基于fNIRs技术的清醒-睡眠状态识别

发布时间：2018-04-22 03:11

  本文选题：功能近红外光谱 + 光谱成像　； 参考：《航天医学与医学工程》2016年05期

【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。
[Abstract]:Objective to study the characteristics of cerebral blood oxygen changes in sleep-wake state and to explore the feasibility of recognizing two states based on functional near infrared spectroscopy (FNIR). Methods A portable functional near infrared device (wavelength 849 nm ~ 757 nm) was used to measure the functional near infrared spectrum (FNIRs) data of 6 channels of brain prefrontal position in sleep awake state in 6 young male volunteers aged 20 to 26 years. The mean value of HBO _ 2, cardiac signal and Burg power spectrum, which reflect the changes of blood oxygen level in prefrontal lobe, were calculated and 36 physiological characteristics were obtained. The recognition model of awake and sleep states was established by using support vector machine (SVM) classifier. Results the mean level of HbO_2 in the prefrontal lobe of the brain decreased during the period of waking and sleep transition, and the frequency of cardiac signal showed a decreasing trend during the process of sleep from shallow to deep. The respiratory wave and cardiac intensity in sleep power spectrum were lower than those in awake (in accordance with the normal sleep breathing bradycardia weakened law and the average classification and recognition accuracy of sleep-wake state can reach 90%). Conclusion it is feasible to realize the automatic recognition of sleep and waking state based on the detection of functional near infrared spectrum information, and it has practical application value for the evaluation and planning of spaceflight space in orbit.
【作者单位】： 中国航天员科研训练中心人因工程重点实验室;
【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)
【分类号】：R740
，

本文编号：1785336