Title: An efficient algorithm for mining closed frequent intervals

Authors: Naba Jyoti Sarmah; Anjana Kakoti Mahanta

Addresses: Nalbari Commerce College, Gauhati University, India ' Nalbari Commerce College, Gauhati University, India

Abstract: In this paper, we propose a method for mining closed frequent intervals from interval dataset. Already known algorithms for mining closed frequent intervals use either the maximal frequent intervals or a tree structure to generate the closed intervals. The algorithm proposed in this paper mines the closed frequent intervals directly from interval datasets. Mathematical proofs of certain properties of closed intervals that are used in the proposed algorithm have been given. The proposed algorithm has been tested with real life and synthetic datasets. Complexity of the proposed algorithm is O(n2), which is better than any other existing algorithms developed for mining closed frequent intervals.

Keywords: data mining; interval data mining; closed frequent interval; maximal frequent interval.

DOI: 10.1504/IJKEDM.2018.094746

International Journal of Knowledge Engineering and Data Mining, 2018 Vol.5 No.3, pp.222 - 240

Received: 10 Apr 2018
Accepted: 27 May 2018

Published online: 14 Sep 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article