Improving classification accuracy for non-communicable disease prediction model based on support vector machine

Over recent years,non-communicable disease (ncds) is the high mortality rate in worldwide likely diabetes mellitus,cardiovascular diseases,liver and cancers. ncds prediction model have problems such as redundant data,missing data,imbalance dataset and irrelevant attribute. this paper proposes a novel ncds prediction model to improve accuracy. our model comprisesk-means as clustering technique,weight by svm as feature selection technique and support vector machine as classifier technique. the result shows that k-means + weight svm + svm improved the classification accuracy on most of all ncds dataset (accuracy; auc),likely pima indian dataset (99.52; 0.999),breast cancer diagnosis dataset (98.85; 1.000),breast cancer biopsy dataset (97.71; 0.998),colon cancer (99.41; 1.000),ecg (98.33; 1.000),liver disorder (99.13; 0.998).the significant different performed by k-means + weight by svm + svm. in the time to come,we are expecting to better accuracy rate with another classifier such as neural network. © 2015 penerbit utm press. all rights reserved.