Affiliation: Iwate Prefectural University, Japan
Title: Understanding EEG signal for better Brain-Computer Interface and other Applications
Brain Computer Interface (BCI) or Brain Machine Interface (BMI)are devices that facilitate communication or interaction by analyzing electrical signals collected by probes set on the scalp or inserted inside the head touching the brain. Electroencephalography (EEG) is recording of electrical potential on the scalp. Analysis of the EEG to interpret the intention of the user, and use that for communication or maneuvering a machine, is the core idea of BCI.
With the advent of low-noise high-sensitivity probes and cheap powerful computers, collection of brain-signals from multiple electrodes and their analysis in real-time, is possible. This is leading to a lot of attention to the research and development of BCI applications. Not only medical applications (like epileptic seizures, monitoring anesthesia or brain function etc.), but also applications like moving a wheelchair, or communicating using BCI speller, are getting more accurate and affordable. There are entertainment applications too, for those who can not move their limbs.
The main problem with present BCI application tool is the fact that the number of probes needed is many. A better understanding of the EEG signals, generated during various BCI applications, is the key to reduce the number of required probes, and make their use more common.
In this talk, we will first explain how we could reduce the number of probes by designing it for an individual. In other words, by exploiting individual variation, we can optimize the number of probes without sacrificing the quality. In the second part of the talk, we will give a new algorithm, to define individuals delay in acknowledging an external stimulus, i.e., the delay of Event Related Potential P300. An accurate measurement could lead to various applications including diagnosis of the state of brain and prediction of its vulnerability to diseases like dementia or Alzheimer.
Goutam Chakraborty is a Professor and Head of the Intelligent Informatics Laboratory, Department of the Software and Information Science, Iwate Prefectural University, Takizawa, Japan. His main research interests are soft computing algorithms and their applications to solve pattern recognition, prediction, scheduling and optimization problems including applications in wired and wireless networking problems.