Removal of muscle artifacts from EEG based on ensemble empirical mode decomposition and classification of seizure using machine learning techniques

Abstract

Occurrence of sudden burst of excess electricity in the brain, manifesting as seizure is common phenomenon observed in patients with epilepsy: a neurological disorder that affects approximately 70 million people in the world. The epilepsy mainly divided into two types - Partial and Generalized. Electroencephalograms (EEG) recordings can capture the brain’s electrical signals, but diagnosis of epilepsy and identifying its correct class is time consuming and can be expensive due to the need for trained specialists to perform the interpretation, because of the nature of EEG signal, which normally get contaminated by noises and artifacts (signals other than brain activity), which affects the visual analysis of EEG and impairs the results of EEG signal processing. We present de-noising of EEG signal using Ensemble Empirical Mode Decomposition (EEMD) and classification based on machine learning Technique using MATLAB.

Publication
2017 International Conference on Inventive Computing and Informatics (ICICI)
Kusumika Dutta
Kusumika Dutta
Assistant Professor

Kusumika Krori Dutta, working as Assistant professor in Electrical and Electronics Engineering Department , MSRIT, Bangalore, India. She completed B.E (Electrical Engg) , M.Sc(Engg) by research and pursuing PhD in investigation on neurological disorder. She believes in lifelong learning and is passionate to explore different socio-cultural needs and their solutions through her indagation. Her love towards research, aided her to invent a mathematical formula of pattern based multiplication and patented many products having social utility

Sunny Arokia Swamy Bellary
Sunny Arokia Swamy Bellary
Engineer/Scientist II

EPRI Engineer | AI Enthusiast | Computer Vision Researcher | Robotics Tech Savvy | Food Lover | Wanderlust | Team Leader @Belaku | Musician |