Hybrid consensus theoretic classification with pruning and regularization

Jon Atli Benediktsson; Kjartan Benediktsson

Hybrid consensus theoretic classification with pruning and regularization

Jon Atli Benediktsson
, Kjartan Benediktsson

University of Iceland

Háskóli Íslands

Rannsóknarafurð: Framlag á ráðstefnu › Vísindagrein › ritrýni

Útdráttur

Conventional statistical pattern recognition methods are not appropriate in classification of multisource data since such data cannot, in most cases, be modeled by a common convenient multivariate statistical model. However, methods based on consensus theory have shown potential in classification of multisource data. Here, optimized combination, regularization, and pruning is proposed for consensus theoretic classification. The regularization scheme iteratively adapts regularization parameters by minimizing the validation error.

Upprunalegt tungumál	Enska
Síður	2486-2488
Síðufjöldi	3
Útgáfustaða	Útgefið - 1999
Viðburður	Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century' - Hamburg, Ger Tímalengd: 28 jún. 1999 → 2 júl. 1999

Ráðstefna

Ráðstefna	Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century'
Borg/bær	Hamburg, Ger
Tímabil	28/06/99 → 2/07/99

Vitna í þetta

@conference{3e18c95b80ee46b9ad718f3c9a15a424,

title = "Hybrid consensus theoretic classification with pruning and regularization",

abstract = "Conventional statistical pattern recognition methods are not appropriate in classification of multisource data since such data cannot, in most cases, be modeled by a common convenient multivariate statistical model. However, methods based on consensus theory have shown potential in classification of multisource data. Here, optimized combination, regularization, and pruning is proposed for consensus theoretic classification. The regularization scheme iteratively adapts regularization parameters by minimizing the validation error.",

author = "Benediktsson, \{Jon Atli\} and Kjartan Benediktsson",

year = "1999",

language = "English",

pages = "2486--2488",

note = "Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century' ; Conference date: 28-06-1999 Through 02-07-1999",

}

Hybrid consensus theoretic classification with pruning and regularization. / Benediktsson, Jon Atli; Benediktsson, Kjartan.
1999. 2486-2488 Fyrirlestur fluttur á Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century', Hamburg, Ger.

Rannsóknarafurð: Framlag á ráðstefnu › Vísindagrein › ritrýni

TY - CONF

T1 - Hybrid consensus theoretic classification with pruning and regularization

AU - Benediktsson, Jon Atli

AU - Benediktsson, Kjartan

PY - 1999

Y1 - 1999

N2 - Conventional statistical pattern recognition methods are not appropriate in classification of multisource data since such data cannot, in most cases, be modeled by a common convenient multivariate statistical model. However, methods based on consensus theory have shown potential in classification of multisource data. Here, optimized combination, regularization, and pruning is proposed for consensus theoretic classification. The regularization scheme iteratively adapts regularization parameters by minimizing the validation error.

AB - Conventional statistical pattern recognition methods are not appropriate in classification of multisource data since such data cannot, in most cases, be modeled by a common convenient multivariate statistical model. However, methods based on consensus theory have shown potential in classification of multisource data. Here, optimized combination, regularization, and pruning is proposed for consensus theoretic classification. The regularization scheme iteratively adapts regularization parameters by minimizing the validation error.

UR - https://www.scopus.com/pages/publications/0033327676

M3 - Paper

SP - 2486

EP - 2488

T2 - Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century'

Y2 - 28 June 1999 through 2 July 1999

ER -

Hybrid consensus theoretic classification with pruning and regularization

Útdráttur

Ráðstefna

Fingerprint

Vitna í þetta