Detection of Stress in Human Brain

The essence of the paper is to develop a stress detection mechanism and a stress level indicator circuit for measuring the stress level of human brain using the Electro-encephalogram (EEG) Signal. Signals coming from the frontal lobe of human brain have been used for the measurement of stress. The brain signals of the thirty subjects are recorded while they are solving five mathematical question sets with increasing complexity. We assume that the subjects undergo through five different stress levels i.e. ‘Relaxed’, ‘Less stressed’, ‘Moderately Stressed’, ‘High Stressed’ and ‘Alarmingly Stressed’ while solving these question sets. After that recorded EEG data is processed and features are extracted. We design a feed forward neural network for classifying the stress level in human brain. We prepare a new question set consisting of easy as well as complex numerical questions for testing purpose. We record the EEG data of a subject while solving this question set. We extract six feature values from the processed EEG data of the subject. These data is fed to the designed feed forward neural network. The neural network predicts the stress level and the predicted stress level is indicated in the ‘Stress Indicating’ circuit.