RETRACTED ARTICLE: Application of music in relief of driving fatigue based on EEG signals

Wang, Qingjun; Mu, Zhendong · 2021 · Crossref

DOI: 10.1186/s13634-021-00794-8

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This retracted 2021 study by Wang and Mu investigates the application of music in alleviating driving fatigue, utilizing electroencephalogram (EEG) signals as a primary metric for assessing driver state. Motivated by the significant contribution of fatigue to traffic accidents—accounting for 20–40% of incidents and increasing accident probability by 4–6 times—the research aims to provide a scientific basis for fatigue mitigation strategies. The authors posit that EEG signals offer a timely and accurate method for determining fatigue states, allowing for the implementation of countermeasures such as auditory stimulation. The methodology involved an indoor simulated driving experiment where participants completed four consecutive hours of driving tasks across different road landscape environments, specifically mountainous and grassland roads. EEG data were collected using a Bluetooth headset and subjected to a rigorous denoising process. This preprocessing included a 0.5–40 Hz band-pass filter to remove environmental interference, followed by Variational Mode Decomposition (VMD) and Independent Component Analysis (ICA) to eliminate bioelectrical noise, particularly ocular artifacts. The study analyzed specific frequency bands—alpha (α), beta (β), and theta (θ)—and derived indices such as the (α + θ)/β ratio. Statistical analysis employed linear regression models and Granger causality methods to quantify the relationship between driving time, road conditions, and EEG indicators. The results indicated that music significantly extended the duration of active EEG signals. Drivers exposed to music maintained active EEG states for over two hours, whereas those without music showed active states for approximately 1.5 hours. The study found that EEG signal activity varied by road condition; on both mountainous and grassland roads, the β wave and the (α + θ)/β ratio were highly correlated with driving time. Specifically, β wave activity was negatively correlated with driving time, while the (α + θ)/β ratio was positively correlated. Furthermore, the accumulation of changes in these indicators demonstrated a strong correlation with driving duration, suggesting that these metrics can effectively track the progression of fatigue. The significance of this work lies in its quantification of EEG indices to evaluate driving fatigue under varying environmental and auditory conditions. By demonstrating that music can delay the onset of fatigue-related EEG changes, the study supports the use of auditory interventions in driver assistance systems. The findings provide reference thresholds for distinguishing between awake and fatigued states, contributing to the development of real-time monitoring systems aimed at improving road safety and reducing fatigue-related accidents.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• drowsiness detection algorithms
• music audio mood
• drowsiness

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: physiological data
• Methodological Resource: tool software