The 6th annual IEEE Conference on Automation Science and Engineering
  

CASE 2010 Paper Abstract

Close

Paper MoC2.5

Fereidunian, Alireza (University of Tehran and Power and Water University of Technolog), Boroomand, Farzam (University of Tehran), Zamani, Mohammad Ali (University of Tehran), Jamalabadi, Hamidreza (University of Tehran), lesani, Hamid (University of Tehran), Lucas, Caro (Control and Intelligent Processing Center of Excellence,Universi), afkhami, Saman (Ryerson University)

AAGLMES:A GLM Equipped Adaptive Autonomy Expert System

Scheduled for presentation during the Regular Session "Computational Intelligence" (MoC2), Monday, August 23, 2010, 17:20−17:40, Trinity III

6th annual IEEE Conference on Automation Science and Engineering, August 21-24, 2010, Marriott Eaton Centre Hotel, Toronto, Ontario, Canada

This information is tentative and subject to change. Compiled on September 21, 2017

Keywords Adaptive and Learning Systems, Autonomous Systems, Machine Learning

Abstract

We introduced a novel framework for implementation of adaptive autonomy concept, as well as several techniques for its realization as expert system. Adaptive autonomy means adapting the level of automation to the changing environmental conditions of the automation system. This study presents an expert system realization of adaptive autonomy, using Generalized Linear Models (GLMs), referred to as AAGLMES. The AAGLMES uses GLMs as expert system inference engine. It is implemented to a practical case of electric power utility management automation system. The practical list of environmental conditions and expertsí judgments are used as the expert system database. The paper presents design methodology, implementation, results and discussions. Four types of training sets are developed and their learning performance is investigated for this implementation of GLMs. Evaluation of the results reveals that AAGLMES can acceptably trace the changing environmental conditions, by updating the levels of automation.

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2017 PaperCept, Inc.
Page generated 2017-09-21  05:24:40 PST  Terms of use