LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1
Azhar, M. H. B.; Badicioiu, A.; Barton, T.
Languages: English
Types: Unknown
Subjects: QA76.75
Brain-computer interface (BCI) controlled systems hold great potential for clinical applications especially in assisting neurologically disabled patients to improve their communication processes [1]. Wearable electroencephalogram devices (EEG) are non-intrusive, meaning they do not require insertion of electrodes into the patient’s brain, and are available “off the shelf” with consumer-grade devices such as the MindWave [2]. While such EEG devices do not possess the same high resolution EEG capabilities of medical grade devices, their affordability does make the technology accessible to new applications, such as robotics control and mood deduction [3], and their wearable nature negates the need for invasive surgery. Campbell et al. [4] investigated the potential for wearable consumer grade EEG in creating a BCI. Their aim was to implement a BCI for simple mobile phone operation, which found that a simple task, winking, could be deduced from raw data with a relatively high accuracy, and with processing being performed on a smartphone device [4]. In doing this several limitations were highlighted with EEG devices, including a poor signal-to-noise ratio, which requires further processing to deduce useful information from raw data. Millan et al. achieved relatively sophisticated control of a mobile robot in a simulated environment with a non-intrusive BCI interface [5]. Combining machine learning with subject-device training, they were able to achieve “almost as efficient as manual control”.\ud The primary objective of our project was to build a prototype hardware system to establish the proof of concept of controlling a robotic system by using a wearable EEG device. A very low-cost Arduino [6] based integrated electronics platform was used to implement the BCI controlled robot. The Arduino platform possesses several advantages, such as their affordability, and the large amount of open source hardware and software modules available. Combining MindWave [2] as the off-the-shelf EEG device with the Arduino platform enabled successful processing of wearer’s attention and mediation levels to be used as commands to control the robot. The levels of attention and mediation were calculated within the Mindwave device and transmitted to Arduino through Bluetooth as serial asynchronous data packets. Successful processing of these packets within Arduino eventually translated raw BCI data into useful commands. At the end, the project could demonstrate a priority based robust BCI control protocol, with further integration of sensor signals to the system.

Share - Bookmark

Cite this article