Article: Embedded binary PSO integrating classical methods for multilevel improved feature selection in liver and kidney disease diagnosis Journal: International Journal of Biomedical Engineering and Technology (IJBET) 2019 Vol.31 No.2 pp.105 - 136 Abstract: Feature selection is an important pre-processing technique in the field of data mining. This process removes irrelevant data thereby reduces the number of features. This paper presents a new algorithm called embedded binary particle swarm optimisation (BPSO) to improve the performance of BPSO for feature selection. Embedded BPSO incorporates classical methods to select elite feature subset. The population is refined or extended at regular intervals using the best features from sequential forward selection and sequential backward selection methods. In this study, probabilistic neural network and support vector machine with threefold cross-validation are used to evaluate the particles. The embedded algorithm is verified in the feature selection module of the liver and kidney cancer diagnostic system. The elite features extracted from wrapper based embedded algorithm are used to characterise diseases using the classifier. Findings show that the proposed system is proficient in selecting the best features with minimum error rate. Inderscience Publishers - linking academia, business and industry through research

Title: Embedded binary PSO integrating classical methods for multilevel improved feature selection in liver and kidney disease diagnosis

Authors: Gunasundari Selvaraj; Janakiraman Subbiah; Meenambal Selvaraj

Addresses: Department of Computer Science and Engineering, Velammal Engineering College, Chennai 600066, Tamil Nadu, India ' Department of Banking Technology, Pondicherry University, Puducherry 605014, India ' Madurai Medical College, Madurai, Tamil Nadu, India

Abstract: Feature selection is an important pre-processing technique in the field of data mining. This process removes irrelevant data thereby reduces the number of features. This paper presents a new algorithm called embedded binary particle swarm optimisation (BPSO) to improve the performance of BPSO for feature selection. Embedded BPSO incorporates classical methods to select elite feature subset. The population is refined or extended at regular intervals using the best features from sequential forward selection and sequential backward selection methods. In this study, probabilistic neural network and support vector machine with threefold cross-validation are used to evaluate the particles. The embedded algorithm is verified in the feature selection module of the liver and kidney cancer diagnostic system. The elite features extracted from wrapper based embedded algorithm are used to characterise diseases using the classifier. Findings show that the proposed system is proficient in selecting the best features with minimum error rate.

Keywords: binary particle swarm optimisation; feature selection; sequential forward selection; sequential backward selection; liver cancer; kidney cancer; computer-aided diagnostic system; medical imaging; benign; malignant.

DOI: 10.1504/IJBET.2019.102119

International Journal of Biomedical Engineering and Technology, 2019 Vol.31 No.2, pp.105 - 136

Received: 24 Oct 2016
Accepted: 01 Mar 2017
Published online: 09 Sep 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Embedded binary PSO integrating classical methods for multilevel improved feature selection in liver and kidney disease diagnosis

Keep up-to-date