Feature Selection using K-Means Genetic Clustering To Predict Rheumatoid Arthritis Disease
B.Jayanthy1, C.Senthamarai2
1B.Jayanthy, Research Scholar, Department of Computer Application, Government Arts College, Salem-636007, Tamil Nadu.
2Dr.C.Senthamarai , Assistant Professor, Department of Computer Application, Government Arts College, Salem-636007, Tamil Nadu
Manuscript received on 02 August 2019. | Revised Manuscript received on 07 August 2019. | Manuscript published on 30 September 2019. | PP: 7020-7023 | Volume-8 Issue-3 September 2019 | Retrieval Number: C6043098319/2019©BEIESP | DOI: 10.35940/ijrte.C6043.098319
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In our Society, Aging society plays serious problems in health and medical care. When compared to other diseases in the real life Rheumatoid Arthritis disease is a common disease, Rheumatoid Arthritis is a disease that causes pain in musculoskeletal system that affect the quality of the people. Rheumatoid Arthritis is onset at middle age, but can affect children and young adults. If the disease is not monitored and treated as early as possible, it can cause serious joint deformities. Cluster analysis is an unsupervised learning technique in data mining for identifying or exploring out the structure of data without known about class label. Many clustering algorithms were proposed to analyze high volume of data, but many of them not evaluate cluster’s quality because of inconvenient features presented in the dataset. Feature selection is a prime task in data analysis in case of high dimensional dataset. Optimal subsets of features are enough to cluster the data. In this study, Rheumatoid Arthritis clinical data were analyzed to predict the patient affected with Rheumatoid Arthritis disease. In this study, K-Means clustering algorithm was used to predict the patient affected with Rheumatoid Arthritis Disease. Genetic algorithm is used to filter the feature and at the end of the process it finds optimal clusters for k-Means clustering algorithm. Based on the initial centroid , K-Means algorithm may have the chance of producing empty cluster. K-means does not effectively handle the outliers or noisy data in the dataset. K-means algorithm when combined with Genetic Algorithm shows high performance quality of clustering and fast evolution process when compared with K-Means alone. In this paper, to diagnosis Rheumatoid Arthritis disease we use machine learning algorithm FSKG. A predictive FSKG model is explored that diagnoses rheumatoid arthritis. After completing data analysis and pre-processing operations, Genetic Algorithm and K-Means Clustering Algorithm are integrated to choose correct features among all the features. Experimental Results from this study imply improved accuracy when compared to k-means algorithm for rheumatoid disease prediction.
Keywords: Clustering , Data mining, Feature selection , Genetic algorithm, K-Means, Machine Learning.
Scope of the Article: Machine Learning.