17-09-2009, 10:08 PM
A SIGNATURE BASED INDEXING METHOD FOR EFFICIENT CONTENT BASED RETRIEVAL OF RELATIVE TEMPORAL PATTERNS
Abstract: Project aims for efficient content based retrieval process of relative temporal pattern using signature based indexing method. Rule discovery algorithms in data mining generate a large number of patterns/rules, sometimes even exceeding the size of the underlying database, with only a small fraction being of interest to the user. It is generally understood that interpreting the discovered patterns/rules to gain insight into the domain is an important phase in the knowledge discovery process. However, when there are a large number of generated rules, identifying and analyzing those that are interesting becomes difficult. We address the problem of efficiently retrieving subsets of a large collection of previously discovered temporal patterns. When processing queries on a small database of temporal patterns, sequential scanning of the patterns followed by straightforward computations of query conditions is sufficient. However, as the database grows, this procedure can be too slow, and indexes should be built to speed up the queries. The problem is to determine what types of indexes are suitable for improving the speed of queries involving the content of temporal patterns. We propose a system with signature-based indexing method to speed up content-based queries on temporal patterns And Itâ„¢s used to optimize the storage and retrieval of a large collection of relative temporal patterns. The use of signature files improves the performance of temporal pattern retrieval. This retrieval system is currently being combined with visualization techniques for monitoring the behavior of a single pattern or a group of patterns over time.