Survivability of complex system - Support vector machine based approach

Y. Hong, N. Gautam, Soundar Rajan Tirupatikumara, A. Surana, H. Gupta, S. Lee, Vijaykrishnan Narayanan, H. Thadakamalla, M. Brinn, M. Greaves

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

Logistic systems which are inherently distributed, in general can be classified as complex systems. Survivability of these systems under varying environment conditions is of paramount importance. Different environmental conditions in which the logistic system resides are translated into several stresses. These in turn will manifest as internal stresses. Logistic systems can be modeled as a collection of software agents. Each agent's behavior is a result of the stresses imposed. Predicting the agents' collective behavior is of paramount importance to ensure survivability. Analytical modeling of such systems becomes very difficult, albeit impossible. In this paper, we study a supply chain in which a real life scenario is used. We implement the supply chain in Cougaar (Cognitive Agent Architecture developed by DARPA) and develop a predictor, based on Support Vector Machine. We report our methodology and results with real-life experiments and stress scenarios.

Original languageEnglish (US)
Pages153-158
Number of pages6
StatePublished - Dec 1 2002
EventProceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design - St. Louis, MO, United States
Duration: Nov 10 2002Nov 13 2002

Other

OtherProceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design
CountryUnited States
CitySt. Louis, MO
Period11/10/0211/13/02

Fingerprint

Support vector machines
Logistics
Large scale systems
Supply chains
Software agents
Residual stresses
Experiments

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Hong, Y., Gautam, N., Tirupatikumara, S. R., Surana, A., Gupta, H., Lee, S., ... Greaves, M. (2002). Survivability of complex system - Support vector machine based approach. 153-158. Paper presented at Proceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design, St. Louis, MO, United States.
Hong, Y. ; Gautam, N. ; Tirupatikumara, Soundar Rajan ; Surana, A. ; Gupta, H. ; Lee, S. ; Narayanan, Vijaykrishnan ; Thadakamalla, H. ; Brinn, M. ; Greaves, M. / Survivability of complex system - Support vector machine based approach. Paper presented at Proceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design, St. Louis, MO, United States.6 p.
@conference{50f0ae4b753640f9aeb9a4c21e6d296f,
title = "Survivability of complex system - Support vector machine based approach",
abstract = "Logistic systems which are inherently distributed, in general can be classified as complex systems. Survivability of these systems under varying environment conditions is of paramount importance. Different environmental conditions in which the logistic system resides are translated into several stresses. These in turn will manifest as internal stresses. Logistic systems can be modeled as a collection of software agents. Each agent's behavior is a result of the stresses imposed. Predicting the agents' collective behavior is of paramount importance to ensure survivability. Analytical modeling of such systems becomes very difficult, albeit impossible. In this paper, we study a supply chain in which a real life scenario is used. We implement the supply chain in Cougaar (Cognitive Agent Architecture developed by DARPA) and develop a predictor, based on Support Vector Machine. We report our methodology and results with real-life experiments and stress scenarios.",
author = "Y. Hong and N. Gautam and Tirupatikumara, {Soundar Rajan} and A. Surana and H. Gupta and S. Lee and Vijaykrishnan Narayanan and H. Thadakamalla and M. Brinn and M. Greaves",
year = "2002",
month = "12",
day = "1",
language = "English (US)",
pages = "153--158",
note = "Proceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design ; Conference date: 10-11-2002 Through 13-11-2002",

}

Hong, Y, Gautam, N, Tirupatikumara, SR, Surana, A, Gupta, H, Lee, S, Narayanan, V, Thadakamalla, H, Brinn, M & Greaves, M 2002, 'Survivability of complex system - Support vector machine based approach' Paper presented at Proceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design, St. Louis, MO, United States, 11/10/02 - 11/13/02, pp. 153-158.

Survivability of complex system - Support vector machine based approach. / Hong, Y.; Gautam, N.; Tirupatikumara, Soundar Rajan; Surana, A.; Gupta, H.; Lee, S.; Narayanan, Vijaykrishnan; Thadakamalla, H.; Brinn, M.; Greaves, M.

2002. 153-158 Paper presented at Proceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design, St. Louis, MO, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Survivability of complex system - Support vector machine based approach

AU - Hong, Y.

AU - Gautam, N.

AU - Tirupatikumara, Soundar Rajan

AU - Surana, A.

AU - Gupta, H.

AU - Lee, S.

AU - Narayanan, Vijaykrishnan

AU - Thadakamalla, H.

AU - Brinn, M.

AU - Greaves, M.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Logistic systems which are inherently distributed, in general can be classified as complex systems. Survivability of these systems under varying environment conditions is of paramount importance. Different environmental conditions in which the logistic system resides are translated into several stresses. These in turn will manifest as internal stresses. Logistic systems can be modeled as a collection of software agents. Each agent's behavior is a result of the stresses imposed. Predicting the agents' collective behavior is of paramount importance to ensure survivability. Analytical modeling of such systems becomes very difficult, albeit impossible. In this paper, we study a supply chain in which a real life scenario is used. We implement the supply chain in Cougaar (Cognitive Agent Architecture developed by DARPA) and develop a predictor, based on Support Vector Machine. We report our methodology and results with real-life experiments and stress scenarios.

AB - Logistic systems which are inherently distributed, in general can be classified as complex systems. Survivability of these systems under varying environment conditions is of paramount importance. Different environmental conditions in which the logistic system resides are translated into several stresses. These in turn will manifest as internal stresses. Logistic systems can be modeled as a collection of software agents. Each agent's behavior is a result of the stresses imposed. Predicting the agents' collective behavior is of paramount importance to ensure survivability. Analytical modeling of such systems becomes very difficult, albeit impossible. In this paper, we study a supply chain in which a real life scenario is used. We implement the supply chain in Cougaar (Cognitive Agent Architecture developed by DARPA) and develop a predictor, based on Support Vector Machine. We report our methodology and results with real-life experiments and stress scenarios.

UR - http://www.scopus.com/inward/record.url?scp=0037004423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037004423&partnerID=8YFLogxK

M3 - Paper

SP - 153

EP - 158

ER -

Hong Y, Gautam N, Tirupatikumara SR, Surana A, Gupta H, Lee S et al. Survivability of complex system - Support vector machine based approach. 2002. Paper presented at Proceedings of the Artificial Neutral Networks in Engineering Conference:Smart Engineering System Design, St. Louis, MO, United States.