Ghent University Academic Bibliography


Project: An exploratory study of feature selection techniques for unsupervised learning

project duration
01-OCT-07 – 30-SEP-13
Feature selection is an important aspect of present day data mining research. The need for feature selection is currently increasing as gradually more large and high dimensional datasets are becoming available. In this research, we will focus on how the existing taxonomy of feature selection for classificationcan be transferred to the related problem of clustering (unsupervised learning).