eduzhai > Applied Sciences > Engineering >

Coronary Heart Disease Diagnosis Based on Improved Ensemble Learning

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Accurate diagnosis is required before performing proper treatments forcoronary heart disease. Machine learning based approaches have been proposed bymany researchers to improve the accuracy of coronary heart disease diagnosis.Ensemble learning and cascade generalization are among the methods which can beused to improve the generalization ability of learning algorithm. The objectiveof this study is to develop heart disease diagnosis method based on ensemblelearning and cascade generalization. Cascade generalization method with loosecoupling strategy is proposed in this study. C4. 5 and RIPPER algorithm wereused as meta-level algorithm and Naive Bayes was used as baselevel algorithm.Bagging and Random Subspace were evaluated for constructing the ensemble. Thehybrid cascade ensemble methods are compared with the learning algorithms innon-ensemble mode and non-cascade mode. The methods are also compared withRotation Forest. Based on the evaluation result, the hybrid cascade ensemblemethod demonstrated the best result for the given heart disease diagnosis case.Accuracy and diversity evaluation was performed to analyze the impact of thecascade strategy. Based on the result, the accuracy of the classifiers in theensemble is increased but the diversity is decreased.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×