Date of Award

2005

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

Keywords

Computer Science.

Rights

info:eu-repo/semantics/openAccess

Abstract

Frequent sequential mining is the process of discovering frequent sequential patterns in data sequences as found in applications like web log access sequences. In data stream applications, data arrive at high speed rates in a continuous flow. Data stream mining is an online process different from traditional mining. Traditional mining algorithms work on an entire static dataset in order to obtain results while data stream mining algorithms work with continuously arriving data streams. With rapid change in technology, there are many applications that take data as continuous streams. Examples include stock tickers, network traffic measurements, click stream data, data feeds from sensor networks, and telecom call records. Mining frequent sequential patterns on data stream applications contend with many challenges such as limited memory for unlimited data, inability of algorithms to scan infinitely flowing original dataset more than once and to deliver current and accurate result on demand. This thesis proposes SSM-Algorithm (sequential stream mining-algorithm) that delivers frequent sequential patterns in data streams. The concept of this work came from FP-Stream algorithm that delivers time sensitive frequent patterns. Proposed SSM-Algorithm outperforms FP-Stream algorithm by the use of a hash based and two efficient tree based data structures. All incoming streams are handled dynamically to improve memory usage. SSM-Algorithm maintains frequent sequences incrementally and delivers most current result on demand. The introduced algorithm can be deployed to analyze e-commerce data where the primary source of the data is click stream data. (Abstract shortened by UMI.)Dept. of Computer Science. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2005 .M668. Source: Masters Abstracts International, Volume: 44-03, page: 1409. Thesis (M.Sc.)--University of Windsor (Canada), 2005.

Share

COinS