• Basheer Al-Maqaleh
• Waleed Ahmed Omar

Automated discovery of classification rule is considered as one of the most fundamental and important approaches in order to obtain valuable knowledge from medical datasets. Building a comprehensible, accurate and interesting classifier for diseases diagnosis and prediction in medical field is one of the most significant challenges in knowledge discovery and data mining domain. A main concern of the population-based Genetic Algorithms (GA) approaches is how to balance exploration and exploitation during the process of evolutionary searching new solutions to avoid premature convergence to a sub-optimal solution. Also, these approaches biased toward majority class instances, and they misclassifying the minority classes, which affect their predictive accuracy. Distributed Genetic Algorithm (DGA) is considered as the most important classification approach to address the problem of simple GA converging to local optimal solutions. In this paper, a Distributed-Population multiobjective Genetic Algorithm (DPMoGA) approach for discovering interesting classification rules discover from medical datasets is proposed. The DPMoGA approach, has a flexible chromosome representation, an effective multiobjective fitness function, appropriate genetic operators for suggested representation, a new dynamic island model based on distributed population with an efficient migration process. The DPMoGA approach is validated on several medical datasets from UCI repository, and the experimental results demonstrate the effectiveness of the proposed approach for interesting classification rules mining with significantly higher predictive accuracy rate.

"A Distributed-Population Multiobjective Genetic Algorithm for Discovering Interesting Classification Rules from Medical Datasets", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.336-346, June 2019, Available :http://www.jetir.org/papers/JETIR1906I80.pdf

"A Distributed-Population Multiobjective Genetic Algorithm for Discovering Interesting Classification Rules from Medical Datasets", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp336-346, June 2019, Available at : http://www.jetir.org/papers/JETIR1906I80.pdf