Back to Search Start Over

Design of metaheuristic rough set-based feature selection and rule-based medical data classification model on MapReduce framework

Authors :
Bhukya Hanumanthu
Manchala Sadanandam
Source :
Journal of Intelligent Systems, Vol 31, Iss 1, Pp 1002-1013 (2022)
Publication Year :
2022
Publisher :
De Gruyter, 2022.

Abstract

Recently, big data analytics have gained significant attention in healthcare industry due to generation of massive quantities of data in various forms such as electronic health records, sensors, medical imaging, and pharmaceutical details. However, the data gathered from various sources are intrinsically uncertain owing to noise, incompleteness, and inconsistency. The analysis of such huge data necessitates advanced analytical techniques using machine learning and computational intelligence for effective decision making. To handle data uncertainty in healthcare sector, this article presents a novel metaheuristic rough set-based feature selection with rule-based medical data classification (MRSFS-RMDC) technique on MapReduce framework. The proposed MRSFS-RMDC technique designs a butterfly optimization algorithm for minimal rough set selection. In addition, Hadoop MapReduce is applied to process massive quantity of data. Moreover, a rule-based classification approach named Repeated Incremental Pruning for Error Reduction (RIPPER) is used with the inclusion of a set of conditional rules. The RIPPER will scale in a linear way with the number of training records utilized and is suitable to build models with data uncertainty. The proposed MRSFS-RMDC technique is validated using benchmark dataset and the results are inspected under varying aspects. The experimental results highlighted the supremacy of the MRSFS-RMDC technique over the recent state of art methods in terms of different performance measures. The proposed methodology has achieved a higher F-score of 96.49%.

Details

Language :
English
ISSN :
2191026X
Volume :
31
Issue :
1
Database :
Directory of Open Access Journals
Journal :
Journal of Intelligent Systems
Publication Type :
Academic Journal
Accession number :
edsdoj.424692ea3ad048cc8e95265cfa30d03c
Document Type :
article
Full Text :
https://doi.org/10.1515/jisys-2022-0066