AI Article Synopsis
- The study introduces a capacitance-based method for recognizing fatigue while driving, which includes four main steps: signal acquisition, pre-processing, blink detection, and fatigue recognition.
- A measurement circuit using the FDC2214 is designed to capture signals, which are then filtered to remove noise before analyzing blink characteristics such as eye closing and opening times.
- The final stage utilizes a BP neural network to assess fatigue levels, achieving a high accuracy rate of 92% in recognizing fatigue across different lighting conditions.
Article Abstract
This study proposes a capacitance-based fatigue driving recognition method. The proposed method encompasses four principal phases: signal acquisition, pre-processing, blink detection, and fatigue driving recognition. A measurement circuit based on the FDC2214 is designed for the purpose of signal acquisition. The acquired signal is initially subjected to pre-processing, whereby noise waves are filtered out. Subsequently, the blink detection algorithm is employed to recognize the characteristics of human blinks. The characteristics of human blink include eye closing time, eye opening time, and idle time. Lastly, the BP neural network is employed to calculate the fatigue driving scale in the fatigue driving recognition stage. Experiments under various working and light conditions are conducted to verify the effectiveness of the proposed method. The results show that high fatigue driving recognition accuracy (92%) can be obtained by the proposed method under various light conditions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3390/s24237633 | DOI Listing |
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11644888 | PMC |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!