Human Brain Signal Analysis using Machine Learning Techniques

Abstract :

Human brain is one of the most wondrous organs that distinguish us from all other organisms. The ability to feel, adapt, reason, remember, make decision and communicate makes human beings intelligent. Human brains are capable of processing billions of bits of information per second with the help of approximately hundred billion neural connections in the brain. The latest trend in unlocking the mysteries of the mind is with the recent advancement in brain-computer interface (BCI) systems. Scientists are emphasizing their research whether BCI can be augmented with human computer interaction (HCI) to give a new aspiration for restoring independence to neurologically disabled individuals. There exist both invasive and non-invasive methods for brain signal acquisition such as electroencephalography (EEG), functional MRI (fMRI), electrocorticography (ECoG), calcium imaging, magnetoencephalography (MEG), functional near- infrared spectroscopy (fNIRS), etc. Electroencephalography signals, which are small amounts of electromagnetic waves produced by the neurons in the brain are one of the most popularly used signal acquisition techniques in the existing BCI systems due to their non-invasiveness, easy to use, reasonable temporal resolution and cost effectiveness compared to other brain signal acquisition methods. Electroencephalography is essential for the diagnosis of epilepsy and useful in characterizing various neurological diseases such as Parkinson’s disease and Alzheimer’s disease. The main objective of this study is to gather information regarding basic structure of the EEG data processing systems and to enhance it with the applications of deep learning with EEG data processing system to unlock the mysteries of human brain. The proposed method is a detailed analysis of electroencephalographic data of both normal and abnormal subjects with respect to various neurological disorders.