preprocessed data is subjected to Feature selection using the TEM technique, which combines three metaheuristic algorithms, namely Xinit-FSO, LCV-ChoA, and AL-HDC, to pick the optimum feature to train the node recognition model. To obtain a high accuracy rate, the proposed Feature selection technique captures the most known feature to train the model. Finally, OAN-ANFIS predicts the various Disaster limitations of communication. The tentative outcome suggests that the proposed framework has high adaptive predictive compression approaches and achieves higher accuracy than existing strategies.

Deep belief network-based approach for detecting Alzheimer's disease using the multi-omics data

Alzheimer's disease (AD) is the most uncertain form of Dementia in terms of finding out the mechanism. AD does not have a vital genetic factor to relate to. There were no reliable techniques and methods to identify the genetic risk factors associated with AD in the past. Most of the data available were from the brain images. However, recently, there have been drastic advancements in the high-throughput techniques in bioinformatics. It has led to focused researches in discovering the AD causing genetic risk factors. Recent analysis has resulted in considerable prefrontal cortex data with which classification and prediction models can be developed for AD. We have developed a Deep Belief Network-based prediction model using the DNA Methylation and Gene Expression Microarray Data, with High Dimension Low Sample Size (HDLSS) issues. To overcome the HDLSS challenge, we performed a two-layer feature selection considering the biological aspects of the features as well. In the two-layered feature selection approach, first the differentially expressed genes and differentially methylated positions are identified, then both the datasets are combined using Jaccard similarity measure. As the second step, an ensemble-based feature selection approach is implemented to further narrow down the gene selection. The results show that the proposed feature selection technique outperforms the existing commonly used feature selection techniques, such as Support Vector Machine Recursive Feature Elimination (SVM-RFE), and Correlation-based Feature Selection (CBS). Furthermore, the Deep Belief Network-based prediction model performs better than the widely used Machine Learning models. Also, the multi-omics dataset shows promising results compared to the single omics.

Designing a supervised feature selection technique for mixed attribute data analysis

Identifying optimal features is critical for increasing the overall performance of data classification. This paper introduces a supervised feature selection technique for analyzing mixed attribute data. It measures data classification performances of features with a user-defined performance criterion and determines optimal features to boost the overall data analysis performance. A performance evaluation is managed to highlight the usefulness of the technique with existing feature selection techniques such as analysis of variance test, chi-square test, principal component analysis, and mutual information. Visualization is also utilized to understand the differences in classifying instances with different features. From a comparative performance testing and evaluation, we found 5 ∼ 10% performance improvements with the proposed technique. Overall, evaluation results showed the usefulness of our proposed feature selection technique in mixed attribute data analysis.

Hybrid particle swarm optimization with sequential one point flipping algorithm for feature selection

SummaryScientific and technological advancements lead to the continuous generation of a large amount of data. These datasets are analyzed computationally to reveal patterns and trends. While the presence of noisy and irrelevant features or attributes in these datasets is unavoidable, they negatively impact the performance of classification techniques. Feature selection is a method to pre‐process these datasets by selecting the most informative features while concurrently improving the classification accuracy. Recently, several metaheuristic algorithms were employed in this feature selection process, including particle swarm optimization (PSO). PSO is prominent in the field of feature selection due to its simplicity and global search abilities. However, it may get stuck in local optima. To solve this problem, a new update mechanism in PSO is proposed and the PSO is hybridized with a local search method. To evaluate the performance of the proposed algorithm, benchmark datasets from the University of California in Irvine (UCI) repository were utilized, the k‐nearest neighbor as the classifier. Results show that the proposed feature selection technique outperforms other optimization algorithms on these feature selection problems.

Radiomics for Discrimination between Early-Stage Nasopharyngeal Carcinoma and Benign Hyperplasia with Stable Feature Selection on MRI.

