普适环境下基于脑电的身份及上下文状态识别

EEG-based individual and context recognition system in ubiquitous environment

为了研究基于脑电的身份识别的具体实现,并满足用户对于普适和上下文状态感知的需求,提出了一种基于脑电的身份及上下文状态识别系统的实现方案.针对一局域范围内身份识别的普适化需求(如各接口身份验证),提出通过采集脑电、信号去噪、特征提取、模式识别各模块进行身份及上下文状态识别方法的普适化实现方案.并设计了具体实验来测试该系统.通过实验采集到5个受试者安静闭眼、听音乐闭眼和玩游戏后闭眼3种上下文状态的脑电信号,分别得到96.43%的身份识别正确率和92.31%的上下文状态识别正确率,证实了此方案的可行性.

In order to implement electroencephalography（EEG）-based individual identification system in ubiquitous environment,as well as to meet the requirements of contextual state awareness,we propose an EEG based individual and context recognition system implementations.Aiming at fulfilling ubiquitous demands of individual identification system in the certain scope（such as the interface to authentication）,an EEG-based individual and context recognition system in ubiquitous environment is presented which includes EEG collection,signal de-nosing,feature extraction and pattern recognition.In order to validate the system,the experiments involving five subjects and three contextual states are conducted.The accuracy of individual identification is 96.43% and the accuracy of contextual state recognition is 92.31%,which confirms the feasibility of this plan.