Havlicek M, Jan J, Brazdil M, Calhoun V D
Dept. of Biomedical Engineering, FEEC, Brno University of Technology, Czech Republic.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:8122-5. doi: 10.1109/IEMBS.2011.6092003.
In this paper we describe a deconvolution technique for estimation of the neuronal signal from an observed hemodynamic responses in fMRI data. Our approach, based on the Rauch-Tung-Striebel smoother for square-root cubature Kalman filter, enables us to accurately infer the hidden states, parameters, and the input of the dynamic system. Additionally, we enhance the cubature Kalman filter with a variational Bayesian approach for adaptive estimation of the measurement noise covariance.
在本文中，我们描述了一种去卷积技术，用于从功能磁共振成像（fMRI）数据中观察到的血液动力学反应估计神经元信号。我们的方法基于平方根容积卡尔曼滤波器的劳赫 - 通 - 施里贝尔平滑器，使我们能够准确推断动态系统的隐藏状态、参数和输入。此外，我们用变分贝叶斯方法增强容积卡尔曼滤波器，以自适应估计测量噪声协方差。
