Manuscript Number : IJSRSET1844251
Meta-Heuristic Approaches for the Classification of Medical Datasets
Authors(2) :-Snegaa A, Dr. S. Sivakumari
In the health care systems, the decision support system and the analysis of clinical data requires an interdisciplinary field of data mining, which guides the automated knowledge discovery process to apply the complex task of clinical data analysis. The wide spread of electronic data collection in medical environments leads to an exponential growth of clinical data extracted from heterogeneous patient samples. Rule-based classification is a typical data mining task that is being used in several medical diagnosis and decision support systems. The rules stored in the rule base have an impact on classification efficiency. Rule sets that are extracted with data mining tools and techniques are optimized using heuristic or meta-heuristic approaches inorder to improve the quality of the rule base. In the existing system a meta-heuristic approach called Wind-driven Swarm Optimization (WSO) is used based on the rule based classifier evaluation metric (Jval) in which the rules are extracted from decision trees. The WSO is used to obtain different permutations and combinations of rules whereby the optimal ruleset that satisfies the requirement of the developer is used for predicting the test data. The multimodal optimization is achieved in two stages in health care data mining applications in the proposed architecture. The formed solution of the wind driven optimization is reorganized to model the elimination of the old set solution by using the multimodal optimization. Second, to accelerate convergence, a differential evolution mutation operator is alternatively utilized to build base vectors for ants to construct new solutions. The results are validated for both heart and liver data set and the proposed solution achieves the significance performance interms of sensitivity, specificity, accuracy, precision and miss rate compared to the wind driven optimization.
Snegaa A
Data Mining, Optimization, Swarm Optimization, Rule based Classification
Publication Details
Published in :
Volume 4 | Issue 4 | March-April 2018 Article Preview
Computer Science and Engineering, Faculty of Engineering, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, Tamil Nadu, India
Dr. S. Sivakumari
Computer Science and Engineering, Faculty of Engineering, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, Tamil Nadu, India
Date of Publication :
2018-04-30
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) :
682-695
Manuscript Number :
IJSRSET1844251
Publisher : Technoscience Academy
Journal URL :
https://ijsrset.com/IJSRSET1844251