Formulation of a Novel Classification Indices for Classification of Human Hearing Abilities According to Cortical Auditory Event Potential signals

Abstract

The classification of brain response signals as per human hearing ability is a complex undertaking. This study presents a novel formulated index for accurately predicting and classifying human hearing abilities based on the auditory brain responses. Moreover, we presented five classification algorithms to classify hearing abilities [normal hearing and sensorineural hearing loss (SNHL)] based on different auditory stimuli. The brain response signals used were the electroencephalography (EEG) evoked by two auditory stimuli (tones and consonant vowels stimulus). The study was carried out on Malaysian (Malay) citizens with and without normal hearing abilities. A new ranking process for the subjects’ EEG data and as well as ranking the nonlinear features will be used to obtain the maximum classification accuracy. The study formulated classification indices (CVHI, PTHIH these classification indices classify human hearing abilities based on the brain auditory responses using features in its numerical values. The K-nearest neighbor and support vector machine classifiers were quite accurate in classifying auditory brain responses for brain hearing abilities. The proposed indices are valuable tools for classifying brain responses, especially in the context of human hearing abilities.