Study of Electroencephalograph-Based Evaluation Method of Car Sound Quality

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

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.

Related collections

Most cited references 54

Record: found
Abstract: found
Article: not found

EEG-based emotion recognition in music listening.

Jiunn-Horng Chen, Chi-Yuen Wang, S F Jeng … (2010)

Ongoing brain activity can be recorded as electroencephalograph (EEG) to discover the links between emotional states and brain activity. This study applied machine-learning algorithms to categorize EEG dynamics according to subject self-reported emotional states during music listening. A framework was proposed to optimize EEG-based emotion recognition by systematically 1) seeking emotion-specific EEG features and 2) exploring the efficacy of the classifiers. Support vector machine was employed to classify four emotional states (joy, anger, sadness, and pleasure) and obtained an averaged classification accuracy of 82.29% +/- 3.06% across 26 subjects. Further, this study identified 30 subject-independent features that were most relevant to emotional processing across subjects and explored the feasibility of using fewer electrodes to characterize the EEG dynamics during music listening. The identified features were primarily derived from electrodes placed near the frontal and the parietal lobes, consistent with many of the findings in the literature. This study might lead to a practical system for noninvasive assessment of the emotional states in practical or clinical applications.