Title: Department of Computer Science Seminar
Date: Thursday, Feb. 24, 2000
Time: 4:00 pm to 5:00 pm
Venue: Room N101, CSIT Building [108]
Speaker: Dr Choh Man Teng (University of New South Wales)
Description: "Correcting Noisy Data"


                        Abstract

Inductive learning aims at constructing a generalized description 
of a given set of data, so that future similar instances can be 
classified correctly. The performance on this task depends crucially
on the quality of the training data. We investigate an approach 
to handling noise in the data by identifying possible noisy attributes 
and/or class in each instance, and replacing such values with more
 appropriate ones.  We make use of the interdependence among elements
 in the data set to predict the values of the attributes.  
Preliminary experimentation suggested that this is a viable approach 
to noise reduction and correction. We will also in particular discuss 
the design of effective measures for evaluating data cleaning mechanisms.
 

 
URL: http://cs.anu.edu.au/lib/seminars/seminars00/dept20000224