Feature Selection for Microarray Data Classification Using Hybrid Information Gain and a Modified Binary Krill Herd Algorithm

Zhang, Ge; Hou, Jincui; Wang, Jianlin; Yan, Chaokun; Liu, Junwei

doi:10.1007/s12539-020-00372-w

Cited by 63 publications

(36 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…is is true in case of testing the methods with a selected dataset on the Dark Web Forum Portal [5]. e CB consists of hatred messages transmitted via social networking, e-mails, etc.…”

Section: Introductionmentioning

confidence: 99%

Nature-Inspired-Based Approach for Automated Cyberbullying Classification on Multimedia Social Networking

Yuvaraj¹,

Srihari²,

Dhiman

et al. 2021

Mathematical Problems in Engineering

144

View full text Add to dashboard Cite

In the modern era, the cyberbullying (CB) is an intentional and aggressive action of an individual or a group against a victim via electronic media. The consequence of CB is increasing alarmingly, affecting the victim either physically or psychologically. This allows the use of automated detection tools, but research on such automated tools is limited due to poor datasets or elimination of wide features during the CB detection. In this paper, an integrated model is proposed that combines both the feature extraction engine and classification engine from the input raw text datasets from a social media engine. The feature extraction engine extracts the psychological features, user comments, and the context into consideration for CB detection. The classification engine using artificial neural network (ANN) classifies the results, and it is provided with an evaluation system that either rewards or penalizes the classified output. The evaluation is carried out using Deep Reinforcement Learning (DRL) that improves the performance of classification. The simulation is carried out to validate the efficacy of the ANN-DRL model against various metrics that include accuracy, precision, recall, and f-measure. The results of the simulation show that the ANN-DRL has higher classification results than conventional machine learning classifiers.

show abstract

“…is is true in case of testing the methods with a selected dataset on the Dark Web Forum Portal [5]. e CB consists of hatred messages transmitted via social networking, e-mails, etc.…”

Section: Introductionmentioning

confidence: 99%

Nature-Inspired-Based Approach for Automated Cyberbullying Classification on Multimedia Social Networking

Yuvaraj¹,

Srihari²,

Dhiman

et al. 2021

Mathematical Problems in Engineering

144

View full text Add to dashboard Cite

show abstract

“…They modified the algorithm by using a horizontal crossover and position mutation operator and applied to ten different gene microarray cancer datasets. For microarray data classification, Zhang et al [169] improved BKH algorithm named as IG-MBKH by using a hyperbolic tangent function and adaptive transfer function. Furthermore, to initialize the population, information gain feature ranking was used to explore the search space efficiently.…”

Section: B Swarm Intelligence Based Algorithmsmentioning

confidence: 99%

Metaheuristic Algorithms on Feature Selection: A Survey of One Decade of Research (2009-2019)

et al. 2021

View full text Add to dashboard Cite

Feature selection is a critical and prominent task in machine learning. To reduce the dimension of the feature set while maintaining the accuracy of the performance is the main aim of the feature selection problem. Various methods have been developed to classify the datasets. However, metaheuristic algorithms have achieved great attention in solving numerous optimization problem. Therefore, this paper presents an extensive literature review on solving feature selection problem using metaheuristic algorithms which are developed in the ten years (2009-2019). Further, metaheuristic algorithms have been classified into four categories based on their behaviour. Moreover, a categorical list of more than a hundred metaheuristic algorithms is presented. To solve the feature selection problem, only binary variants of metaheuristic algorithms have been reviewed and corresponding to their categories, a detailed description of them explained. The metaheuristic algorithms in solving feature selection problem are given with their binary classification, name of the classifier used, datasets and the evaluation metrics. After reviewing the papers, challenges and issues are also identified in obtaining the best feature subset using different metaheuristic algorithms. Finally, some research gaps are also highlighted for the researchers who want to pursue their research in developing or modifying metaheuristic algorithms for classification. For an application, a case study is presented in which datasets are adopted from the UCI repository and numerous metaheuristic algorithms are employed to obtain the optimal feature subset.

show abstract

“…In addition to filter methods, the wrapper methods utilize classification accuracy as a measurement standard for evaluation and find the optimal feature subset by iteration of meta-heuristic algorithms (Rodrigues et al, 2014). A lot of meta-heuristic algorithms had been well-applied to wrapper methods for feature selection of cancer such as bat algorithm (BA), recursive memetic algorithm (RMA), binary krill herd algorithm (MBKH), and so on (Dashtban et al, 2018;Ghosh et al, 2019;Zhang et al, 2020). Dashtban et al proposed MOBBA-LS which utilized fisher criterion and BA (Dashtban et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

“…The accuracy achieved 100, 97, and 100% on leukemia, prostate, and SRBCT datasets, respectively. Ghosh et al developed a recursive memetic algorithm (RMA) model for feature selection (Ghosh et al, 2019), and Zhang et al proposed a pre-screening method of feature ranking, IG-MBKH, which is based on information gain (IG) and an improved binary krill herd (MBKH) (Zhang et al, 2020). The above methods can obtain favorable classification accuracy on microarray data of cancer.…”

Section: Related Workmentioning

confidence: 99%

“…Related parameters are given as follows: DNN is set as described in the Section 3.3; SVM: degree = 3, gamma = auto, kernel = "rbf, " cache_size = 200; KNN: K = 5. The parameters of methods are set according to the original literature (Dashtban et al, 2018;Hsu and Si, 2018;Wang et al, 2020;Zhang et al, 2020). The specific settings are shown in Table 2.…”

Section: Parameter Settingmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Biomarker Identification Approach for Gastric Cancer Using Gene Expression and DNA Methylation Dataset

et al. 2021

Self Cite

View full text Add to dashboard Cite

As one type of complex disease, gastric cancer has high mortality rate, and there are few effective treatments for patients in advanced stage. With the development of biological technology, a large amount of multiple-omics data of gastric cancer are generated, which enables computational method to discover potential biomarkers of gastric cancer. That will be very important to detect gastric cancer at earlier stages and thus assist in providing timely treatment. However, most of biological data have the characteristics of high dimension and low sample size. It is hard to process directly without feature selection. Besides, only using some omic data, such as gene expression data, provides limited evidence to investigate gastric cancer associated biomarkers. In this research, gene expression data and DNA methylation data are integrated to analyze gastric cancer, and a feature selection approach is proposed to identify the possible biomarkers of gastric cancer. After the original data are pre-processed, the mutual information (MI) is applied to select some top genes. Then, fold change (FC) and T-test are adopted to identify differentially expressed genes (DEG). In particular, false discover rate (FDR) is introduced to revise p_value to further screen genes. For chosen genes, a deep neural network (DNN) model is utilized as the classifier to measure the quality of classification. The experimental results show that the approach can achieve superior performance in terms of accuracy and other metrics. Biological analysis for chosen genes further validates the effectiveness of the approach.

show abstract

Feature Selection for Microarray Data Classification Using Hybrid Information Gain and a Modified Binary Krill Herd Algorithm

Cited by 63 publications

References 39 publications

Nature-Inspired-Based Approach for Automated Cyberbullying Classification on Multimedia Social Networking

Nature-Inspired-Based Approach for Automated Cyberbullying Classification on Multimedia Social Networking

Metaheuristic Algorithms on Feature Selection: A Survey of One Decade of Research (2009-2019)

A Novel Biomarker Identification Approach for Gastric Cancer Using Gene Expression and DNA Methylation Dataset

Contact Info

Product

Resources

About