An Improved K-modes Clustering Algorithm Based on Intra-cluster and Inter-cluster Dissimilarity Measure
Hongfang Zhou, Yihui Zhang, Yibin Liu
Available Online July 2016.
- https://doi.org/10.2991/iccia-17.2017.67How to use a DOI?
- Clustering, categorical data, dissimilarity measure, k-modes algorithm.
- Categorical data clustering has attracted much attentions recently because most practical data contains categorical attributes. The k-modes algorithm, as the extension of the k-means algorithm, is one of the most widely used clustering algorithms for categorical data. In this paper, we firstly analyzed the limitations of two existing dissimilarity measures. Based on this, we proposed a novel dissimilarity measure--IID. IID considers the relationship between the object and all clusters as well as that within clusters. Finally the experiments are made on six benchmark data sets from UCI. And the corresponding results show that IID achieves better performance than two existing ones used in k-modes and KBGRD algorithms.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Hongfang Zhou AU - Yihui Zhang AU - Yibin Liu PY - 2016/07 DA - 2016/07 TI - An Improved K-modes Clustering Algorithm Based on Intra-cluster and Inter-cluster Dissimilarity Measure BT - Proceedings of the 2nd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2017) PB - Atlantis Press SP - 398 EP - 406 SN - 2352-538X UR - https://doi.org/10.2991/iccia-17.2017.67 DO - https://doi.org/10.2991/iccia-17.2017.67 ID - Zhou2016/07 ER -