Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection

Mete Özay; Okan Akalin; Fatoş T. Yarman-Vural

doi:10.1109/ISCIS.2009.5291800

Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection

Mete Özay, Okan Akalin, Fatoş T. Yarman-Vural

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

Abstract

In this work, we propose a framework for multimodal data fusion at decision level under a multilayer hierarchical ensemble learning architecture. The architecture provides a generative discriminative model for probability density estimations and decreases the entropy of the data throughout the vector spaces. The architecture is implemented for human motion detection problem, where the motion analysis problem is formulated as a multi-class classification problem on audio-visual data. The vector space transformations are analyzed by the investigation of probability density and entropy transitions of data across the levels. The architecture provides an efficient sensor fusion framework for the robotics research, object classification, target detection and tracking applications.

Original language	English
Title of host publication	2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
Pages	420-425
Number of pages	6
DOIs	https://doi.org/10.1109/ISCIS.2009.5291800
Publication status	Published - 2009
Externally published	Yes
Event	2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009 - Guzelyurt, Cyprus Duration: 2009 Sept 14 → 2009 Sept 16

Publication series

Name	2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009

Other

Other	2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
Country/Territory	Cyprus
City	Guzelyurt
Period	09/9/14 → 09/9/16

Keywords

Data fusion
Ensemble learning
Kernel methods
Object detection
Probabilistic models

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software

Access to Document

10.1109/ISCIS.2009.5291800

Cite this

Özay, M., Akalin, O., & Yarman-Vural, F. T. (2009). Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection. In 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009 (pp. 420-425). [5291800] (2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009). https://doi.org/10.1109/ISCIS.2009.5291800

Ensemble detection : A new architecture for multisensor data fusion with ensemble learning for object detection. / Özay, Mete; Akalin, Okan; Yarman-Vural, Fatoş T.

2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009. 2009. p. 420-425 5291800 (2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009).

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

Özay, M, Akalin, O & Yarman-Vural, FT 2009, Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection. in 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009., 5291800, 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009, pp. 420-425, 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009, Guzelyurt, Cyprus, 09/9/14. https://doi.org/10.1109/ISCIS.2009.5291800

Özay M, Akalin O, Yarman-Vural FT. Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection. In 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009. 2009. p. 420-425. 5291800. (2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009). doi: 10.1109/ISCIS.2009.5291800

@inproceedings{504cdc48f3b142b2ab5ea90a50e992b9,

title = "Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection",

abstract = "In this work, we propose a framework for multimodal data fusion at decision level under a multilayer hierarchical ensemble learning architecture. The architecture provides a generative discriminative model for probability density estimations and decreases the entropy of the data throughout the vector spaces. The architecture is implemented for human motion detection problem, where the motion analysis problem is formulated as a multi-class classification problem on audio-visual data. The vector space transformations are analyzed by the investigation of probability density and entropy transitions of data across the levels. The architecture provides an efficient sensor fusion framework for the robotics research, object classification, target detection and tracking applications.",

keywords = "Data fusion, Ensemble learning, Kernel methods, Object detection, Probabilistic models",

author = "Mete {\"O}zay and Okan Akalin and Yarman-Vural, {Fato{\c s} T.}",

year = "2009",

doi = "10.1109/ISCIS.2009.5291800",

language = "English",

isbn = "9781424450237",

series = "2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009",

pages = "420--425",

booktitle = "2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009",

note = "2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009 ; Conference date: 14-09-2009 Through 16-09-2009",

}

TY - GEN

T1 - Ensemble detection

T2 - 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009

AU - Özay, Mete

AU - Akalin, Okan

AU - Yarman-Vural, Fatoş T.

PY - 2009

Y1 - 2009

N2 - In this work, we propose a framework for multimodal data fusion at decision level under a multilayer hierarchical ensemble learning architecture. The architecture provides a generative discriminative model for probability density estimations and decreases the entropy of the data throughout the vector spaces. The architecture is implemented for human motion detection problem, where the motion analysis problem is formulated as a multi-class classification problem on audio-visual data. The vector space transformations are analyzed by the investigation of probability density and entropy transitions of data across the levels. The architecture provides an efficient sensor fusion framework for the robotics research, object classification, target detection and tracking applications.

AB - In this work, we propose a framework for multimodal data fusion at decision level under a multilayer hierarchical ensemble learning architecture. The architecture provides a generative discriminative model for probability density estimations and decreases the entropy of the data throughout the vector spaces. The architecture is implemented for human motion detection problem, where the motion analysis problem is formulated as a multi-class classification problem on audio-visual data. The vector space transformations are analyzed by the investigation of probability density and entropy transitions of data across the levels. The architecture provides an efficient sensor fusion framework for the robotics research, object classification, target detection and tracking applications.

KW - Data fusion

KW - Ensemble learning

KW - Kernel methods

KW - Object detection

KW - Probabilistic models

UR - http://www.scopus.com/inward/record.url?scp=73949084681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73949084681&partnerID=8YFLogxK

U2 - 10.1109/ISCIS.2009.5291800

DO - 10.1109/ISCIS.2009.5291800

M3 - Conference contribution

AN - SCOPUS:73949084681

SN - 9781424450237

T3 - 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009

SP - 420

EP - 425

BT - 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009

Y2 - 14 September 2009 through 16 September 2009

ER -

Ensemble detection: A new architecture for multisensor data fusion with ensemble learning for object detection

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this