@inbook{6f49fdbd71c8497cb84bff887eafbaa3,

title = "A statistical μ-partitioning method for clustering data streams",

abstract = "A data stream is a massive unbounded sequence of data elements continuously generated at a rapid rate. Due to this reason, most algorithms for data streams sacrifice the correctness of their results for fast processing time. This paper proposes a clustering method over a data stream based on statistical μ-partition. The multi-dimensional space of a data domain is divided into a set of mutually exclusive equal-size initial cells. A cell maintains the distribution statistics of data elements in its range. Based on the distribution statistics of a cell, a dense cell is dynamically split into two mutually exclusive smaller cells called intermediate cells. Eventually, the dense sub-range of an initial cell is recursively partitioned until it becomes the smallest cell called a unit cell. A cluster of a data stream is a group of adjacent dense unit cells. As the size of a unit cell is set to be smaller, the resulting set of clusters is more accurately identified. Through a series of experiments, the performance of the proposed algorithm is comparatively analyzed.",

author = "Park, {Nam Hun} and Lee, {Won Suk}",

year = "2003",

doi = "10.1007/978-3-540-39737-3_37",

language = "English",

isbn = "3540204091",

series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",

publisher = "Springer Verlag",

pages = "292--299",

editor = "Adnan Yazici and Cevat Sener",

booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",

address = "Germany",

}