EEG based mind controlled

• Main Author: Wu, Qiu Long
• Other Authors: Xie Lihua
• Format: Final Year Project
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/63594
• Institution: Nanyang Technological University

Brain Computer Interfaces (BCIs) should be one of the most important technological in artificial intelligence. In this project will implement an Electroencephalography (EEG) base BCIs control system by using Filter Bank Common Spatial Pattern (FBCSP) algorithm as a feature extraction method and Extreme Learning Machine (ELM) as a feature classification method. Motor imagery is sensitive for think “left” and “right”. The Common Spatial Pattern (CSP) method is widely use for EEG signal feature extraction. Machine learning ELM method was used for both training and testing stage for classification. The results show 90% accuracy for two classes’ classification “think left” and “think right” and used this two classes’ classification permutation and combination to result output four directions.