Dimensionality Reduction for Feature and Pattern Selection in Classification Problems

Voulgaris, Zacharias; Magoulas, George D.

doi:10.1109/iccgi.2008.34

Cited by 3 publications

(2 citation statements)

References 25 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, descriptors were reduced using the Boruta method (Kursa et al, 2010). We used four different machine learning methods, namely, Support Vector Machine (SVM) (Mitchell, 1997), random forest (Breiman, 2001), Extreme Gradient Boosting (XGBoost) (Chen and Guestrin, 2016), and kappa nearest neighbor (kNN) (Voulgaris and Magoulas, 2008), to build the classification models. All the classification experiments and calculations were conducted using the R.3.0.2 environment (http://www.R-project.org/) and Python (http://www.python.org/) platform.…”

Section: Data Collection and Model Buildingmentioning

confidence: 99%

Combining machine learning and structure-based approaches to develop oncogene PIM kinase inhibitors

Almukadi

Jadkarim²,

Mohammed³

et al. 2023

Front. Chem.

View full text Add to dashboard Cite

Introduction: PIM kinases are targets for therapeutic intervention since they are associated with a number of malignancies by boosting cell survival and proliferation. Over the past years, the rate of new PIM inhibitors discovery has increased significantly, however, new generation of potent molecules with the right pharmacologic profiles were in demand that can probably lead to the development of Pim kinase inhibitors that are effective against human cancer.Method: In the current study, a machine learning and structure based approaches were used to generate novel and effective chemical therapeutics for PIM-1 kinase. Four different machine learning methods, namely, support vector machine, random forest, k-nearest neighbour and XGBoost have been used for the development of models. Total, 54 Descriptors have been selected using the Boruta method.Results: SVM, Random Forest and XGBoost shows better performance as compared to k-NN. An ensemble approach was implemented and, finally, four potential molecules (CHEMBL303779, CHEMBL690270, MHC07198, and CHEMBL748285) were found to be effective for the modulation of PIM-1 activity. Molecular docking and molecular dynamic simulation corroborated the potentiality of the selected molecules. The molecular dynamics (MD) simulation study indicated the stability between protein and ligands.Discussion: Our findings suggest that the selected models are robust and can be potentially useful for facilitating the discovery against PIM kinase.

show abstract

Section: Data Collection and Model Buildingmentioning

confidence: 99%

Combining machine learning and structure-based approaches to develop oncogene PIM kinase inhibitors

Almukadi

Jadkarim²,

Mohammed³

et al. 2023

Front. Chem.

View full text Add to dashboard Cite

show abstract

“…DR can be done via either reduce the number of features, a task called feature selection, or via reduce the number of patterns, called data reduction [19]. Data dimensionality reduction produce a compact low-dimensional encoding of a given high dimensional data set [20].…”

Section: Dimension Reduction (Dr) and Feature Selectionmentioning

confidence: 99%

Human Activity Recognition System to Benefit Healthcare Field by using HOG and Harris Techniques with K-NN Model

Jasim¹,

Harfash²

2018

IJCA

View full text Add to dashboard Cite

Enhancing the performance of hybrid evolutionary algorithms in microarray colon data classification

Nirmalakumari¹,

Rajaguru²

2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Microarray technology aids in monitoring simultaneous gene expressions of human cells for diagnosis and treatment of infectious diseases in a single experiment. The microarray data are of high dimension with a large number of genes and fewer samples. Highly informative features and appropriate classifiers are necessary to increase the accuracy of disease classification. In this paper, a publicly available colon cancer dataset is analyzed for classification.At first, Power Spectral Density (PSD) technique is employed to obtain the reduced gene features and after that, they are classified using various types of classifiers for colon cancer classification. To improve the classification accuracy, the hybridized evolutionary classifiers, namely, Artificial Bee Colony-Firefly (ABC-Firefly), Artificial Bee Colony-Particle Swarm Optimization (ABC-PSO), Particle Swarm Optimization-Firefly (PSO-Firefly) are derived from the conventional evolutionary classifiers, namely, Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO) and Firefly classifiers. The performance of the three hybridized evolutionary algorithms is compared with the conventional classifiers. Additionally, the comparison was also performed on the conventional and hybridized evolutionary algorithms using Expectation Maximization (EM) and cascaded Power Spectral Density-Expectation Maximization (PSD-EM) dimensionality reduction techniques. Although there are many classifiers for colon classification, it is wise to use PSD features with a Hybrid ABC-PSO classifier for enhanced performance. The experimental results reveal that the Hybrid ABC-PSO classifier with PSD features achieves 98.96% for colon cancer samples and 100% accuracy for colon normal samples when compared with the other classifiers reported in the literature.

show abstract

Dimensionality Reduction for Feature and Pattern Selection in Classification Problems

Cited by 3 publications

References 25 publications

Combining machine learning and structure-based approaches to develop oncogene PIM kinase inhibitors

Combining machine learning and structure-based approaches to develop oncogene PIM kinase inhibitors

Human Activity Recognition System to Benefit Healthcare Field by using HOG and Harris Techniques with K-NN Model

Enhancing the performance of hybrid evolutionary algorithms in microarray colon data classification

Contact Info

Product

Resources

About