摘要
功能性近红外光谱技术(fNIRS)是一种可用于探测大脑皮层血红蛋白浓度变化的光学成像技术,在无创脑机接口领域备受瞩目。然而,国内的近红外设备研究起步晚,价格昂贵且不易便携。为此,基于近红外光谱技术(NIRS)的检测原理,设计一种软硬件完备的便携式系统,以解决脑血氧信号微弱难以采集和头部结构复杂设备难以佩戴的问题。本文研究设计心算实验范式,并进行多人实验,运用支持向量机(SVM)算法对心算状态和休息状态进行分类,分类精度最高可达82.86%,平均精度为65.12%。结果表明,该系统可用于表征脑活动检测。
Functional near-infrared spectroscopy(fNIRS)is an optical imaging technique that can be used to detect changes in hemoglobin concentration in the cerebral cortex and attracts much attention in the field of non-invasive brain-computer interface.However,the research on near-infrared devices in China started late,and they are expensive and not easily portable.Therefore,based on the detection principle of near-infrared spectroscopy(NIRS),a complete set of software and hardware portable systems is designed to solve the problems that weak brain oxygen signal is difficult to collect and it is difficult to wear because of complex head structure.A mental arithmetic experimental paradigm is designed,and multi-person experiments are carried out,and the support vector machine(SVM)algorithm is used to classify the mental arithmetic state and the rest state,with a classification precision of up to 82.86%and an average precision of 65.12%.The results show that this system can be used to characterize and detect brain activity.
作者
李国楠
罗海军
谢惜如
范鑫燕
王康宇
李忠洪
LI Guonan;LUO Haijun;XIE Xiru;FAN Xinyan;WANG Kangyu;LI Zhonghong(Key Laboratory on Optoelectronic Functional Materials,College of Physics and Electronic Engineering,Chongqing Normal University,Chongqing 401331,China;National Center for Applied Mathematics in Chongqing,Chongqing Normal University,Chongqing 401331,China)
出处
《传感器与微系统》
北大核心
2025年第12期98-102,共5页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(51507023)
重庆市自然科学基金(面上项目)资助项目(cstc2020jcyj-msxmX0726)
重庆市教委科学技术研究项目(KJZD-K202100506)。
关键词
近红外光谱技术
血氧浓度变化
脑活动
便携式
NIRS
changes in blood oxygen concentration
brain activity
portability
