Abstract
This study compares the classification ability of various fusion algorithms (average, majority vote, median, max/min) when individual classifiers are potentially correlated. A logistic transformation of multivariate normal distribution (MVN) is used to generate the posterior probability estimates, assuring that the probability exists between 0 and 1. With varying parameters of MVN and number of classifiers, we measure the relative performance of the fusion algorithms to that of single classifier. Our results can be utilized for the selection of the most effective fusion method for given situation.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004 |
| Editors | P. Svensson, J. Schubert |
| Pages | 569-575 |
| Number of pages | 7 |
| Publication status | Published - 2004 Nov 2 |
| Event | Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004 - Stockholm, Sweden Duration: 2004 Jun 28 → 2004 Jul 1 |
Publication series
| Name | Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004 |
|---|---|
| Volume | 1 |
Other
| Other | Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004 |
|---|---|
| Country | Sweden |
| City | Stockholm |
| Period | 04/6/28 → 04/7/1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
Cite this
}
Comparison of fusion algorithms based on logistic model of correlated classifiers. / Sohn, S. Y.; Kim, Y. S.
Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004. ed. / P. Svensson; J. Schubert. 2004. p. 569-575 (Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004; Vol. 1).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Comparison of fusion algorithms based on logistic model of correlated classifiers
AU - Sohn, S. Y.
AU - Kim, Y. S.
PY - 2004/11/2
Y1 - 2004/11/2
N2 - This study compares the classification ability of various fusion algorithms (average, majority vote, median, max/min) when individual classifiers are potentially correlated. A logistic transformation of multivariate normal distribution (MVN) is used to generate the posterior probability estimates, assuring that the probability exists between 0 and 1. With varying parameters of MVN and number of classifiers, we measure the relative performance of the fusion algorithms to that of single classifier. Our results can be utilized for the selection of the most effective fusion method for given situation.
AB - This study compares the classification ability of various fusion algorithms (average, majority vote, median, max/min) when individual classifiers are potentially correlated. A logistic transformation of multivariate normal distribution (MVN) is used to generate the posterior probability estimates, assuring that the probability exists between 0 and 1. With varying parameters of MVN and number of classifiers, we measure the relative performance of the fusion algorithms to that of single classifier. Our results can be utilized for the selection of the most effective fusion method for given situation.
UR - http://www.scopus.com/inward/record.url?scp=6344248964&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=6344248964&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:6344248964
SN - 917056115X
T3 - Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004
SP - 569
EP - 575
BT - Proceedings of the Seventh International Conference on Information Fusion, FUSION 2004
A2 - Svensson, P.
A2 - Schubert, J.
ER -