Temporal association rules mining: a heuristic methodology applied to time series databases (TSDBs)

Authors:
Conti Dante;J. Martinez De Pison Francisco;Pernia Alpha
Affiliations:
Departamento de Investigacion de Operaciones de la Escuela de Ingenieria de Sistemas, Universidad de Los Andes, Facultad de Ingenieria, Merida, Venezuela;EDMANS Group, Departamento de Ingenieria Mecanica, Universidad de La Rioja, La Rioja, Spain;EDMANS Group, Departamento de Ingenieria Mecanica, Universidad de La Rioja, La Rioja, Spain
Venue:
CIMMACS '10 Proceedings of the 9th WSEAS international conference on computational intelligence, man-machine systems and cybernetics
Year:
2010

Citing 15
Cited 0

Breaking the barrier of transactions: mining inter-transaction association rules

KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Principles of data mining

Principles of data mining
Discovery of Frequent Episodes in Event Sequences

Data Mining and Knowledge Discovery
Scalable Algorithms for Association Mining

IEEE Transactions on Knowledge and Data Engineering
Discovering Representative Episodal Association Rules from Event Sequences Using Frequent Closed Episode Sets and Event Constraints

ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Discovering Sequential Association Rules with Constraints and Time Lags in Multiple Sequences

ISMIS '02 Proceedings of the 13th International Symposium on Foundations of Intelligent Systems
Data Mining in Time Series Database

Data Mining in Time Series Database
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
A survey of interestingness measures for knowledge discovery

The Knowledge Engineering Review
An efficient algorithm for mining frequent inter-transaction patterns

Information Sciences: an International Journal
ARMADA - An algorithm for discovering richer relative temporal association rules from interval-based data

Data & Knowledge Engineering
Efficient mining of frequent episodes from complex sequences

Information Systems
Univariate modeling and forecasting of monthly energy demand time series using abductive and neural networks

Computers and Industrial Engineering
Statistical mining of interesting association rules

Statistics and Computing
Fuzzy expert systems and challenge of new product pricing

Computers and Industrial Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper shows and describes a heuristic methodology applied to Time Series Databases (TSDBs) by approaching Temporal Data Mining (TDM). The methodology focuses on temporal association rules from multiple time series which could be captured from many applications and processes (industrial processes, financial assets, environment variables, demographic series, etc). This heuristic methodology is designed to obtain temporal association rules that represent the repeated relationships between events/episodes of a big number of time series, using a time window and a time lag. The process involves finding significant events into multivariate time series and then, with the consequent fixed, extracting previous important episodes within a time window and time lag established. In the next stage, a search is made for sequences of episodes or items that are repeated amongst the various time series. Finally, extraction is carried out of the temporal association rules for those cases that appear on a high number of times and have a high rate of hits. This proposal is computerised by using R-language supported with a software tool that has been called CONOTOOL.