Using consensus ensembles to identify suspect data

Clark, David

Login to OUR Archive using your University of Otago credentials. We have changed how you log into OUR Archive so you will not need to create another account in order to deposit your research outputs. If you have bookmarked the old login page, please update your bookmarks. Note: This change will not affect Thesis Deposit, because an account is not required to submit your e-thesis.

Using consensus ensembles to identify suspect data

Clark, David

Cite this item: Clark, D. (2000). Using consensus ensembles to identify suspect data (Information Science Discussion Papers Series No. 2000/17). University of Otago. Retrieved from http://hdl.handle.net/10523/967

Permanent link to OUR Archive version: http://hdl.handle.net/10523/967

Date: 2000-11

Publisher: University of Otago

Pages: 11

Series: Information Science Discussion Papers Series

Series number: 2000/17

Research Type: Discussion Paper

Abstract:

In a consensus ensemble all members must agree before they classify a data point. But even when they all agree some data is still misclassified. In this paper we look closely at consistently misclassified data to investigate whether some of it may be outliers or may have been mislabeled.

Show full item record