Computer Vision And Pattern Analysis Laboratory Home Page  Home
People  People
Publications  Publications
Publications  Databases
Contact Information  Contact
Supported Research Projects  Supported Research Projects
Research Activites  Research Activites
Research Groups
SPIS - Signal Processing and Information Systems Lab.SPIS - Signal Processing and Information Systems Lab.
Medical Vision and Analysis Group  Medical Research Activities
Biometrics Research Group  Biometrics Research Group
SPIS - Signal Processing and Information Systems Lab.MISAM - Machine Intelligence for Speech Audio and Multimedia.
Knowledge Base
  Paper Library

Development of Electroencephalography (EEG) Signal Analysis Techniques for Brain Computer Interface (BCI) Systems

Project Team
  • Ali Ozgur Argunsah
  • Aytul Ercil
  • Mujdat Cetin
  • Ali Baran Curuklu (Malardalen University)
  • Zubeyir Bayraktaroglu (Istanbul University)

ContactAli Ozgur Argunsah Send e-mail
Project Description
Electroencephalography (EEG) based Brain-Computer Interface (BCI) systems are a new development in the field of applied neurophysiology. These systems are being developed in order to enable people who cannot use their motor functions, such as Amyotrophic Lateral Sclerosis (ALS) and Tetraplegic patients, to control some computer based devices. Currently the most important application areas of BCI systems are: to facilitate the communication of ALS and paralyzed patients with their environments; and to enable people with spinal cord injuries to physically manipulate their surroundings by controlling neuroprostheses. This new approach has been made possible thanks to progress in EEG analysis and in information technology which has led to a better understanding of psychophysical aspects of the EEG signals. BCI systems enable information flow the brain directly to the outside world. For widespread use of brain signals for such objectives, effective signal analysis and patterns recognition techniques are needed.

In this project, our objective is to develop new signal analysis and pattern recognition algorithms based on statistical graphical models, and to demonstrate the effectiveness of these algorithms both on standard data sets and on the data collection and BCI system we will set up. The techniques we are going to develop will be based on representation of the temporal and the spatial structure of EEG signals as well as the relationships between mental activity and the collected data by statistical models which are accurate, but at the same time not too complex. This aspect forms the most important superiority of our approach over existing methods. We will learn such graphical models by using machine learning techniques that take into account neuro-anatomical constraints as well. We will then take advantage of these learned models in the pattern recognition process through a Bayesian approach. We expect that our approach will have the following advantages over existing techniques: recognizing larger numbers of classes of mental activity; obtaining similar performance with less data (shorter temporal observations or smaller number of electrodes), robustness against low quality or missing data.

Below you will see a guy who is trying to move the cursor right or left by using his brain waves recorded from his scalp. The guy is performing imaginary hand movement either right or left.

Resulting Papers
In the framework of the "Development of Electroencephalography (EEG) Signal Analysis Techniques for Brain Computer Interface (BCI) Systems" project, the following papers are published:

Home Back Make a Comment