EEG based hearing threshold determination using artifical neural networks

Electroencephalogram (EEG) based hearing level determination is most suitable for persons who lack verbal communication and behavioral response to sound stimulation. Auditory evoked potentials (AEPs) are a type of EEG signal emanated from the scalp of the brain by an acoustical stimulus. AEP response reflects the auditory ability level of an individual. In this paper, AEP signals were generated at fixed acoustic stimulus intensity in order to determine the hearing perception level of a person. Spatio-temporal domain features of three distinct bands were extracted from the recorded AEP signal. Feedforward neural network models were employed to classify the normal hearing and abnormal hearing level of a person. The maximum classification accuracy of the developed neural network model was observed as 95.6 per cent in distinguishing the normal hearing and abnormal hearing person.