摘要
目的研究睡眠-清醒状态下大脑血氧变化特性,探讨基于功能近红外光谱深层次信息识别两状态的可行性。方法采用便携式功能近红外设备（波长849 nm、757 nm）测量了6名年轻（20~26岁）男性志愿者静止躺卧姿势下睡眠-清醒状态大脑前额位置6通道的功能近红外谱（f NIRs）数据,计算得到反映前额叶血氧水平变化的氧合血红蛋白（HbO_2）均值、心动信号和Burg功率谱等共计36个生理特征,并用支持向量机（support vector machine,SVM）分类器建立了清醒与睡眠两个状态的识别模型。结果在清醒与睡眠过渡阶段大脑前额叶HbO_2均值水平呈下降趋势,心动信号频率在睡眠由浅入深过程中也呈下降趋势;睡眠时功率谱中呼吸波与心动强度均比清醒时有所下降（符合正常睡眠呼吸变缓、心动减弱规律）;睡眠-清醒状态的平均分类识别准确率可达90%。结论基于功能近红外光谱信息检测实现人体静止躺卧姿势下睡眠与清醒状态的自动化识别具有技术可行性,对在轨航天员空间作息评估与规划具有实际应用价值。
Objective To study the brain oxyhemoglobin changes and the feasibility for near-infrared spectroscopy to distinguish sleep-wake state. Methods The portable near infrared（ wavelength 849 nm,757 nm） equipment was used to measure the changes of oxyhemoglobin（ Hb O2） and deoxyhemoglobin（ Hbr） from 6Channels on the prefrontal cortex for wake-sleep state in six subjects（ 20 ~ 26 years old） lying on bed. Total36 Physiological features including means,power spectrum and cardiac signal were extracted as the sensitive features for wake-sleep state. Then the support vector machine（ SVM） classifier recognition model was established by these features. Results Obvious decrease of oxy-hemoglobin and power of respiratory and cardiac signal in f NIRs signal were found during the transition from wake to sleep（ In accordance with respiration and heart beat slowing down when sleeping in our daily life）. An average of 90% classification accuracy was reached. Conclusion The feasibility of automated detection of the wake-sleep state in people with lying posture using the f NIRs was preliminarily confirmed in this paper. It is valuable to schedule and assess the work and rest state of astronauts in space.
作者
张朕
焦学军
潘津津
姜劲
曹勇
杨涵钧
徐凤刚
Zhang Zhen Jiao Xuejun Pan Jin- jin Jiang Jin Cao Yong Yang Hanjun Xu Fengang.(National key Laboratory of Human Factors Engineering, China Astronaut Research and Training Center, Beijing 100094, China)
出处
《航天医学与医学工程》
CAS
CSCD
北大核心
2016年第5期347-352,共6页
Space Medicine & Medical Engineering
基金
中国航天员科研训练中心国家重点实验室资助课题(9140C770208150C77320
2012SY54B1701)
国家重点实验室自主课题(HF2011ZZA01
HF2011ZZB02)
关键词
功能近红外光谱
光谱成像
信息处理
清醒-睡眠检测
functional near-infrared spectroscopy
spectral imaging
signal processing
wake-sleep detection
