supervised by dr Sarah Nabil and Eng Radwa Samy PRESENTED BY Amr Hamdi Hassan Hamdy Hossam Mohamed Philip Naguib 1 Introduction 12 How do we control our bodies Approximately 185000 amputations occur in the United States each year1 ID: 1046887
Download Presentation The PPT/PDF document "Assistive limbs: Using MYO armband" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
1. Assistive limbs: Using MYO armbandsupervised by dr. Sarah Nabil and Eng. Radwa SamyPRESENTED BY: Amr Hamdi, Hassan Hamdy, Hossam Mohamed, Philip Naguib1
2. Introduction 1/2How do we control our bodies?Approximately 185,000 amputations occur in the United States each year[1].In 2009, hospital costs associated with amputation totaled more than $8.3 billion[2].2
3. Introduction 2/2MYO Armband.EMG signals.MYO Sensors.8 Channels.33
4. Why MYO?Portability.Easy to use.Real-time.Bluetooth.Very limited power supply. 4
5. Problem StatementDetection and IMPROVEMENT THE CLASSIFICATION ACCURACY of EMG signals to move the prosthetic arm at REAL-TIME. 5
6. Related Work 1/3Classified by (KNN) and Extract features by (RMS).Pros: 10 movementsCons: it uses electrodes which is not portableAlso it’s not programmable6Toward improved control of prosthetic fingers using surface electromyogram. [5]
7. Related Work 2/3Bebionic Arm.[4]Founder, Otto bock.Programmable.7
8. Related Work 3/3Classification of Finger Movements for the Dexterous Hand Prosthesis Control With Surface ElectromyographyThe paper is trying classify hand movements Uses only adhesive electrodes88
9. Market Motivation PortabilityAdding new movements.9
10. Motivation 1/410
11. Motivation 2/411
12. Motivation 3/412
13. Motivation 4/413
14. System Overview 1/4Collect Data.8 Channels signals.Preprocessing.RMS, MAV.Remove noise.Send signals to cloud.1414
15. System Overview 2/4Receive signals.Processing unit.Classify signals.CNN, KNN, SVM.Increasing accuracy.1515
16. System Overview 3/4Receive movement.Render move.Misclassification.Feedback.Profiling.1616
17. System Overview 4/417
18. ChallengesClassification (Neural Network).Huge Datasets to process.Build Dataset.18
19. Expected ContributionApplying software on Realtime.Increase the accuracy of classification.Integration.User customization19
20. Wireframe 1/320
21. Wireframe 2/321
22. Wireframe 3/322
23. Demo23
24. Questions?24
25. Thanks25
26. References[1]Owings M, Kozak LJ, National Center for Health S. Ambulatory and Inpatient Procedures in the United States, 1996. Hyattsville, Md.: U.S. Dept. of Health and Human Services, Centers for Disease Control and Prevention, National Center for Health Statistics; 1998.[2]HCUP Nationwide Inpatient Sample (NIS). Healthcare Cost and Utilization Project (HCUP). Rockville, MD: Agency for Healthcare Research and Quality; 2009.[4]http://bebionic.com [5]Khushaba, R.N., Kodagoda, S., Takruri, M. and Dissanayake, G., 2012. Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals. Expert Systems with Applications, 39(12), pp.10731-10738.26
27. Class diagram 1/227
28. Class diagram 2/228
29. Use case29
30. Functional Requirement 30
31. Non Functional Requirements31
32. Design Patterns32