1 / 19

BCI Brain Computer Interface

BCI Brain Computer Interface. by Omar Nada & Sina Firouzi. Introduction. What is it A communication channel between brain and electronic device Computer to brain/Brain to computer Why we need it Medical purposes Repairing eyesight, hearing, movement of body parts

tilden
Download Presentation

BCI Brain Computer Interface

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. BCIBrain Computer Interface by Omar Nada & Sina Firouzi

  2. Introduction • What is it • A communication channel between brain and electronic device • Computer to brain/Brain to computer • Why we need it • Medical purposes • Repairing eyesight, hearing, movement of body parts • Entertainment and multimedia communications • Toys, video games, activity in virtual reality environments, controlling devices with thought, synthetic telepathy • Military • Mood control , commanding and telepresence • How does it work • Algorithms are used to translate brain activity into control signals • Brain can handle signals generated by electronic devices

  3. Overview Source: wingsforlife.com

  4. How does it work • Brain’s electrical activity produced by firing of electrically charged neurons is observed by sensors • Invasive sensors • Electrodes are implanted directly into gray matter • High quality of signals, risk of scar-tissue • Partially invasive • Electrodes are implanted inside skull but not into gray matter • Lower quality, less risk of scar-tissue • Non-invasive • Signals are observed from outside the skull • Low quality as skull dampens signal, no surgery, no scar-tissue, safest method • Electroencephalography (EEG) by observing the wave of ions released by neurons • Magnetoencephalography (MEG) by observing magnetic fields produced in brain • Functional magnetic resonance imaging (FMRI) • This information is translated using algorithms and used by electronic devices and vice versa

  5. Using Invasive Sensors

  6. BCI Projects • Assist Arm Robot • Carleton University • BCI + Assist • Berlin Brain-Computer Interface • Health Care

  7. 1) Assist ARM Robot • Early phase One degree of freedom Assist Arm • Uses nerves and force sensor as input • Assist in a desired motion ( for recovery) MEG(using electrodes) Biceps & triceps Projected Motion impedance control schema Motion(force sensor) Up & Down directions

  8. Assisted Movement force sensor electrodes Initial movement Assisted movement

  9. Challenges • Same group muscles can control different joints • Body fat, muscle mass, muscle fatigue affect measurements • Different people give different values ( like PWM) • Lack of volunteers!!!! (especially for invasive methods) • Guessing the user Intensions!

  10. Work Arounds / Solutions • Session Calibration • Using min and max values of voltages • Muscle Group Calibration • Run the above technique for all the group muscles used for readings • THEN: Work relatively • Use the session and group muscle boundaries to predict user intention

  11. 2) Berlin BCI • The Berlin Brain-Computer Interface: EEG-based communication without subject training Benjamin Blankertz, Guido Dornhege, Matthias Krauledat, Klaus-Robert Müller, Volker Kunzmann, FlorianLosch, Gabriel Curio • Non-invasive • Key features • Use of well-established motor competences as control paradigms • High-dimensional features from 128-channel EEG • Advanced machine learning techniques

  12. 2) Berlin BCI • Establishing a BCI system based on motor imagery that works without subject training • ‘Let the machine learn’ • System automatically adapts to the specific brain signals of each user by using advanced techniques of machine learning and signal processing • It is possible to transfer the results obtained with regard to movement intentions in healthy subjects to phantom movements in patients with traumatic amputations. • High information transfer rates can be obtained from single-trial classification of fast-paced motor commands

  13. 3) Health Care • Health care example • Repairing damaged hearing • Sounds are received by an external device and signals are sent to brain • Repairing damaged eyesight • A camera sends signals to brain • Helping people with spine injuriesand paralyzed limbs by electrically stimulating muscles • Moving paralyzed body parts with help of robotic parts

  14. 3) Health Care • Replacing damaged or lost body parts • Mechanical hands, fingers. • Helping people with severe paralysis to communicate with outside world using a computer. • Restore speech • Patient concentrates on a letter and computer receives and pronounces it

  15. Feasible Future • What is in research • Are people able to willingly fire specific neurons in real-time? • Images seen by human eyes have been recorded in black and white. Recording color images is in research • Recording dreams and thoughts • What is coming out soon • Affordable non invasive sensors • Calibration using heart rates ( more accurate results)

  16. Omar’s view of the future • BCI • Better control algorithm to decode the brain activities (cheap non invasive) coming to reality • Check out TED video emotivby Tan Le • Application • ‘HandsFree’ Driving • Thinking Pattern Authentication

  17. Sina’s view of the future • Virtual reality • Being able to interact with others in a virtual 3D environment without using muscles or mouse • Using electronic devices without touch or any muscle movement • Well functioning moving body parts • Mood control • Sending signals to your brain can improve your mood

  18. Conclusion • BCI = Brain + Computer + Communication Channel • BCI Applications • Carleton Assist ARM • Berlin BCI • Health applications • How we view the future from the BCI lens

More Related