EEG-based driver’s awareness/vigilance monitoring for future car design
Driving with low vigilance becomes a significant factor for traffic accidents. Comparing with other resources, Electroencephalograph (EEG) provides direct and early measure to detect vigilance. Extreme Learning Machine (ELM) as a machine learning technique is used for efficient solutions to generali...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
2016
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/67945 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Driving with low vigilance becomes a significant factor for traffic accidents. Comparing with other resources, Electroencephalograph (EEG) provides direct and early measure to detect vigilance. Extreme Learning Machine (ELM) as a machine learning technique is used for efficient solutions to generalized feed-forward neural networks. Bayesian Extreme Learning Machine (BELM) is another machine learning theory based on ELM but provides a soft labelling for classification. This paper introduces an in-vehicle system to recognize and monitor human vigilance in real-time based on human brain performance. Corresponding warning will be sent to the driver according to different vigilance levels. Experiments for EEG row data collection, ELM and BELM for data training and the method Principle Component Analysis (PCA) for visualization are introduced, followed by a real-time user interface of the system. The paper is to contribute to future car design for driver’s safety. |
|---|