@inproceedings{ecc3300c4493454da28b1ba54aaf0b38,
title = "Ensemble clustering of high dimensional data with fastmap projection",
abstract = "In this paper, we propose an ensemble clustering method for high dimensional data which uses FastMap projection to generate subspace component data sets. In comparison with popular random sampling and random projection, FastMap projection preserves the clustering structure of the original data in the component data sets so that the performance of ensemble clustering is improved significantly. We present two methods to measure preservation of clustering structure of generated component data sets. The comparison results have shown that FastMap preserved the clustering structure better than random sampling and random projection. Experiments on three real data sets were conducted with three data generation methods and three consensus functions. The results have shown that the ensemble clustering with FastMap projection outperformed the ensemble clusterings with random sampling and random projection.",
keywords = "Consensus function, Ensemble clustering, FastMap, Random projection, Random sampling",
author = "Imran Khan and Huang, {Joshua Zhexue} and Tung, {Nguyen Thanh} and Graham Williams",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2014.; International Workshops on Data Mining and Decision Analytics for Public Health, Biologically Inspired Data Mining Techniques, Mobile Data Management, Mining, and Computing on Social Networks, Big Data Science and Engineering on E-Commerce, Cloud Service Discovery, MSMV-MBI, Scalable Dats Analytics, Data Mining and Decision Analytics for Public Health and Wellness, Algorithms for Large-Scale Information Processing in Knowledge Discovery, Data Mining in Social Networks, Data Mining in Biomedical informatics and Healthcare, Pattern Mining and Application of Big Data in conjunction with 18th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2014 ; Conference date: 13-05-2014 Through 16-05-2014",
year = "2014",
doi = "10.1007/978-3-319-13186-3_43",
language = "English",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "483--493",
editor = "Wen-Chih Peng and Haixun Wang and Zhi-Hua Zhou and Ho, {Tu Bao} and Tseng, {Vincent S.} and Chen, {Arbee L.P.} and James Bailey",
booktitle = "Trends and Applications in Knowledge Discovery and Data Mining - PAKDD 2014 International Workshops",
}