NDLI: Efficient construction and usefulness of hyper-rectangle greedy covers

Content Provider	IEEE Xplore Digital Library
Author	Ouchi, K. Nakamura, A. Kudo, M.
Copyright Year	2011
Description	Author affiliation: Graduate School of Information Science and Technology, Hokkaido University, Kita 14, Nishi 9, Kita-ku, Sapporo, Hokkaido, 060-0814, Japan (Ouchi, K.; Nakamura, A.; Kudo, M.)
Abstract	We discuss efficient construction and usefulness of greedy covers of positive instances by axis-parallel rectangles that exclude negative instances. A rectangle greedy cover is expected to be a simple classification rule with high readability because the number of its component rectangles is expected to be small and it can be seen as a disjunctive normal form, which is one of the most readable representations. We develop efficient construction methods of rectangle greedy covers by making use of algorithms for efficient maximal frequent itemsets. We empirically demonstrate that, for high dimensional datasets, the method of finding a component rectangle one by one without enumerating candidate covering component sets is faster than the method with independent greedy covering process after the enumeration. In our classification experiments using 10 datasets in UCI repository, rectangle greedy covers (RGC) were shown to have classification performance comparable to the randomized subclass method (RSM) developed in [1], which is a conventional classification method using rectangles, though RGC used significantly smaller number of rectangles. The performance of RGC was also shown to be comparable to that of popular classifiers such as logistic regression and SVM. The DNF-representation of the classification rules obtained by RGC was demonstrated to be simpler than that obtained by RSM and C4.5 through our experiment.
Starting Page	533
Ending Page	538
File Size	307551
Page Count	6
File Format	PDF
ISBN	9781457703720
e-ISBN	9781457703713
DOI	10.1109/GRC.2011.6122653
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2011-11-08
Publisher Place	Taiwan
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Support vector machines Training Iris Itemsets Lungs DNF-rule Liver Glass rectangle learning greedy learning
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

An Efficient Construction and Application Usefulness of Rectangle Greedy Covers (2014)

Direct L2 Support Vector Machine classifier and performances of its two implementations

New decision function for support vector data description

A hyper-box approach using relational databases for large scale machine learning

Spectral Clustering-based Classification

Biased Support Vector Machine with Self-Constructed Universum for PU Learning

Dynamic Combination of SVM Based on Optimal Kernel

An Iris Recognition Approach based on Fuzzy Support Vector Machine

Improved support vector data description

Efficient construction and usefulness of hyper-rectangle greedy covers

Similar Documents

An Efficient Construction and Application Usefulness of Rectangle Greedy Covers (2014)

Direct L2 Support Vector Machine classifier and performances of its two implementations

New decision function for support vector data description

A hyper-box approach using relational databases for large scale machine learning

Spectral Clustering-based Classification

Biased Support Vector Machine with Self-Constructed Universum for PU Learning

Dynamic Combination of SVM Based on Optimal Kernel

An Iris Recognition Approach based on Fuzzy Support Vector Machine

Improved support vector data description

Efficient construction and usefulness of hyper-rectangle greedy covers