Data Mining Time Series Data With Virtual Transaction


The KIPS Transactions:PartD, Vol. 9, No. 2, pp. 251-257, Apr. 2002
10.3745/KIPSTD.2002.9.2.251,   PDF Download:

Abstract

There has been much research on data mining techniques for applying more advanced applications. However, most of these techniques has focused on transaction data rather than time series data. In this paper, we introduce a approach to convert time series data into virtual transaction data for more useful data mining applications. A virtual transaction is defined to be a collection of events that occur relatively close to each other. A virtual transaction generator uses time window or event window methods. Our approach based on time series data can be used with most conventional transaction algorithms without further modification.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
U. M. Kim, M. S. Kim, C. H. Kim, "Data Mining Time Series Data With Virtual Transaction," The KIPS Transactions:PartD, vol. 9, no. 2, pp. 251-257, 2002. DOI: 10.3745/KIPSTD.2002.9.2.251.

[ACM Style]
Ung Mo Kim, Min Soo Kim, and Chul Hwan Kim. 2002. Data Mining Time Series Data With Virtual Transaction. The KIPS Transactions:PartD, 9, 2, (2002), 251-257. DOI: 10.3745/KIPSTD.2002.9.2.251.