Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


ucin1141325950.pdf (2.86 MB)

ETD Abstract Container

Abstract Header

FINDING TEMPORAL ASSOCIATION RULES BETWEEN FREQUENT PATTERNS IN MULTIVARIATE TIME SERIES

TATAVARTY, GIRIDHAR
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1141325950

Abstract Details

2006, MS, University of Cincinnati, Engineering : Computer Science.
Multivariate time series datasets represents multiple attributes recorded over a period of time. Each attribute may have repeating patterns and there may also be correlations among patterns observed across different attributes. Discovery of these repeating patterns, dependencies amongst them gives power to predict other events in the data and is useful for building diagnostic and predictive tools. An example from weather monitoring may say that observation of a particular pattern of temperature and pressure may signify a particular type of precipitation a few time units later. This thesis presents a novel approach for discovering all frequent patterns in each observed attribute and also temporal dependencies among these patterns. The methodology and algorithms presented are generic and can be adapted to various application environments. Robustness against noise, random variation, minor temporal shifting and scaling of patterns is demonstrated. Experiments from a large real life datasets show very interesting temporal relationships.
Dr. Raj Bhatnagar (Advisor)
95 p.
Computer Science
multivariate; time series; data mining; temporal association rules; suffix trees; summarization

Recommended Citations

Citations

  • TATAVARTY, G. (2006). FINDING TEMPORAL ASSOCIATION RULES BETWEEN FREQUENT PATTERNS IN MULTIVARIATE TIME SERIES [Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1141325950

    APA Style (7th edition)

  • TATAVARTY, GIRIDHAR. FINDING TEMPORAL ASSOCIATION RULES BETWEEN FREQUENT PATTERNS IN MULTIVARIATE TIME SERIES. 2006. University of Cincinnati, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1141325950.

    MLA Style (8th edition)

  • TATAVARTY, GIRIDHAR. "FINDING TEMPORAL ASSOCIATION RULES BETWEEN FREQUENT PATTERNS IN MULTIVARIATE TIME SERIES." Master's thesis, University of Cincinnati, 2006. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1141325950

    Chicago Manual of Style (17th edition)

ucin1141325950
1,403
© 2006, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.