Control of bionic arm using ICA-EEG
| Autor: | Ganesha Udupa, G. Gayathri, G. J. Nair |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Rehabilitation
medicine.diagnostic_test business.industry Computer science medicine.medical_treatment 0206 medical engineering Feature extraction 02 engineering and technology Electroencephalography 020601 biomedical engineering Independent component analysis Orthotic device Support vector machine Statistical classification ComputingMethodologies_PATTERNRECOGNITION Arduino 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Brain–computer interface |
| Zdroj: | 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). |
| DOI: | 10.1109/icicict1.2017.8342749 |
| Popis: | Prosthetic and orthotic devices play a significant role in the lives of physically disabled people. Use of brain computer interface (BCI) in development of prosthetics is an important area of research. Amrita University has developed an advanced and conveniently designed Electroencephalogram (EEG) controlled bionic arm. Ocular signals present in EEG corresponding to coded commands are extracted for performing predefined mechanical tasks. For this purpose the EEG to corresponding eye-blink signals are acquired from the subjects using neuro-headset. Independent component analysis (ICA) of the EEG data was done to extract the commands. Classification techniques-multiclass SVM and LDA are used to classify the commands obtained from ICA data. The accuracy of classification for multiclass SVM is 80% and LDA is 100%. The classified commands are sent to an arduino processor to perform the predefined mechanical tasks of the 3-D printed bionic arm. The intended use of this technology is in the field of rehabilitation and skill development of upper limb amputees. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|