Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/547596
Title: | Machine learning based enhanced brain computer interface system for classification of motor imagery eeg signals |
Researcher: | Thenmozhi, T |
Guide(s): | Ulagammai, M and Helen, R |
Keywords: | Engineering Engineering and Technology Engineering Electrical |
University: | Anna University |
Completed Date: | 2023 |
Abstract: | Brain Computer Interface (BCI) is a fast-emerging technology to newlineinteract human brain with the computer. BCI serves as a tool for diagnosing and newlinetreatment for neuropsychological and neurophysiological diseases such as newlineDisorder of Consciousness (DOC), schizophrenia, Autism Spectrum Disorder newline(ASD), Attention Deficit Hyperactivity Disorder (ADHD), Stroke, seizures, newlineAlzheimer and Amyotrophic Lateral Sclerosis (ALS). With the help of this newlineassistive technology, people suffering from the above diseases perform their daily newlinetasks independently based on their thought. Motor Imagery BCI works based on newlinethe neural activity produced by the kinesthetic imagination of motor organs. These newlineneural activities can be detected by EEG and brain signals are acquired through newlineelectrodes placed over the scalp. These brain signals are filtered, amplified, and newlinefed into the external assistive prosthetic devices such as wheel-chair, and robotic newlinearms. newlineThe MI based BCI pipeline consists of five stages such as signal newlineacquisition, pre-processing, Feature extraction, Feature selection, and newlineclassification. The brain signals can be acquired from the sensorimotor cortex newlineregion through invasive and non-invasive techniques. Based on the human newlineimagination of motor movements, the user s brain activity is recorded through newlinenon-invasive EEG. In this research, MI based EEG recordings are acquired from newlinetwo public motor imagery BCI competition III-IIIa and IVa datasets. These signals newlineare preprocessed with alpha and beta frequencies and filtered by fifth-order newlineBandpass from artifacts such as eye blinks, muscle disturbances, electrode newlineimpedance, ocular and cardiac artifacts. newline |
Pagination: | xxiii,162p. |
URI: | http://hdl.handle.net/10603/547596 |
Appears in Departments: | Faculty of Electrical Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 236.56 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 5.6 MB | Adobe PDF | View/Open | |
03_content.pdf | 17.43 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 86.11 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 1.18 MB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 728.71 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 886.97 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 420.37 kB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 2.68 MB | Adobe PDF | View/Open | |
10_annexures.pdf | 114.17 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 65.38 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: