摘要
警觉度是指人集中注意力执行某项任务时所表现出的灵敏程度。为保证生产安全,很多岗位需要对工作人员的警觉度进行估计和预测,如高铁司机和危险品运输司机等。基于脑电和眼电等生理信号的警觉度估计与预测是警觉度研究的一个重要方向,如何提取眼电信号中的警觉度特征是该研究的核心问题之一。本研究应用小波包变换方法从水平眼电中提取不同频段能量的比值,以期找出高相关度的警觉度特征。探讨了水平眼电中16种不同的低高频分段的能量比特征,对特征分别进行了移动平均和线性动力系统去噪处理。实验表明,分段为(0～1.50 Hz)/(1.50～31.25 Hz)的能量比值与警觉度的相关系数最高。35组实验的相关系数平均值为0.742,标准差为0.151,比已有的慢速眼动、快速眼动以及眨眼等11种特征中最好特征的相关系数平均值提高了5.55%,标准差降低了6.62%。
Vigilance refers to the sensitivity when a person concentrates on executing an assignment. To ensure safety, vigilant estimation and prediction is necessary for many kinds of posts, such as high-speed railway drivers and dangerous goods transport drivers. The vigilant estimation and prediction based on physiological signals such as EEG and EOG is an important subject in vigilant research. How to get the be.st vigilant feature is one of the kernel problems. In this article, the wavelet packet transform was applied for extracting energy ratio in frequency domain from horizontal EOG in order to get the features closely related with vigilance. We discussed energy ratio features in 16 different segmentations and adopted moving average and linear dynamic system to denoise the acquired features. Experimental results show that the demarcation at （0 - 1.50 Hz）/ （1.50 -31.25 Hz） is the best condition. From 35 data sets, the average correlation coefficient is 0. 742 and the standard deviation is 0. 151, which is better than the existing 11 features such as slow eye movement, rapid eye movement and blink. The average correlation coefficient increases 5.55% and the standard deviation decreases 6. 62% than the best feature in the literature.
出处
《中国生物医学工程学报》
CAS
CSCD
北大核心
2012年第5期641-648,共8页
Chinese Journal of Biomedical Engineering
基金
国家自然科学基金项目(90820018)
国家重点基础研究发展(973)计划(2009CB320901)
关键词
眼电信号
警觉度
警觉度特征
小波包变换
相关分析
Electrooculography
vigilance
vigilant feature
wavelet packet transform
correlation analysis
