An Improved Approach for Extracting Features and Classifying Motor Imagery EEG Signals Through Machine Learning

Autor: T. Thenmozhi, R. Helen
Rok vydání: 2021
Předmět:
Zdroj: Advances in Automation, Signal Processing, Instrumentation, and Control ISBN: 9789811582202
Popis: The brain–computer interface allows interaction between human brain and a machine. BCI is mainly helpful for disabled persons to do their day-to-day activities independently. Brain can communicate with the machine through EEG (non-invasive method) from user’s brain cortex. This paper focuses on controlling the hand and foot movements based on human’s thoughts. The EEG recordings are taken from datasets of BCI competition III. The electroencephalogram (EEG) signal features are extracted using common spatial pattern combined with power spectral density and Hilbert transform. The classification of signals based on right hand and right foot movement is done by linear discriminant analysis (LDA) method. This proposed method is tested on five healthy subjects, and average accuracy is improved to 85.76%. In future, the classified output is converted into command signals and can able to control the robotic devices such as arm or wheelchair which will assist the people with motor impairment.
Databáze: OpenAIRE