Research Repository

AdaBoost Algorithm with Random Forests for Predicting Breast Cancer Survivability

Thongkam, Jaree and Xu, Guandong and Zhang, Yanchun (2008) AdaBoost Algorithm with Random Forests for Predicting Breast Cancer Survivability. In: IEEE International Joint Conference on Neural Networks, 2008 : IJCNN 2008 (IEEE World Congress on Computational Intelligence) : 1-8 June, 2008. IEEE, Piscataway, New Jersey, pp. 3062-3069.

Full text for this resource is not available from the Research Repository.

Abstract

In this paper we propose a combination of the AdaBoost and random forests algorithms for constructing a breast cancer survivability prediction model. We use random forests as a weak learner of AdaBoost for selecting the high weight instances during the boosting process to improve accuracy, stability and to reduce overfitting problems. The capability of this hybrid method is evaluated using basic performance measurements (e.g., accuracy, sensitivity, and specificity), Receiver Operating Characteristic (ROC) curve and Area Under the receiver operating characteristic Curve (AUC). Experimental results indicate that the proposed method outperforms a single classifier and other combined classifiers for the breast cancer survivability prediction. --Conference held in Hong Kong

Item Type: Book Section
ISBN: 9781424418206 (print) 9781424418213 (online) 9781424418213
Uncontrolled Keywords: ResPubID14757, educational technologies, artificial intelligence, cancer, medical computing, sensitivity analysis, stability, prediction, predictive models, overfitting problems, data mining, decision trees, diseases, mathematics, medical diagnostic imaging, mathematical models, signal processing algorithms, support vector machines
Subjects: FOR Classification > 1117 Public Health and Health Services
SEO Classification > 8903 Information Services
Faculty/School/Research Centre/Department > School of Engineering and Science
Depositing User: VUIR
Date Deposited: 18 Nov 2013 22:47
Last Modified: 15 Dec 2014 01:41
URI: http://vuir.vu.edu.au/id/eprint/5159
DOI: 10.1109/IJCNN.2008.4634231
ePrint Statistics: View download statistics for this item
Citations in Scopus: 5 - View on Scopus

Repository staff only

View Item View Item

Search Google Scholar