ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Analyzing Similarities of Datasets Using a Pattern Set Kernel

Ibrahim, A and Sastry, PS and Sastry, Shivakumar (2016) Analyzing Similarities of Datasets Using a Pattern Set Kernel. In: 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), APR 19-22, 2016, Univ Auckland, Auckland, NEW ZEALAND, pp. 265-276.

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1007/978-3-319-31753-3_22


In the area of pattern discovery, there is much interest in discovering small sets of patterns that characterize the data well. In such scenarios, when data is represented by a small set of characterizing patterns, an interesting problem is the comparison of datasets, by comparing the respective representative sets of patterns. In this paper, we propose a novel kernel function for measuring similarities between two sets of patterns, which is based on evaluating the structural similarities between the patterns in the two sets, weighted using their relative frequencies in the data. We define the kernel for injective serial episodes and itemsets. We also present an efficient algorithm for computing this kernel. We demonstrate the effectiveness of our kernel on classification scenarios and for change detection using sequential datasets and transaction databases.

Item Type: Conference Proceedings
Series.: Lecture Notes in Artificial Intelligence
Additional Information: Copy right for this article belongs to the SPRINGER-VERLAG BERLIN, HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 04 Jan 2017 05:08
Last Modified: 15 Oct 2018 14:21
URI: http://eprints.iisc.ac.in/id/eprint/55730

Actions (login required)

View Item View Item