Loading...

Human Motion Imitation and Learning It by Fuzzy Elastic Matching Machine

Noorafkan, Salman | 2015

613 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 47334 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Bagheri Shouraki, Saeed
  7. Abstract:
  8. In this thesis, the goal is movement recording by observer and learning it to Fuzzy Elastic Matching Machine (FEMM). For this purpose, first using the camera (Microsoft LifeCam HD-3000), the information specified on the man, taken during the move. After preprocessing performed on the data, Data on each node of the FEMM the classified and is given to special FEMM for that movement and the FEMM to be trained by adaptive neuro fuzzy inference system. During each iteration of training, Sensitivity of FEMM for training new movement information is reduced because the FEMM updated correctly. In test part, one movement among all movements that training in all FEMMs is selected and is done by different speed. System detect movement and the FEMM of this movement. If selected FEMM is correct then training it again. But if incorrect then correct FEMM is detected for system and correct FEMM is trained. In this case system has a punnishment. Number of all FEMMs is 5. Each FEMM has 5 nodes (state) and each node has 3 mixtures. Input number is 4 and each input dimension has 3 membership function in FEMM system. Number of data for training is different because speed of mivement is variable
  9. Keywords:
  10. Adaptive Neuro-Fuzzy Inference System (ANFIS) ; Mixture Model ; Moving Person ; Fuzzy Elastic Matching Machine ; Membership Function

 Digital Object List

 Bookmark

No TOC