An Innovation of Evaluation and Design of Vehicle Acceleration Sound Based on EEG Signals

• Published in: Journal of bionics engineering Vol. 21; no. 1; pp. 344 - 361
• Main Authors: Xie, Liping, Lin, XinYou, Chen, Wan, Liu, Zhien, Zhu, Yawei
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.01.2024
• Subjects: Artificial Intelligence; Biochemical Engineering; Bioinformatics; Biomaterials; Biomedical Engineering and Bioengineering; Biomedical Engineering/Biotechnology; Engineering; Research Article; Vehicle sound design; EEG signal; Brain activity analysis; Adaptive genetic algorithm; Elman model
• ISSN: 1672-6529; 2543-2141
• DOI: 10.1007/s42235-023-00455-6

There is a bottleneck in the design of vehicle sound that the subjective perception of sound quality that combines multiple psychological factors fails to be accurately and objectively quantified. Therefore, EEG signals are introduced in this paper to investigate the evaluation and design method of vehicle acceleration sound with powerful sound quality. Firstly, the experiment of EEG acquisition and subjective evaluation under the stimulation of powerful vehicle sounds is conducted, respectively, then three physiological EEG features of PSD_β, PSD_γ and DE are constructed to evaluate the vehicle sounds based on the correlation analysis algorithms. Subsequently, the Adaptive Genetic Algorithm (AGA) is proposed to optimize the Elman model, where an intelligent model (AGA–Elman) is constructed to objectively predicate the perception of subjects for the vehicle sounds with powerful sound quality. The results demonstrate that the error of the constructed AGA–Elman model is only 2.88%, which outperforms than the traditional BP and Elman model; Finally, two vehicle acceleration sounds (Design1 and Design2) are designed based on the constructed AGA–Elman model from the perspective of order modulation and frequency modulation, which provide the acoustic theoretical guidance for the design of vehicle sound incorporating the EEG signals.