Ensemble SVM for imbalanced data and missing values in postoperative risk management

Author

Zieba, Maciej ; Swiatek, Jerzy

Author_Institution

Dept. of Comput. Sci. & Manage., Wroclaw Univ. of Technol., Wroclaw, Poland

fYear

2013

fDate

9-12 Oct. 2013

Firstpage

95

Lastpage

99

Abstract

In this work, we propose the ensemble SVM that solves the problem of missing values of attributes and the imbalanced data phenomenon in the domain of postoperative risk management. Contrary to the other approaches the our solution effectively deals with the problems of high percentage of unknown values of the features. The problem of imbalanced data is solved by applying the cost-sensitive SVM as a base classifier of an ensemble, The quality of the proposed classifier is examined on a real-life dataset.

Keywords

learning (artificial intelligence); medical information systems; optimisation; pattern classification; risk management; support vector machines; attribute missing value problem; base classifier; cost-sensitive ensemble SVM; imbalanced data phenomenon; postoperative risk management domain; real-life dataset; unknown feature values; Indexes; Lungs; Risk management; Support vector machines; Surgery; Training; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

e-Health Networking, Applications & Services (Healthcom), 2013 IEEE 15th International Conference on

Conference_Location

Lisbon

Print_ISBN

978-1-4673-5800-2

Type

conf

DOI

10.1109/HealthCom.2013.6720646

Filename

6720646