Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on...Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.展开更多
In order to achieve the data exchanging and sharing in complex hospital information systems, the patients, the hospitals and the doctors were put into an integration platform, and improve the regional healthcare incor...In order to achieve the data exchanging and sharing in complex hospital information systems, the patients, the hospitals and the doctors were put into an integration platform, and improve the regional healthcare incorporating and collaborating, the operators, such as the patients, the regional healthcare departments and community operators were put an uniform platform, the study focused on the design of common interface based on the EMR （electronic medical records） system so as to get the uniform information from anywhere at anytime. In the hospital, we set up the common interface based on the HL7 （health level seven） criterion to connect the different models and among the regional healthcare departments, we set up the common interface based on the middleware technology to connect the different medical management information systems. The design of common interface based on the HL7 engine integrated the platform of all the hospital models, and middleware completed the collaboration applications among the regional healthcare departments. The common interfaces based on HL7 and middleware satisfied the requirements of data and formed in different medical information systems, and complemented the regional healthcare information sharing by the integration platform. It is a feasible solution that supports the mobile nursing and smarter healthcare by the theory analysis and practice application.展开更多
为提高运动想象脑机接口识别准确率,结合共空间模式(common spatial pattern,CSP)和卷积神经网络(convolutional neural network,CNN)方法,提出一种改进滤波器组共空间模式(filter bank common spatial pattern,FBCSP)和CNN的算法,用于...为提高运动想象脑机接口识别准确率,结合共空间模式(common spatial pattern,CSP)和卷积神经网络(convolutional neural network,CNN)方法,提出一种改进滤波器组共空间模式(filter bank common spatial pattern,FBCSP)和CNN的算法,用于多分类运动想象脑电信号识别任务。信号预处理后,使用包含重叠频带的FBCSP计算空间投影矩阵,数据经过投影得到更有区分度的特征序列。然后将特征序列以二维排列方式输入搭建的CNN模型中进行分类。所提出方法在脑机接口竞赛数据集2a和Ⅲa上验证,并和其他文献方法对比。结果表明,本文方法一定程度上提高了运动想象脑电信号的分类准确率,为运动想象研究提供了一个有效办法。展开更多
基金supported by the National Natural Science Foundation of China under Grant No. 30525030, 60701015, and 60736029.
文摘Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.
文摘In order to achieve the data exchanging and sharing in complex hospital information systems, the patients, the hospitals and the doctors were put into an integration platform, and improve the regional healthcare incorporating and collaborating, the operators, such as the patients, the regional healthcare departments and community operators were put an uniform platform, the study focused on the design of common interface based on the EMR （electronic medical records） system so as to get the uniform information from anywhere at anytime. In the hospital, we set up the common interface based on the HL7 （health level seven） criterion to connect the different models and among the regional healthcare departments, we set up the common interface based on the middleware technology to connect the different medical management information systems. The design of common interface based on the HL7 engine integrated the platform of all the hospital models, and middleware completed the collaboration applications among the regional healthcare departments. The common interfaces based on HL7 and middleware satisfied the requirements of data and formed in different medical information systems, and complemented the regional healthcare information sharing by the integration platform. It is a feasible solution that supports the mobile nursing and smarter healthcare by the theory analysis and practice application.
文摘为提高运动想象脑机接口识别准确率,结合共空间模式(common spatial pattern,CSP)和卷积神经网络(convolutional neural network,CNN)方法,提出一种改进滤波器组共空间模式(filter bank common spatial pattern,FBCSP)和CNN的算法,用于多分类运动想象脑电信号识别任务。信号预处理后,使用包含重叠频带的FBCSP计算空间投影矩阵,数据经过投影得到更有区分度的特征序列。然后将特征序列以二维排列方式输入搭建的CNN模型中进行分类。所提出方法在脑机接口竞赛数据集2a和Ⅲa上验证,并和其他文献方法对比。结果表明,本文方法一定程度上提高了运动想象脑电信号的分类准确率,为运动想象研究提供了一个有效办法。
