P300 Speller Based ALS Detection Using Daubechies Wavelet Transform in Electroencephalograph

Abstract

The Brain is the main controller of the human body consisting of neurons which generate electrical signals to control the body. Different neurological diseases can cause brain abnormalities such as ALS that affect the electrical activity of the brain which can be seen in the EEG signal. Therefore, these abnormalities can be detected by analyzing the EEG signal. As the Alpha and Beta waves are recorded during the active state of the brain, the effect of abnormalities can be seen in the waves. This study proposes a technique to detect the brain abnormalities and detect ALS syndromes based on Alpha and Beta waves. In this study, the Alpha and Beta waves are extracted from the raw EEG signal by discrete wavelet transformation. Here, the raw EEG signal is divided into several orthogonal wavelets using Doubechis 4 wavelet transform; Alpha and Beta wave frequency components are selected and reconstructed. Then these waves can be compared between different types of ALS patients and normal people based on amplitude and event related potential. The result showed great variation in amplitude as well as event related potential for different ALS patients and normal people. The proposed technique could be used in detecting abnormalities and their severity. It could also help in detecting ALS at a primary stage.