Auditory evoked potential based detection of hearing loss: A prototype system

Abstract

Hearing loss has been the most prevalent sensory disability throughout the world. Over 275 million people around the world are affected by various hearing related problems. A conventional hearing screening test's applicability is limited as it requires a feedback response from the subject under test. To overcome such problems, the primary focus of this study is to develop an intelligent hearing ability level assessment system using auditory evoked potential signals (AEP). AEP signal is an electrical potential signal elicited from the brain while an auditory stimulus is presented in a time-locked manner. The AEP responses of normal hearing and abnormal hearing subjects were administered to fixed acoustic stimulus intensity in order to detect the hearing threshold level. The detrended fluctuation analysis (DFA) has been used to estimate the fractal values of the normal and abnormal hearing subjects. The extracted fractal features were then associated to hearing threshold level of the subjects. Feed-forward and feedback neural networks are employed to distinguish normal and abnormal hearing subjects. The classification performance of the proposed intelligent hearing ability level assessment system is in the range of 85-90%. This study indicates that mean fractal values of the abnormal hearing subjects are relatively higher while compared with the mean fractal values of the normal hearing subjects.