International Journal of Computer
Trends and Technology

Research Article | Open Access | Download PDF

Volume 1 | Issue 2 | Year 2011 | Article Id. IJCTT-V1I2P11 | DOI : https://doi.org/10.14445/22312803/IJCTT-V1I2P11

Stroke economy approach for constructing complex expert system using multi agent architecture.

U.Chandrasekhar , S.Sahithya.

Citation :

U.Chandrasekhar , S.Sahithya., "Stroke economy approach for constructing complex expert system using multi agent architecture.," International Journal of Computer Trends and Technology (IJCTT), vol. 1, no. 2, pp. 190-194, 2011. Crossref, https://doi.org/10.14445/22312803/IJCTT-V1I2P11

Abstract

In a highly competitive and ever evolving dynamic environment the need for an effective and a highly efficient work force that can reduce various overheads , is massive. This is where a distributed, multi agent architecture comes into play. In th is paper, we propose a decentralized, multi agent architecture that works in a distributed and dynamic environment . It uses stroke economy approach to optimize itself and evolve into an expert system of experts . The aim is to construct a unified mind from several minds, each exp ert in a sub domain. The goal is to achieve variety in task handling approaches and quality output, while optimizing task scheduling process. We also present a learning mechanism which helps individual agents to lift themselves up to the le vel of more expe rienced agents, i n their sub domain. We also aim to minimize the size of system , initially commissioned for that application , optimize transfer of data and schedule tasks effectively , promising a high quality performance.

Keywords

Multi agent architectur e , Distributed AI, Subsumption architecture , Reinforcement learning.

References

[1] Mark Humphrys and Ciaran O’Leary, “Constructing complex minds through multiple authors”, 7tn International conference, SAB’02, August - 2002
[2] Munir Merdan, Vedran Kordic, Alois Zoitl & Aleksandar Lazinica,"Knowledge - based Multi - agent Architecture", IEEE (CIMCA - IAWTIC`06) .
[3] D. Vallejo, J.Albusac, J.J.Castro - Schez, C.Glez - Morcillo, L.Jime ´nez, "A multi - agent architecture for supporting distributed normality - based Intelligent surveillance", Engineering Applications of Artificial Intelligen ce 24(2011)325 – 340 .
[4] Yuanda Cao,Nutao Jiang, Qing Zhou, "A Distributed Multi - agent Cooperative Expert System Tool",Proceedings of I C SP `98 .
[5] Ming Tan, “Multi - Agent Reinforcement Learning: Independent vs. Cooperative Agents”, Proceedings of 10 th International Conference on Machine Learning. 330 - 337 .
[6] Jyi - Shane Liu, Katia P.Sycara, “Multiagent Coordination in Tightly Coupled Task Scheduling”, Proceedings of 1 st International conference on Multi Agent systems, 1996. American Association for AI , 181 - 188.