Agent-based forward analysis

Ryan Kerekes; Yu Jiao; Mallikarjun Shankar; Thomas Potok; Rick Lusk

doi:10.1109/MILCOM.2008.4753516

Agent-based forward analysis

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

Abstract

We propose software agent-based "forward analysis" for efficient information retrieval in a network of sensing devices. In our approach, processing is pushed to the data at the edge of the network via intelligent software agents rather than pulling data to a central facility for processing. The agents are deployed with a specific query and perform varying levels of analysis of the data, communicating with each other and sending only relevant information back across the network. We demonstrate our concept in the context of face recognition using a wireless test bed comprised of PDA cell phones and laptops. We show that agent-based forward analysis can provide a significant increase in retrieval speed while decreasing bandwidth usage and information overload at the central facility.

Original language	English
Title of host publication	2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success
DOIs	https://doi.org/10.1109/MILCOM.2008.4753516
State	Published - 2008
Event	2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success - Washington, DC, United States Duration: Nov 17 2008 → Nov 19 2008

Publication series

Name	Proceedings - IEEE Military Communications Conference MILCOM

Conference

Conference	2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success
Country/Territory	United States
City	Washington, DC
Period	11/17/08 → 11/19/08

Access to Document

10.1109/MILCOM.2008.4753516

Cite this

@inproceedings{db88054818824fbd8d725dcf6ad254c0,

title = "Agent-based forward analysis",

abstract = "We propose software agent-based {"}forward analysis{"} for efficient information retrieval in a network of sensing devices. In our approach, processing is pushed to the data at the edge of the network via intelligent software agents rather than pulling data to a central facility for processing. The agents are deployed with a specific query and perform varying levels of analysis of the data, communicating with each other and sending only relevant information back across the network. We demonstrate our concept in the context of face recognition using a wireless test bed comprised of PDA cell phones and laptops. We show that agent-based forward analysis can provide a significant increase in retrieval speed while decreasing bandwidth usage and information overload at the central facility.",

author = "Ryan Kerekes and Yu Jiao and Mallikarjun Shankar and Thomas Potok and Rick Lusk",

year = "2008",

doi = "10.1109/MILCOM.2008.4753516",

language = "English",

isbn = "9781424426775",

series = "Proceedings - IEEE Military Communications Conference MILCOM",

booktitle = "2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success",

note = "2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success ; Conference date: 17-11-2008 Through 19-11-2008",

}

Kerekes, R, Jiao, Y, Shankar, M , Potok, T & Lusk, R 2008, Agent-based forward analysis. in 2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success., 4753516, Proceedings - IEEE Military Communications Conference MILCOM, 2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success, Washington, DC, United States, 11/17/08. https://doi.org/10.1109/MILCOM.2008.4753516

TY - GEN

T1 - Agent-based forward analysis

AU - Kerekes, Ryan

AU - Jiao, Yu

AU - Shankar, Mallikarjun

AU - Potok, Thomas

AU - Lusk, Rick

PY - 2008

Y1 - 2008

N2 - We propose software agent-based "forward analysis" for efficient information retrieval in a network of sensing devices. In our approach, processing is pushed to the data at the edge of the network via intelligent software agents rather than pulling data to a central facility for processing. The agents are deployed with a specific query and perform varying levels of analysis of the data, communicating with each other and sending only relevant information back across the network. We demonstrate our concept in the context of face recognition using a wireless test bed comprised of PDA cell phones and laptops. We show that agent-based forward analysis can provide a significant increase in retrieval speed while decreasing bandwidth usage and information overload at the central facility.

AB - We propose software agent-based "forward analysis" for efficient information retrieval in a network of sensing devices. In our approach, processing is pushed to the data at the edge of the network via intelligent software agents rather than pulling data to a central facility for processing. The agents are deployed with a specific query and perform varying levels of analysis of the data, communicating with each other and sending only relevant information back across the network. We demonstrate our concept in the context of face recognition using a wireless test bed comprised of PDA cell phones and laptops. We show that agent-based forward analysis can provide a significant increase in retrieval speed while decreasing bandwidth usage and information overload at the central facility.

UR - https://www.scopus.com/pages/publications/78650758845

U2 - 10.1109/MILCOM.2008.4753516

DO - 10.1109/MILCOM.2008.4753516

M3 - Conference contribution

AN - SCOPUS:78650758845

SN - 9781424426775

T3 - Proceedings - IEEE Military Communications Conference MILCOM

BT - 2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success

T2 - 2008 IEEE Military Communications Conference, MILCOM 2008 - Assuring Mission Success

Y2 - 17 November 2008 through 19 November 2008

ER -

Agent-based forward analysis

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this