ECE-10: 1st International Conference on Electrical and Computers Engineering
Cairo ,Egypt
New Modular Strategy For Action Sequence Automation Using Neural Networks And Hidden Markov Models
Mohammad A. Taher, Mostapha Abdeljawad
Abstract
The present proposes a new strategy for action sequence automation based on artificial neural networks (ANNS) and hidden Markov models (HMMS). Action sequence automation is achieved through 2 consecutive modules. The first is a target generation module which uses an ANN to predict, given a current state image, the “should be” coming state images if the action sequence is proceeding in correct tracks. The second module is the Hidden Markov Model (HMM) action sequence generator, which given a sequence of states, produces the most probable related actions. The proposed strategy is illustrated through an example
of an automated welding system
ليست هناك تعليقات:
إرسال تعليق