Kernel SVM Classifiers based on Fractal Analysis for Estimation of Hearing Loss

ENP Engineering Science Journal

article

Mohamed Djemai¹  Mhania Guerti² 

[1] Ziane Achour university;Ecole Nationale Polytechnique

关键词: Auditory evoked potentials;    Hearing Thresholds;    Detrented Fluctuation Analysis;    Grid search;    SupportVector Machine;   

DOI  :  10.53907/enpesj.v2i1.88

学科分类：社会科学、人文和艺术（综合）

来源: Ecole Nationale Polytechnique

【 摘 要 】

Hearing screening consists of analyzing the hearing capacity of an individual, regardless of age. It identifiesserious hearing problems, degree, type and cause of the hearing loss and the needs of the person to propose a solution.Auditory evoked potentials (AEPs) which are detected on the EEG auditory cortex area are very small signals in responseto a sound stimulus (or electric) from the inner ear to the primary auditory areas of the brain. AEPs are noninvasivemethods used to detect hearing disorders and to estimate hearing thresholds level. In this paper, due to the nonlinearcharacteristics of EEG, Detrented Fluctuation Analysis (DFA) is used to characterize the irregularity or complexity ofEEG signals by calculating the Fractal Dimension (FD) from the recorded AEP signals of the impaired hearing and thenormal subjects. This is to estimate their hearing threshold. In order to classify both groups, hearing-impaired andnormal persons, support vector machine (SVM) is used. For comparably evaluating the performance of SVM classifier,three kernel functions: linear, radial basis function (RBF) and polynomial are employed to distinguish normal and theabnormal hearing subjects. Grid search technique is selected to estimate the optimal kernel parameters. Our resultsindicate that the RBF kernel SVM classifier is promising; it is able to obtain a high training as well as testing classificationaccuracy.

【 授权许可】

CC BY-NC-SA