147
Copyright © 2010, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Chapter 7
Classifcation with
Incomplete Data
Pedro J. García-Laencina
Universidad Politécnica de Cartagena, Spain
Juan Morales-Sánchez
Universidad Politécnica de Cartagena, Spain
Rafael Verdú-Monedero
Universidad Politécnica de Cartagena, Spain
Jorge Larrey-Ruiz
Universidad Politécnica de Cartagena, Spain
José-Luis Sancho-Gómez
Universidad Politécnica de Cartagena, Spain
Aníbal R. Figueiras-Vidal
Universidad Carlos III de Madrid, Spain
ABStrAct
Many real-word classifcation scenarios suffer a common drawback: missing, or incomplete, data.
The ability of missing data handling has become a fundamental requirement for pattern classifcation
because the absence of certain values for relevant data attributes can seriously affect the accuracy of
classifcation results. This chapter focuses on incomplete pattern classifcation. The research works on
this topic currently grows wider and it is well known how useful and effcient are most of the solutions
based on machine learning. This chapter analyzes the most popular and proper missing data techniques
based on machine learning for solving pattern classifcation tasks, trying to highlight their advantages
and disadvantages.
DOI: 10.4018/978-1-60566-766-9.ch007