Simple SummaryIn this study, we investigated the potential of radiomic models to discriminate nasopharyngeal carcinoma from benign hyperplasia on MRI, which is important to enable screening programs to detect cancer early. We found that whereas radiomics showed promising performance, instability was presented by the feature selection step in the radiomics pipeline, which could undermine its reliability. Therefore, we built a radiomics model using 17 features selected from a pool of 422 features by a proposed ensemble technique that improved the feature selection stability using a combination of bagging and boosting. This radiomic model achieved an area under the curve of 0.85 and 0.80 for discriminating the two abnormalities on the training and testing data, respectively. In addition, the proposed feature selection technique significantly improved stability when compared to well-established techniques.Discriminating early-stage nasopharyngeal carcinoma (NPC) from benign hyperplasia (BH) on MRI is a challenging but important task for the early detection of NPC in screening programs. Radiomics models have the potential to meet this challenge, but instability in the feature selection step may reduce their reliability. Therefore, in this study, we aim to discriminate between early-stage T1 NPC and BH on MRI using radiomics and propose a method to improve the stability of the feature selection step in the radiomics pipeline. A radiomics model was trained using data from 442 patients (221 early-stage T1 NPC and 221 with BH) scanned at 3T and tested on 213 patients (99 early-stage T1 NPC and 114 BH) scanned at 1.5T. To verify the improvement in feature selection stability, we compared our proposed ensemble technique, which uses a combination of bagging and boosting (BB-RENT), with the well-established elastic net. The proposed radiomics model achieved an area under the curve of 0.85 (95% confidence interval (CI): 0.82–0.89) and 0.80 (95% CI: 0.74–0.86) in discriminating NPC and BH in the 3T training and 1.5T testing cohort, respectively, using 17 features selected from a pool of 422 features by the proposed feature selection technique. BB-RENT showed a better feature selection stability compared to the elastic net (Jaccard index = 0.39 ± 0.14 and 0.24 ± 0.06, respectively; p < 0.001).

Feature Selection Using Elephant Herd Principal Component Optimization Technique in Big Data Streams Using Internet of Things

In this digital world, large volume of data is transmitted across various sectors like production industry, healthcare, IoT devices, sales, and other organizations. In this paper, an Elephant Herd Principal Component Optimization (EHPCO) technique is used as a feature selection model to analyse the features of the data that are collected from the IoT devices. The improved perturbation technique is used the privacy preserving of data streams from the IoT devices. The machine learning classifiers are used to analyse its performance based on the proposed feature selection technique. Experimental results show that the proposed HPCO technique outperforms to improve the performance of the machine learning classifiers in terms of TPR, FPR, and accuracy. The DBN classifier obtains more than 86% of accuracy when compared with other algorithms like SVM, MLP, DT, and RF. When the certain features are extracted using the proposed EHPCO technique, the performance of the classifier is improved much in terms of accuracy. The analysis is made for four datasets such as, HPMD, FRDD, EZSD, and SSTD.

A Novel Feature Selection Algorithm using Multi-Objective Improved Honey Badger Algorithm and Strength Pareto Evolutionary Algorithm-II

An important task for classification is feature selection that removes the redundant or irrelevant features from the dataset. Multi-objective feature selection approach is mainly proposed by many researchers. However, these approaches failed to maintain the higher classification accuracy while removing redundancy in the features. In this work, a wrapper based feature selection technique is proposed with a hybrid of Multi Objective Honey Badger Algorithm (MO-HBA) and Strength Pareto Evolutionary Algorithm-II to maintain the balance between classification accuracy and removal of redundancy. Classification accuracy improvement and removal of redundant features are considered as the multi-objective optimization functions of the proposed multi-objective feature selection technique. The Levy flight algorithm is utilized to initialize the population to enhance the ability of the exploration and exploitation of MO-HBA. The regularized Extreme Learning Machine is used to classify the selected features. To evaluate the performance of the proposed feature selection technique, eighteen benchmark datasets are utilized and results are compared with the four well known multi-objective feature selection techniques in terms of accuracy, hamming loss, ranking loss, mean value, standard deviation, length of features, and training time. The proposed approach achieved maximum accuracy of 100% with the maximum value of selected features as 80. The minimum value of hamming loss, ranking loss, mean value and standard deviation value achieved by the proposed approach are 0.0092, 0.0003, 0.018 and 0.001 respectively. The experimental results show that the proposed approach can give improved classification accuracy while the removal of redundancy in large scale datasets.

