Loading...

Design of Intelligent Controller to Improve Goal in Emotional Controller Using Fuzzy Concepts

Amiri Tehranizadeh, Mohammad Amin | 2012

1048 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 42911 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Bagheri Shouraki, Saeed; Beigy, Hamid
  7. Abstract:
  8. Developing algorithms in engineering and decision making systems based on psychological and biological mechanisms is a promising area of research. The challenging part of any psychological or biological system development is its learning necessity to adapt itself to random incidents, inherent in the environment. Goals, as defined in engineering problems, are the performance functions that continuously evaluate the responses of environment. They have a duty of directing the learning system to the desirable state. If the environment is corrupted by a variety of disturbances that cannot be predicted from the outset, adapting the parameter of learning agent is inevitable. In this work, we introduce a new mechanism for learning and improving goal in BELBIC. In order to improve a goal, we make use of a mechanism like actor-critic. Actor-critic is a temporal difference based learning method that uses an interaction mechanism to learn proper action in a state-action space. The main difference of our method, compared with other methods, is that critic in our approach is an actor, and Stress- Evaluator is a critic in actor-critic structure. State-stress value planes are modeled as RLIDS. RLIDS is a reinforcement learning approach based on a powerful concept named Active Learning Method (ALM). Ink drop spread (IDS) is employed as ALM engine in RLIDS method. IDS is a fuzzy modeling algorithm, which expresses multi-input-single-output system as a fuzzy combination of several single-input-single-output systems. In our algorithm, initial goal and its update rule is designed using IDS method. Results show that our approach truly detects stressful actions and directs the goal towards increasing the performance of the overall controller.

  9. Keywords:
  10. Learning ; Decision Making ; Emotion ; Fuzzy Modeling ; Intelligent Controller ; Emotional Controller

 Digital Object List

 Bookmark

...see more