@inproceedings{d2d978a289fa486ab798d2f3b9beeda2,
title = "A comparison of categorical attribute data clustering methods",
abstract = "Clustering data in Euclidean space has a long tradition and there has been considerable attention on analyzing several different cost functions. Unfortunately these result rarely generalize to clustering of categorical attribute data. Instead, a simple heuristic k-modes is the most commonly used method despite its modest performance. In this study, we model clusters by their empirical distributions and use expected entropy as the objective function. A novel clustering algorithm is designed based on local search for this objective function and compared against six existing algorithms on well known data sets. The proposed method provides better clustering quality than the other iterative methods at the cost of higher time complexity.",
author = "Ville Hautam{\"a}ki and Antti P{\"o}ll{\"a}nen and Tomi Kinnunen and Lee, {Kong Aik} and Haizhou Li and Pasi Fr{\"a}nti",
year = "2014",
doi = "10.1007/978-3-662-44415-3_6",
language = "English",
isbn = "9783662444146",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "53--62",
booktitle = "Structural, Syntactic, and Statistical Pattern Recognition - Joint IAPR International Workshop, S+SSPR 2014, Proceedings",
address = "Germany",
note = "Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition, S+SSPR 2014 ; Conference date: 20-08-2014 Through 22-08-2014",
}