Adaptive multimedia mining on distributed stream processing systems

Deepak S. Turaga; Hyunggon Park; Rong Yan; Olivier Verscheure

doi:10.1109/ICDMW.2010.159

Adaptive multimedia mining on distributed stream processing systems

Deepak S. Turaga, Hyunggon Park, Rong Yan, Olivier Verscheure

Electronic and Electrical Engineering

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

2 Scopus citations

Abstract

We present an application for distributed semantic concept detection in multimedia streams. The streams are mined using Support Vector Machine based concept detectors (classifiers) deployed on a distributed stream processing system. We organize the classifiers into a hierarchical topology based on semantic relationships between the concepts of interest, and use the system resource manager to place the topology across a set of processing nodes. We then develop distributed game theoretic optimization strategies for dynamic adaptation of individual classifier operating characteristics in order to maximize end-to-end application utility under varying resource availability. As part of this paper, we will demonstrate the principles behind large-scale multimedia stream mining, and showcase the design, development, deployment, and distributed adaptation of such applications on a large scale cluster. A video demonstration of the system can be found at: http://childman.bol.ucla.edu/ICDM/ demovideoicdm2009.swf

Original language	English
Title of host publication	Proceedings - 10th IEEE International Conference on Data Mining Workshops, ICDMW 2010
Pages	1419-1422
Number of pages	4
DOIs	https://doi.org/10.1109/ICDMW.2010.159
State	Published - 2010
Event	10th IEEE International Conference on Data Mining Workshops, ICDMW 2010 - Sydney, NSW, Australia Duration: 14 Dec 2010 → 17 Dec 2010

Publication series

Name	Proceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)	1550-4786

Conference

Conference	10th IEEE International Conference on Data Mining Workshops, ICDMW 2010
Country/Territory	Australia
City	Sydney, NSW
Period	14/12/10 → 17/12/10

Keywords

Large-scale mining
Multimedia mining
Resource adaptive mining
Semantic concept detection
Stream processing

Access to Document

10.1109/ICDMW.2010.159

Cite this

@inproceedings{6d65debe5b6d45d49d1324c8245c7499,

title = "Adaptive multimedia mining on distributed stream processing systems",

abstract = "We present an application for distributed semantic concept detection in multimedia streams. The streams are mined using Support Vector Machine based concept detectors (classifiers) deployed on a distributed stream processing system. We organize the classifiers into a hierarchical topology based on semantic relationships between the concepts of interest, and use the system resource manager to place the topology across a set of processing nodes. We then develop distributed game theoretic optimization strategies for dynamic adaptation of individual classifier operating characteristics in order to maximize end-to-end application utility under varying resource availability. As part of this paper, we will demonstrate the principles behind large-scale multimedia stream mining, and showcase the design, development, deployment, and distributed adaptation of such applications on a large scale cluster. A video demonstration of the system can be found at: http://childman.bol.ucla.edu/ICDM/ demovideoicdm2009.swf",

keywords = "Large-scale mining, Multimedia mining, Resource adaptive mining, Semantic concept detection, Stream processing",

author = "Turaga, {Deepak S.} and Hyunggon Park and Rong Yan and Olivier Verscheure",

year = "2010",

doi = "10.1109/ICDMW.2010.159",

language = "English",

isbn = "9780769542577",

series = "Proceedings - IEEE International Conference on Data Mining, ICDM",

pages = "1419--1422",

booktitle = "Proceedings - 10th IEEE International Conference on Data Mining Workshops, ICDMW 2010",

note = "null ; Conference date: 14-12-2010 Through 17-12-2010",

}

Turaga, DS, Park, H, Yan, R & Verscheure, O 2010, Adaptive multimedia mining on distributed stream processing systems. in Proceedings - 10th IEEE International Conference on Data Mining Workshops, ICDMW 2010., 5693467, Proceedings - IEEE International Conference on Data Mining, ICDM, pp. 1419-1422, 10th IEEE International Conference on Data Mining Workshops, ICDMW 2010, Sydney, NSW, Australia, 14/12/10. https://doi.org/10.1109/ICDMW.2010.159

Adaptive multimedia mining on distributed stream processing systems. / Turaga, Deepak S.; Park, Hyunggon; Yan, Rong et al.

Proceedings - 10th IEEE International Conference on Data Mining Workshops, ICDMW 2010. 2010. p. 1419-1422 5693467 (Proceedings - IEEE International Conference on Data Mining, ICDM).

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

TY - GEN

T1 - Adaptive multimedia mining on distributed stream processing systems

AU - Turaga, Deepak S.

AU - Park, Hyunggon

AU - Yan, Rong

AU - Verscheure, Olivier

PY - 2010

Y1 - 2010

N2 - We present an application for distributed semantic concept detection in multimedia streams. The streams are mined using Support Vector Machine based concept detectors (classifiers) deployed on a distributed stream processing system. We organize the classifiers into a hierarchical topology based on semantic relationships between the concepts of interest, and use the system resource manager to place the topology across a set of processing nodes. We then develop distributed game theoretic optimization strategies for dynamic adaptation of individual classifier operating characteristics in order to maximize end-to-end application utility under varying resource availability. As part of this paper, we will demonstrate the principles behind large-scale multimedia stream mining, and showcase the design, development, deployment, and distributed adaptation of such applications on a large scale cluster. A video demonstration of the system can be found at: http://childman.bol.ucla.edu/ICDM/ demovideoicdm2009.swf

AB - We present an application for distributed semantic concept detection in multimedia streams. The streams are mined using Support Vector Machine based concept detectors (classifiers) deployed on a distributed stream processing system. We organize the classifiers into a hierarchical topology based on semantic relationships between the concepts of interest, and use the system resource manager to place the topology across a set of processing nodes. We then develop distributed game theoretic optimization strategies for dynamic adaptation of individual classifier operating characteristics in order to maximize end-to-end application utility under varying resource availability. As part of this paper, we will demonstrate the principles behind large-scale multimedia stream mining, and showcase the design, development, deployment, and distributed adaptation of such applications on a large scale cluster. A video demonstration of the system can be found at: http://childman.bol.ucla.edu/ICDM/ demovideoicdm2009.swf

KW - Large-scale mining

KW - Multimedia mining

KW - Resource adaptive mining

KW - Semantic concept detection

KW - Stream processing

UR - http://www.scopus.com/inward/record.url?scp=79951742652&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2010.159

DO - 10.1109/ICDMW.2010.159

M3 - Conference contribution

AN - SCOPUS:79951742652

SN - 9780769542577

T3 - Proceedings - IEEE International Conference on Data Mining, ICDM

SP - 1419

EP - 1422

BT - Proceedings - 10th IEEE International Conference on Data Mining Workshops, ICDMW 2010

Y2 - 14 December 2010 through 17 December 2010

ER -

Adaptive multimedia mining on distributed stream processing systems

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this