MSc Semester Project
Prof. Dr. Touradj Ebrahimi
Assistant: Ashkan Yazdani
June 17, 2011
High speed EEG signal processing is of significant importance in brain-computer interface (BCI) systems that are developed for real-time communication. To this end, many efforts have been focused to reduce the dimension of the feature vectors after the feature extraction stage and subsequently to speed up the processing.One the other hand, one can contemplate the recorded EEG single trials before feature extraction, and evaluate the time period in which the corresponding EEG signals convey maximum information, which can be used for detection or classification. According to the information theory, entropy can be a powerful tool for this evaluation. A method, namely wavelet entropy can be used to calculate the entropy of signals in short duration intervals. The aim of this project is to detect the information maximization time in EEG signals during different mental tasks and/or different emotions and to use the corresponding EEG segments to evaluate the overall performance of the system and compare the result with previous researches. There is no need to acquire data for this project and we will use a dataset, which is available.
- Studying state of the art for measuring information maximization time (literature of information theory)
- Studying state of the art for univariate measuring instantaneous information of a signal, using multi resolution such as DWT, EMD, etc
- Studying the 3. For Multivariate mode.
- Implementing the selected methodology.
- Studying an available dataset and state of the art methodology to analyze it. (Anderson Dataset )