Embedded Files
TELE - SIGNING with BCI
TELE - SIGNING with BCI
objectives
objectives
To assist persons who have physical problems in either arms and wrists, whether due to a disability or an illness, in signing their signature.
To investigate the usage of technologies such as BCI (Brain-Computer Interface).
To apply gadgets like BCI (Brain-Computer Interface) to solve real-world problems.
System OVerview
System OVerview
Tele Signing with BCI : Control it with your head to sign the signature from anywhere at any time.
System : BCI (Unicorn Hybrid Black), Tele Signing Machine, Computer, User
Target : Anyone who want to sign a document online from a remote location, particularly those who have arm or hand problems and are disabled.
Tele - signing
Tele - signing
Tele-signing is a technology that allows users to control a signing machine from a remote location and sign documents. Users simply sign their signatures online via website, and the robot will sign their documents. Only 3 steps!
Login >> Sign >> Run
Scope & time
Scope & time
Tele-signing with BCI : This project combines tele-signing with BCI, allowing the user to think about the signature before the signing machine takes action.
According to the system's diagram, the user must wear the Unicorn Hybrid Black while focusing on their signatures, after which the system will read the data (brain-wave signals) and convert it into an order of commands, which will then be used to create SVG files using Python, which will then be uploaded to the signing machine's website and the machine will work automatically.
Scope
The system must be able to read data (brain-wave signal) from Unicorn Hybrid Black.
The system can generate SVG files using Python.
Due to the obvious time limitations, the system must be able to draw at least a line, but maybe not the entire signature pattern.
Time Duration : 1 Week (21 - 28 April 2022)
https://www.unicorn-bi.com/
Hardware
Hardware
Unicorn Hybrid Black
Access your brain with Non-invasive BCI Hardware. Wearable, high-quality EEG headset by g.tec medical engineering GmbH.
For more information : https://sites.google.com/mail.kmutt.ac.th/fra500-hri-62340500028/home
The Unicorn Brain Interface acquires the EEG from 8 Unicorn Hybrid EEG Electrodes.
Ref : https://www.youtube.com/watch?v=UVVUJTwvGnw
Software
Software
OpenViBE
Free and Open Source Software for Brain Computer Interfaces and Real Time Neurosciences
http://openvibe.inria.fr/
Supported Architecture
http://openvibe.inria.fr/supported-architectures/
References
References
Choose BCI paradigms
OpenViBE contains demos of all the current major BCI paradigms: P300, SSVEP, Motor Imagery, and neurofeedback. Each current BCI paradigm has its pros and cons. Different paradigms may suit different users better.
Ref : http://openvibe.inria.fr/tutorial-level-1-choosing-the-bci-paradigm/
P300
P300 is a paradigm where the user is requested to focus on something, like a specific letter on a screen, or a specific sound.
Pros: User does not need skill. Good for multiple choice selection.
Cons: The repetitions can become annoying. P300 signal processing can be very sensitive timing: the event markers must be aligned correctly wrt the EEG.
Usual pace: One letter after tens of flashes. Not usually used to mimic continuous control.
SSVEP
Steady-State Visually Evoked Potentials (SSVEP) is an example of a paradigm where elements flicker steadily on a screen, but with different frequencies. For SSVEP, machine learning can be used to learn classifiers that distinguish between the flickering frequencies.
Pros: User does not need skill. SSVEP is less sensitive to time precision than P300.
Cons: The flicker may quickly fatigue the user. It may be difficult to reliably select between more than 3 elements.
Usual pace: One prediction each few seconds of signal. Can be used to mimic continuous control (sliding window).
MI
Motor imagery is based on the user kinetically(!) imagining some limb movement, such as the movement of right or left hand. The user should imagine the “sensation” of the movement
Pros: Motor imagery does not need stimuli (e.g. flicker or flashes). MI is less sensitive to timing than P300.
Cons: Users may need training to become good in motor imagery. The imagining itself can be tiring. Detecting more than 2 classes can be difficult.
Usual pace: One prediction after ~4 seconds of single class imagery. Can be used to mimic continuous control (sliding window).
Neurofeedback
Although not a BCI paradigm in the usual sense, neurofeedback is another way to use the EEG signal. Instead of using the EEG to predict some discrete choice of the user, the signal is processed in some manner and then provided back to the user as feedback. For example, the user may get a display visualizing some measure of relaxation. Subsequently, the user may attempt to improve this measure with the hope that it also trains the underlying state, assuming a connection between the two.
References
References
Relative Papers
BRAIN COMPUTER INTERFACES: AN ENGINEERING VIEW — Niccolò Mora
ElectroEncephaloGraphy (EEG) is the most widely used brain monitoring technique in non-invasive BCI. EEG measures neuronal electrical activity in terms of scalp potentials.
The P300 response is an evoked potential which is elicited when the user recognizes an event he/she considers important. The P300 response can be then observed in the EEG as a positive deflection, time-locked to the attended stimuli (typically delayed by 300 ms)
Performance comparison of a non-invasive P300- based BCI mouse to a head-mouse for people with SCI (Spinal Cord Injury)— Aviroop Dutt-Mazumder & Jane E. Huggins
The head-mouse performed better for all the outcome measures.
A P300-BCI MED (Mouse Emulation Device) is a promising alternative for those who require a MED, but further development would be desirable.
Electrode Montage of a
16-channel EEG cap
3. Critical Decision-Speed and Information Transfer in the “Graz Brain–Computer Interface” — G. Krausz, R. Scherer, G. Korisek, and G. Pfurtscheller
2 different types of motor imagery (movement of the right vs. left hand or both feet) were classified by processing 2 bipolar EEG channels (derived at electrode positions C3 and C4).
The horizontal position was controlled by the BCI-output signal and the trial length was varied by the investigator across runs. A minimal trial length of 2 s is possible with only 1 s of feedback for decision.
3 out of 4 participants had good results after a few runs.
Classification of data was performed by linear discriminant analysis (LDA).
The recommended BCI paradigm for controlling the mouse to sign the signature is P300, but it requires O1 and O2 channels, which Unicorn Hybrid Black missing, thus we choose the second-recommended BCI paradigm instead, MI.
Implementation
Implementation
Due to the current condition of the signing machine, which is not suitable for physical testing, this project's implementation will focus on the programming part, which is split into 2 parts as following,
Read Signal (Brain Wave) by OpenViBE tutorial
Read Brain Waves.mp4Read Raw Signal from BCI
MI Tutorial
Create SVG files using Python ( Bézier curve )
summary & suggestion
summary & suggestion
Summary
Summary
Due to issues with reading data and a third-party program that makes the connection between devices unstable, we were only able to complete two of the three scopes. The final scope must understand the signal pattern from the relevant EEG channel and learn more about each form of BCI paradigm. However, we can achieve the primary goal of learning, understanding, and applying BCI technology.
Suggestion
Suggestion
Unicorn has its own software for reading signals and applying them in a variety of ways, but it requires Unicorn's official license, which is more convenient than using a third-party program.
Take time to practice using BCI equipment and to concentrate or focus, as reading the signal will be easier. Perhaps there should only be one tester because everyone's brain waves are different, therefore it will take less time.
Members
Members
Keedita Chaihetphon 62340500003
Tester & Blogger
Research all of necessary informations
Dharmmasil Pattanasiri 62340500028
Programming part
Research all of necessary informations
Page updated
Report abuse