Mixture of HMM Experts with applications to landmine detection

Seniha Esen Yuksel; Paul D. Gader

doi:10.1109/IGARSS.2012.6352589

Mixture of HMM Experts with applications to landmine detection

Seniha Esen Yuksel
, Paul D. Gader

University of Florida

Research output: Contribution to conference › Paper › peer-review

6 Citations (Scopus)

Abstract

This paper introduces a novel mixture of experts model, the Mixture of Hidden Markov Model Experts (MHMME). This model is designed to perform context-based classification of samples that are variable length sequences. The contexts are determined by the gates and the classifiers are determined by the experts. The gates and the experts are learned simultaneously using a single probabilistic model. Experimental results on landmine dataset show that MHMME significantly outperforms the HMM-based and ME-based models.

Original language	English
Pages	6852-6855
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2012.6352589
Publication status	Published - 2012
Externally published	Yes
Event	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany Duration: 22 Jul 2012 → 27 Jul 2012

Conference

Conference	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
Country/Territory	Germany
City	Munich
Period	22/07/12 → 27/07/12

Keywords

HMM
ME
Mixture of experts
WEMI
hidden Markov models
landmine detection
metal detector

Access to Document

10.1109/IGARSS.2012.6352589

Cite this

@conference{48aecd0e5f014354bf7a3f99f40584a6,

title = "Mixture of HMM Experts with applications to landmine detection",

abstract = "This paper introduces a novel mixture of experts model, the Mixture of Hidden Markov Model Experts (MHMME). This model is designed to perform context-based classification of samples that are variable length sequences. The contexts are determined by the gates and the classifiers are determined by the experts. The gates and the experts are learned simultaneously using a single probabilistic model. Experimental results on landmine dataset show that MHMME significantly outperforms the HMM-based and ME-based models.",

keywords = "HMM, ME, Mixture of experts, WEMI, hidden Markov models, landmine detection, metal detector",

author = "Yuksel, \{Seniha Esen\} and Gader, \{Paul D.\}",

year = "2012",

doi = "10.1109/IGARSS.2012.6352589",

language = "English",

pages = "6852--6855",

note = "2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

}

TY - CONF

T1 - Mixture of HMM Experts with applications to landmine detection

AU - Yuksel, Seniha Esen

AU - Gader, Paul D.

PY - 2012

Y1 - 2012

N2 - This paper introduces a novel mixture of experts model, the Mixture of Hidden Markov Model Experts (MHMME). This model is designed to perform context-based classification of samples that are variable length sequences. The contexts are determined by the gates and the classifiers are determined by the experts. The gates and the experts are learned simultaneously using a single probabilistic model. Experimental results on landmine dataset show that MHMME significantly outperforms the HMM-based and ME-based models.

AB - This paper introduces a novel mixture of experts model, the Mixture of Hidden Markov Model Experts (MHMME). This model is designed to perform context-based classification of samples that are variable length sequences. The contexts are determined by the gates and the classifiers are determined by the experts. The gates and the experts are learned simultaneously using a single probabilistic model. Experimental results on landmine dataset show that MHMME significantly outperforms the HMM-based and ME-based models.

KW - HMM

KW - ME

KW - Mixture of experts

KW - WEMI

KW - hidden Markov models

KW - landmine detection

KW - metal detector

UR - https://www.scopus.com/pages/publications/84873194640

U2 - 10.1109/IGARSS.2012.6352589

DO - 10.1109/IGARSS.2012.6352589

M3 - Paper

AN - SCOPUS:84873194640

SP - 6852

EP - 6855

T2 - 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012

Y2 - 22 July 2012 through 27 July 2012

ER -

Mixture of HMM Experts with applications to landmine detection

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this