ICS Research Seminar on "Efficient Hardware Implementation of a Feature Extraction and Classification Algorithm for Brain Computer Interface (BCI) Signals"
ICS Research Seminar on "Efficient Hardware Implementation of a Feature Extraction and Classification Algorithm for Brain Computer Interface (BCI) Signals" by Alireza Malekmohammadi, Chair for Cognitive Systems, TUM
Abstract: Making a connection between brain and computer, or Brain Computer Interface (BCI) for broad applications in areas such as medical and gaming has caused the subject to one of the most important and attractive issues in recent decades. From the perspective of pattern recognition, BCI is a classification issue that should receive signals that relate to the certain decisions of the brain and then after processing, it is concluded that the person has thought to what decision. Decisions that taken by an individual, is sent from the brain to the body by signals, which is called Electroencephalogram (EEG). The number of these decisions is further, classified it also becomes more difficult. That is why the steps leading to the classification of decisions are very important. In general, parts such as pre-processing, feature extraction, feature selection, feature reduction, and suitable classifier for detecting a decision are needed to solve a BCI problem. Solving BCI problem includes two Phases called train and test sections. In the train part after recording signal and processing BCI steps, the parameters of the test section can be adjusted. In the test part, the new data is recorded and afterward, it is clear that new data belongs to what class according to the parameters in the test section which has been set by train data. To implement this, we need an efficient algorithm. The aim of this project, efficient hardware implementation for a BCI algorithm. Analyzing algorithm and its improvement in the direction an efficient hardware architecture is a part of the activities involved in this project. The proposed algorithm has a better accuracy around 10% compared with other algorithms.
Bio: He received his bachelor’s degree in “Electrical Engineering” from Shahid Beheshti University, Tehran, Iran, in 2013. In 2015, he awarded his M.Sc. degree in “Digital Electronics Engineering” from Sharif University of Technology. During his master, he attended the Brain-Computer Interface (BCI) group, developing an efficient design and hardware implementation of a BCI system based on motor imagery on a Virtex-6 FPGA. From 2017 till 2018, he spent one year as a research assistant at Tuebingen University. His research was about effects of intra- operative monopolar deep brain stimulation of the sub-thalamic nucleus on cortical physiology in Parkinson’s disease.
For more info please visit: http://web.ics.ei.tum.de/~ehrlich/ICS_seminar/index.htm
04. July 2018,16:30h, ICS Karlstraße 45, 2. Floor, seminar room 2026