Control of bionic arm using ICA-EEG

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.

[1]  S. S. Poorna,et al.  Classification of EEG based control using ANN and KNN — A comparison , 2016 .

[2]  Gary E. Birch,et al.  Online Removal of Eye Movement and Blink EEG Artifacts Using a High-Speed Eye Tracker , 2012, IEEE Transactions on Biomedical Engineering.

[3]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[4]  Ganesha Udupa,et al.  Design and manufacture of 3D printec myoelectric multi-fingered hand for prosthetic application , 2016, 2016 International Conference on Robotics and Automation for Humanitarian Applications (RAHA).

[5]  Aasim Raheel,et al.  Real time text speller based on eye movement classification using wearable EEG sensors , 2016, 2016 SAI Computing Conference (SAI).

[6]  Francisco Cuellar,et al.  Hybrid BCI system to operate an electric wheelchair and a robotic arm for navigation and manipulation tasks , 2016, 2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO).

[7]  Masaki Nakanishi,et al.  Assessing the effects of voluntary and involuntary eyeblinks in independent components of electroencephalogram , 2016, Neurocomputing.

[8]  Rajesh Kannan Megalingam,et al.  Switch and thought controlled robotic arm for paralysis patients and arm amputees , 2013, 2013 IEEE Global Humanitarian Technology Conference: South Asia Satellite (GHTC-SAS).

[9]  Artem Lenskiy,et al.  Extracting Blink Rate Variability from EEG Signals , 2016, 1603.03031.

[10]  Yasuharu Koike,et al.  Classification of Four Eye Directions from EEG Signals for Eye-Movement-Based Communication Systems , 2014 .

[11]  Antti Savelainen,et al.  An introduction to EEG artifacts , 2010 .

[12]  Wahidah Mansor,et al.  Detection of eye blinks from EEG signals for home lighting system activation , 2009 .

[13]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.