Authoritative citation KNN learning in multiple-instance problems

Joseph Bernadt; Leen Kiat Soh

doi:10.1109/icmla.2004.1383543

Authoritative citation KNN learning in multiple-instance problems

Joseph Bernadt, Leen Kiat Soh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose an authoritative citation K-nearest neighbor (ACKNN) algorithm for learning and classification in multiple-instance problems. We devise an authority measure for each instance or each bag of instances. This authority measure records how well an instance or a bag of instances has contributed to a correct classification, thus documenting how well an instance or a bag has been cited as a nearest neighbor. Based on our experiments with the Musk1 and Musk2 datasets, by learning the authority measures, the ACKNN algorithm outperforms most other algorithms in Musk1 classification accuracy, but only performs reasonably well in Musk2 classification accuracy.

Original language	English (US)
Title of host publication	Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	410-417
Number of pages	8
ISBN (Print)	0780388232, 9780780388239
DOIs	https://doi.org/10.1109/icmla.2004.1383543
State	Published - 2004
Event	2004 International Conference on Machine Learning and Applications, ICMLA '04 - Louisville, KY, United States Duration: Dec 16 2004 → Dec 18 2004

Publication series

Name	Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04

Conference

Conference	2004 International Conference on Machine Learning and Applications, ICMLA '04
Country/Territory	United States
City	Louisville, KY
Period	12/16/04 → 12/18/04

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/icmla.2004.1383543

Cite this

Bernadt, J., & Soh, L. K. (2004). Authoritative citation KNN learning in multiple-instance problems. In Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04 (pp. 410-417). (Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icmla.2004.1383543

Authoritative citation KNN learning in multiple-instance problems. / Bernadt, Joseph; Soh, Leen Kiat.
Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04. Institute of Electrical and Electronics Engineers Inc., 2004. p. 410-417 (Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bernadt, J & Soh, LK 2004, Authoritative citation KNN learning in multiple-instance problems. in Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04. Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04, Institute of Electrical and Electronics Engineers Inc., pp. 410-417, 2004 International Conference on Machine Learning and Applications, ICMLA '04, Louisville, KY, United States, 12/16/04. https://doi.org/10.1109/icmla.2004.1383543

Bernadt J, Soh LK. Authoritative citation KNN learning in multiple-instance problems. In Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04. Institute of Electrical and Electronics Engineers Inc. 2004. p. 410-417. (Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04). doi: 10.1109/icmla.2004.1383543

Bernadt, Joseph ; Soh, Leen Kiat. / Authoritative citation KNN learning in multiple-instance problems. Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04. Institute of Electrical and Electronics Engineers Inc., 2004. pp. 410-417 (Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04).

@inproceedings{5b111312f2af4b4789d7af29bf163b2a,

title = "Authoritative citation KNN learning in multiple-instance problems",

abstract = "In this paper, we propose an authoritative citation K-nearest neighbor (ACKNN) algorithm for learning and classification in multiple-instance problems. We devise an authority measure for each instance or each bag of instances. This authority measure records how well an instance or a bag of instances has contributed to a correct classification, thus documenting how well an instance or a bag has been cited as a nearest neighbor. Based on our experiments with the Musk1 and Musk2 datasets, by learning the authority measures, the ACKNN algorithm outperforms most other algorithms in Musk1 classification accuracy, but only performs reasonably well in Musk2 classification accuracy.",

author = "Joseph Bernadt and Soh, {Leen Kiat}",

year = "2004",

doi = "10.1109/icmla.2004.1383543",

language = "English (US)",

isbn = "0780388232",

series = "Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "410--417",

booktitle = "Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04",

note = "2004 International Conference on Machine Learning and Applications, ICMLA '04 ; Conference date: 16-12-2004 Through 18-12-2004",

}

TY - GEN

T1 - Authoritative citation KNN learning in multiple-instance problems

AU - Bernadt, Joseph

AU - Soh, Leen Kiat

PY - 2004

Y1 - 2004

N2 - In this paper, we propose an authoritative citation K-nearest neighbor (ACKNN) algorithm for learning and classification in multiple-instance problems. We devise an authority measure for each instance or each bag of instances. This authority measure records how well an instance or a bag of instances has contributed to a correct classification, thus documenting how well an instance or a bag has been cited as a nearest neighbor. Based on our experiments with the Musk1 and Musk2 datasets, by learning the authority measures, the ACKNN algorithm outperforms most other algorithms in Musk1 classification accuracy, but only performs reasonably well in Musk2 classification accuracy.

AB - In this paper, we propose an authoritative citation K-nearest neighbor (ACKNN) algorithm for learning and classification in multiple-instance problems. We devise an authority measure for each instance or each bag of instances. This authority measure records how well an instance or a bag of instances has contributed to a correct classification, thus documenting how well an instance or a bag has been cited as a nearest neighbor. Based on our experiments with the Musk1 and Musk2 datasets, by learning the authority measures, the ACKNN algorithm outperforms most other algorithms in Musk1 classification accuracy, but only performs reasonably well in Musk2 classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=21244440667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21244440667&partnerID=8YFLogxK

U2 - 10.1109/icmla.2004.1383543

DO - 10.1109/icmla.2004.1383543

M3 - Conference contribution

AN - SCOPUS:21244440667

SN - 0780388232

SN - 9780780388239

T3 - Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04

SP - 410

EP - 417

BT - Proceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2004 International Conference on Machine Learning and Applications, ICMLA '04

Y2 - 16 December 2004 through 18 December 2004

ER -

Authoritative citation KNN learning in multiple-instance problems

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this