Hybrid Feature Selection and Ensemble Learning Methods for Gene Selection and Cancer Classification

Qasem, Sultan Noman; Saeed, Faisal

doi:10.14569/ijacsa.2021.0120225

Cited by 6 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [35], a number of combinations of wrapping approaches (using NB and KNN with rank search, greedy stepwise, and best first) and ranking methods (using information gain [IG] with threshold of 1% and 5%) were employed for choosing the most crucial genes for microarray datasets. Brain cancer, CNS, breast cancer, and lung cancer datasets were among these datasets.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Hybrid Runge Kutta Optimizer with Support Vector Machine on Gene Expression Data for Cancer Classification

2023

View full text Add to dashboard Cite

It is crucial to accurately categorize cancers using microarray data. Researchers have employed a variety of computational intelligence approaches to analyze gene expression data. It is believed that the most difficult part of the problem of cancer diagnosis is determining which genes are informative. Therefore, selecting genes to study as a starting point for cancer classification is common practice. We offer a novel approach that combines the Runge Kutta optimizer (RUN) with a support vector machine (SVM) as the classifier to select the significant genes in the detection of cancer tissues. As a means of dealing with the high dimensionality that characterizes microarray datasets, the preprocessing stage of the ReliefF method is implemented. The proposed RUN–SVM approach is tested on binary-class microarray datasets (Breast2 and Prostate) and multi-class microarray datasets in order to assess its efficacy (i.e., Brain Tumor1, Brain Tumor2, Breast3, and Lung Cancer). Based on the experimental results obtained from analyzing six different cancer gene expression datasets, the proposed RUN–SVM approach was found to statistically beat the other competing algorithms due to its innovative search technique.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Novel Hybrid Runge Kutta Optimizer with Support Vector Machine on Gene Expression Data for Cancer Classification

2023

View full text Add to dashboard Cite

show abstract

“…It is considered to be one of the most critical and challenging problems in machine learning. It is widely used to solve the problem of dimension reduction of datasets in different fields, such as the best gene screening in biomedicine [ 7 ], the hot topic recognition in text mining [ 8 ], and the best visual content pixel and color selection in image analysis [ 9 ]. These algorithms are mainly divided into the filter and wrapper method.…”

Section: Preliminaries and Related Workmentioning

confidence: 99%

An Efficient Hybrid Feature Selection Method Using the Artificial Immune Algorithm for High-Dimensional Data

Zhu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Feature selection provides the optimal subset of features for data mining models. However, current feature selection methods for high-dimensional data also require a better balance between feature subset quality and computational cost. In this paper, an efficient hybrid feature selection method (HFIA) based on artificial immune algorithm optimization is proposed to solve the feature selection problem of high-dimensional data. The algorithm combines filter algorithms and improves clone selection algorithms to explore the feature space of high-dimensional data. According to the target requirements of feature selection, combined with biological research results, this method introduces the lethal mutation mechanism and the Cauchy operator to improve the search performance of the algorithm. Moreover, the adaptive adjustment factor is introduced in the mutation and update phases of the algorithm. The effective combination of these mechanisms enables the algorithm to obtain a better search ability and lower computational costs. Experimental comparisons with 19 state-of-the-art feature selection methods are conducted on 25 high-dimensional benchmark datasets. The results show that the feature reduction rate for all datasets is above 99%, and the performance improvement for the classifier is between 5% and 48.33%. Compared with the five classical filtering feature selection methods, the computational cost of HFIA is lower than the two of them, and it is far better than these five algorithms in terms of the feature reduction rate and classification accuracy improvement. Compared with the 14 hybrid feature selection methods reported in the latest literature, the average winning rates in terms of classification accuracy, feature reduction rate, and computational cost are 85.83%, 88.33%, and 96.67%, respectively.

show abstract

“…Researchers have investigated how data mining algorithms are utilized in healthcare and biomedicine, offering recommendations on how to employ these algorithms and the potential applications of data mining in the healthcare sector [24]. Additionally, a work published in [25] shows the use of several data mining techniques for the identification of the most significant genes and gene sequences in a collection of gene expression microarrays. Qasem et al discussed how to cope with learning models for forecasting patient health and the difficulty of utilizing predictive data mining in clinical medicine [25].…”

Section: Related Workmentioning

confidence: 99%

“…Additionally, a work published in [25] shows the use of several data mining techniques for the identification of the most significant genes and gene sequences in a collection of gene expression microarrays. Qasem et al discussed how to cope with learning models for forecasting patient health and the difficulty of utilizing predictive data mining in clinical medicine [25]. These models can be quite helpful in assisting doctors with activities related to diagnosis, treatment, or monitoring.…”

Section: Related Workmentioning

confidence: 99%

Data Mining for Autism Spectrum Disorder detection among Adults

Al-Qazzaz

Jaffer

Abdulazez

et al. 2022

NJES

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is one of the most common children's neurodevelopmental disorders (NDD) with an estimated global incidence of 1% to 2%. There are two aims for this research, first, to propose a data mining architecture that combines behavioural and clinical characteristics with demographic data. Second, to provide a quick, acceptable and easy way to support the ASD diagnosis. this can be performed by conducting a comparison study to determine the efficacy of four possible classifiers: logistic regression (LR), sequential minimum optimization (SMO), naïve Bayes, and instance-based technique based on k-neighbors (IBK). These classifiers have been performed with Waikato Environment for Knowledge Analysis (WEKA) tools to distinguish autistic adults from healthy, normal subjects. The results showed that, with 99.71%, SMO classification accuracy was 99.71, which exceeded the accuracy of other classifiers. The proposed architecture allows for early detection of ASD, distinguishing between ASD and healthy control subjects. This study could help doctors and clinicians by giving them a better idea of what the future holds for people with autism spectrum disorder (ASD) and by improving therapy programs, allowing people with ASD to live a long and happy life.

show abstract

Hybrid Feature Selection and Ensemble Learning Methods for Gene Selection and Cancer Classification

Cited by 6 publications

References 34 publications

A Novel Hybrid Runge Kutta Optimizer with Support Vector Machine on Gene Expression Data for Cancer Classification

A Novel Hybrid Runge Kutta Optimizer with Support Vector Machine on Gene Expression Data for Cancer Classification

An Efficient Hybrid Feature Selection Method Using the Artificial Immune Algorithm for High-Dimensional Data

Data Mining for Autism Spectrum Disorder detection among Adults

Contact Info

Product

Resources

About