Brain Signal Analysis for Mind Controlled Type-Writer Using a Deep Neural Network

The prime objective of this work is to develop a notable methodology for modeling a mind controlled type writing system to cater the needs of individuals suffering from various communication related disorders using EEG signal analysis technique. First, the EEG signals are procured from twelve subjects who were involved in mental utterance of seven vowel sounds. The eLORETA analysis of the acquired signals confirms the involvement of occipital, parietal and pre-frontal lobes for this cognitive activity. The procured signals are then filtered to circumvent the effects of various artifacts and are transferred to a novel deep multilayer perceptron classifier for categorization of seven class labels. Performance analysis undertaken confirms that the proposed classifier is able to distinctly categorize the seven class levels with a very high precision level. A coding mechanism has also been proposed to represent the consonants by the concoction of two vowel sounds segregated by a space. Thus, the proposed scheme can be effectively utilized as a mind controlled type writing system to serve the basic requirements of disabled individuals. Additionally, this technique can also be used in certain military scenarios that demand non-verbal communication as a secure option and in various gaming applications that will aid in exhilarating the player's experience.