A novel feature selection technique for enhancing performance of unbalanced text classification problem

Since the last few decades, Text Classification (TC) is being witnessed as an important research direction due to the availability of a huge amount of digital text documents on the web. It would be tedious to manually organize and label them by human experts. Again digging a large number of highly sparse terms and skewed categories present in the documents put a lot of challenges in the correct labeling of the unlabeled documents. Hence feature selection is an essential aspect in text classification, which aims to select more concise and relevant features for further mining of the documents. Additionally, if the text in the document set is associated with multiple categories and the distribution of classes in the dataset is unbalanced, it imposes more challenges on the suitable selection of features for text classification. In this paper, a Modified Chi-Square (ModCHI) based feature selection technique is proposed for enhancing the performance of classification of multi-labeled text documents with unbalanced class distributions. It is an improved version of the Chi-square (Chi) method, which emphasizes selecting maximum features from the classes with a large number of training and testing documents. Unlike Chi, in which the top features are selected with top Chi value, in this proposed technique a score is calculated by considering the total number of relevant documents corresponding to each class with respect to the total number of documents in the original dataset. According to the score the features related to the highly relevant classes as well as high Chi-square value are selected for further processing. The proposed technique is verified with four different classifiers such as Linear SVM (LSVM), Decision tree (DT), Multilevel KNN (MLKNN), Random Forest (RF) over Reuters benchmark multi-labeled, multi-class, unbalanced dataset. The effectiveness of the model is also tested by comparing it with four other traditional feature selection techniques such as term frequency-inverse document frequency (TF-IDF), Chi-square, and Mutual Information (MI). From the experimental outcomes, it is clearly inferred that LSVM with ModCHI produces the highest precision value of 0.94, recall value of 0.80, f-measure of 0.86 and the least hamming loss value of 0.003 with a feature size 1000. The proposed feature selection technique with LSVM produces an improvement of 3.33%, 2.19%, 16.25% in the average precision value, 3.03%, 33.33%, 21.42% in the average recall value, 4%, 34.48%, 14.70% in average F-measure value and 14%, 37.68%, 31.74% in average hamming loss value compared to TF-IDF, Chi and MI techniques respectively. These findings clearly interpret the better performance of the proposed feature selection technique compared to TF_IDF, Chi and MI techniques on the unbalanced Reuters Dataset.

Clothes Retrieval Using M-AlexNet With Mish Function and Feature Selection Using Joint Shannon’s Entropy Pearson’s Correlation Coefficient

The online retrieval of images related to clothes is a crucial task because finding the exact items like the query image from a large amount of data is extremely challenging. However, large variations in clothes images degrade the retrieval accuracy of visual searches. Another problem with retrieval accuracy is high dimensions of feature vectors obtained from pre-trained deep CNN models. This research is an effort to enhance the training and test accuracy of clothes retrieval by using two different means. Initially, features are extracted using the modified AlexNet (M-AlexNet) with little modification in which ReLU activation function is replaced with a self-regularized Mish activation function because of its non-monotonic nature. The M-AlexNet with Mish is trained on CIFAR-10 dataset using SoftMax classifier. Another contribution is to reduce the dimensions of feature vectors obtained from M-AlexNet. The dimensions of features are reduced by selecting the top <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> ranked features and removing some of the dissimilar features using the proposed Joint Shannon’s Entropy Pearson Correlation Coefficient (JSE-PCC) technique to enhance the clothes retrieval performance. To calculate the efficacy of suggested methods, the comparison is performed with other deep CNN models such as baseline AlexNet, VGG-16, VGG-19, and ResNet50 on DeepFashion2, MVC, and the proposed Clothes Image Dataset (CID). Extensive experiments indicate that AlexNet with Mish attains 85.15%, 82.04%, and 83.65% accuracy on DeepFashion2, MVC, and 83.65% on CID datasets respectively. Hence, M-AlexNet and the proposed feature selection technique surpassed the results with a margin of 5.11% on DeepFashion2, 1.95% on MVC, and 3.51% CID datasets.

A HYBRID SENTIMENT ANALYSIS APPROACH USING BLACK WIDOW OPTIMIZATION BASED FEATURE SELECTION

This paper proposes a novel hybrid framework with 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 PSO and GAbased feature selection techniques with reduced computation time of 21 sec. Moreover, our sentiment analysis approach is analysed using performance metrices 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.