Feature selection is crucial for improving the efficiency and effectiveness of machine learning models by identifying and choosing the most pertinent subset of features from the original dataset. This review article comprehensively surveys a diverse range of feature selection techniques in the context of Support Vector Machine (SVM) classification model in machine learning. This research work delves into several prominent techniques, including Mutual Information, Chi-Square, Sequential Feature Selection (SFS), Recursive Feature Elimination (RFE), LASSO, and Random Forest. The study reveals that RFE (Recursive Feature Elimination) emerges as the highly effective feature selection technique, demonstrating superior performance metrics compared to the other methods considered. Additionally, the study proposes the integration of hybrid algorithms to further enhance the performance of SVM classification models. Furthermore, this review extends its scope to encompass an evaluation of various kernel methods within the SVM classification paradigm, offering a comprehensive perspective on their efficacy and performance.

Feature Selection Technique, Chi-Square, RFE (Recursive Feature Elimination), SVM (Support Vector Machine), Kernel methods

[1] Hamed Mazreati, Reza Radfar, Mohammad-Reza Sohrabi, Babak Sabet Divshali, Mohammad Ali Afshar Kazemi, “Comparing the Performance of Feature Selection Methods for Predicting Gastric Cancer”, International Journal of Cancer Management, Vol.16, Issue 1, 2023.
[2] Mei-Ling Huang, Yung-Hsiang Hung, W. M. Lee, R. K. Li and Bo-Ru Jiang, “SVM-RFE Based Feature Selection and Taguchi Parameters Optimization for Multiclass SVM Classifier”, The Scientific World Journal, Hindawi, 2014.
[3] Prasannavenkatesan Theerthagiri & Sahana Devarayapattana Siddalingaiah, “Recursive Gaussian support vector machine based feature selection algorithm for liver disease classification”, Multimedia Tools and Applications, Springer Link, 2023.
[4] Javier Alcaraz, Martine Labbé and Mercedes Landete, “Support Vector Machine with feature selection: A multiobjective approach”, Elsevier, Vol.204, 2022.
[5] J. Vijayashree & H. Parveen Sultana, “A Machine Learning Framework for Feature Selection in Heart Disease Classification Using Improved Particle Swarm Optimization with Support Vector Machine Classifier”, Journal of Russian Law, 2019.
[6] Chandra Babu Gokulnath, S.P. Shantharajah, “An optimized feature selection based on genetic approach and support vector machine for heart disease”, Springer link, Vol.22, pp.14777-14787, 2018.
[7] M. Sahaya Sheelal, C. A. Arun, “Hybrid PSO–SVM algorithm for Covid-19 screening and quantification”, International Journal of Information Technology”, Springer Link, Vol.14, pp.2049-2056, 2022.
[8] Shaoze Cui, Dujuan Wang, Yanzhang Wang, Pay-Wen Yu, Yaochu Jin, “An improved support vector machine-based diabetic readmission prediction”, Elsevier, Vol.166, pp.123-135, 2018.
[9] Vamsidhar Enireddy, Mathe John Kenny Kumar, Babitha Donepudi and C Karthikeyan, “Detection of COVID-19 using Hybrid ResNet and SVM”, IOP Science, 2020.
[10] Warda M. Shaban, Asmaa hamdy Rabie, Ahmed Ibrahim Saleh, Mohy Eldin A. Abo-Elsoud, “A new COVID-19 Patients Detection Strategy (CPDS) based on hybrid feature selection and enhanced KNN classifier”, Knowledge Based Systems, Research Gate, 2020.
[11] Behnood Gholami, saiah Norton, Allen R. Tannenbaum, and Nathalie Y. R. Agar, “Recursive Feature Elimination for Brain Tumor Classification using Desorption Electrospray Ionization Mass Spectrometry Imaging”, PubMed, National Library of Medicine, 2012.
[12] Viktor Wottschela, Declan T. Chard , Christian Enzingerd , Massimo Filippie, “SVM recursive feature elimination analyses of structural brain MRI predicts near-term relapses in patients with clinically isolated syndromes suggestive of multiple sclerosis”, Multicenter Study, PubMed, 2019.
[13] Irfan Ullah Khattak, Aihab Khan, Farhan Hassan Khan, Abdullah Gani, Muhammad Shiraz, “A Novel Feature Selection Method for Classification of Medical Data using Filters, Wrappers and Embedded Approaches”, Hindawi, Vol.2022, 2022.
[14] Hector Sanz , Clarissa Valim, Esteban Vegas , Josep M. Oller and Ferran Reverter, “SVM-RFE: selection and visualization of the most relevant features through non-linear kernels”, BMC Bioinformatics, Nov. 2018.
[15] Huda M. Alshanbari, Tahir Mehmood, Waqas Sami, Wael Alturaiki, Mauawia A. Hamza and Bandar Alosaimi, “Prediction and Classification of COVID-19 Admissions to Intensive Care Units (ICU) Using Weighted Radial Kernel SVM Coupled with Recursive Feature Elimination (RFE)”, PubMed, National Library of Medicine, 2022.
[16] Arti Patle; Deepak Singh Chouhan, “SVM kernel functions for classification”, 2013 International Conference on Advances in Technology and Engineering (ICATE), IEEE, 2013.
[17] Asa Ben-Hur, Cheng Soon Ong, Sören Sonnenburg, Bernhard Schölkopf, Gunnar Rätsch, “Support Vector Machines and Kernels for Computational Biology”, PubMed, National Library of Medicine, 2008,
[18] Wenbo Liu, Shengnan Liang, Xiwen Qin, “Weighted p-norm distance t kernel SVM classification algorithm based on improved polarization”, Scientific Reports, 2022.
[19] Jiawei Yanga, Zeping Wua,KePenga, Patrick N. Okolob,c, Weihua Zhanga,Hailong Zhaoaand Jingbo Sun, “Parameter selection of Gaussian kernel SVM based on local density of training set”, Inverse Problem in Science and Engineering, Taylor & Francis”, Vol.29, No.4, pp.536-548, 2021.
[20] C. Dharmadevi and S. Thaddeus, “Prediction of COVID-19 Infections using Classification Algorithms in Machine Learning”, Indian Journal of Natural Sciences, Vol.24, pp.61005-61011, 2023.