Study of Electroencephalograph-Based Evaluation Method of Car Sound Quality

Abstract

Abstract Those methods that are applied to evaluate car sound quality by means of the scoring mode cannot guarantee the universality of results. Some studies have shown that the sound-induced change of electroencephalograph (EEG) can reflect human cerebral activities and mental perceptions. Thus, EEG is introduced here to evaluate the car sound quality, and a new method is put forward to map the powerful sound quality on account of EEG-based physiological acoustic index (EPAI). Twelve types of EEG features are selected in views of time and frequency domains and entropy feature to establish the feature matrix, and the difference of car sounds with the powerful sound quality are identified by means of five classifiers. Then, the correlation between the powerful sound quality and 12 types of EEG features is further analyzed to screen out the effective EEG features that are strongly related to the powerful car sound quality. Subsequently, seven EPAIs are defined by means of regression model based on three effective EEG features, which are the second-order difference (SOD), power spectral density (PSD) of gamma (PSD_γ), and differential entropy (DE), respectively. Our results show that the support vector machine (SVM) and linear discriminant analysis (LDA) models can be applied to effectively identify the difference of powerful car sounds, and the correlations between SOD, PSD_γ, and DE and the powerful sound quality are high, which are up to 0.86, 0.88, and 0.85, respectively, and our EPAIs 1, 2, and 4 can map the powerful car sound quality where the EPAI 4 results in the best evaluation effect. It is also proved that our EPAIs can reflect the subjective perception of participants under stimulation of the powerful sound quality, and EEG can be used as an evaluation method of car sound quality.