@article{TIAN2005, 
author = {Jinlan TIAN and Lin ZHU and Suqin ZHANG and Lu LIU},
title = {Improvement and Parallelism of k-Means Clustering Algorithm},
year = {2005},
journal = {Tsinghua Science and Technology},
volume = {10},
number = {3},
pages = {277-281},
keywords = {data mining, cluster analysis, k-means algorithm, parallelism},
url = {https://www.sciopen.com/article/10.1016/S1007-0214(05)70069-9},
doi = {10.1016/S1007-0214(05)70069-9},
abstract = {The k-means clustering algorithm is one of the most commonly used algorithms for clustering analysis. The traditional k-means algorithm is, however, inefficient while working on large numbers of data sets and improving the algorithm efficiency remains a problem. This paper focuses on the efficiency issues of cluster algorithms. A refined initial cluster centers method is designed to reduce the number of iterative procedures in the algorithm. A parallel k-means algorithm is also studied for the problem of the operation limitation of a single processor machine when given huge data sets. The analytical results demonstrate that these improvements can greatly enhance the efficiency of the k-means algorithm, i.e., allow the grouping of a large number of data sets more accurately and more quickly. The analysis has theoretical and practical importance for work on the improvement and parallelism of cluster algorithms.}
}