Water J Freeman教授在生理实验的基础上建立了一套基于嗅觉系统的神经网络模型。这套模型运用非线性动力学的方法较好的模拟了人体的嗅觉系统,并能够产生类似脑电的非周期背景信号。利用这个的基于嗅觉系统而建立的模型--K系列模型可...Water J Freeman教授在生理实验的基础上建立了一套基于嗅觉系统的神经网络模型。这套模型运用非线性动力学的方法较好的模拟了人体的嗅觉系统,并能够产生类似脑电的非周期背景信号。利用这个的基于嗅觉系统而建立的模型--K系列模型可以实现模式识别。本文首先从原理上介绍了K系列模型的拓扑结构和数学基础,然后通过实际的计算机数值模拟介绍了KII网络和KIII模型在实现一维序列识别时的方法和结果,简单说明了这个模型在模式识别上的特点。展开更多
Obtaining an electrocorticograms(ECoG)signal requires an invasive procedure in which brain activity is recorded from the cortical surface.In contrast,obtaining electroencephalograms(EEG)recordings requires the non-inv...Obtaining an electrocorticograms(ECoG)signal requires an invasive procedure in which brain activity is recorded from the cortical surface.In contrast,obtaining electroencephalograms(EEG)recordings requires the non-invasive procedure of recording the brain activity from the scalp surface,which allows EEG recordings to be performed more easily on healthy humans.In this work,a technique previously used to study spatial-temporal patterns of brain activity on animal ECoG was adapted for use on EEG.The main issues are centered on solving the problems introduced by the increment on the interelectrode distance and the procedure to detect stable frames.The results showed that spatial patterns of beta and gamma activity can also be extracted from the EEG signal by using stable frames as time markers for feature extraction.This adapted technique makes it possible to take advantage of the cognitive and phenomenological awareness of a normal healthy subject.展开更多
基金supported by the National Natural Science Foundation of China(Nos.60421002 and 60874098)the National High-Tech Research and Development Program(863)of China(No.2007AA042103)
文摘Obtaining an electrocorticograms(ECoG)signal requires an invasive procedure in which brain activity is recorded from the cortical surface.In contrast,obtaining electroencephalograms(EEG)recordings requires the non-invasive procedure of recording the brain activity from the scalp surface,which allows EEG recordings to be performed more easily on healthy humans.In this work,a technique previously used to study spatial-temporal patterns of brain activity on animal ECoG was adapted for use on EEG.The main issues are centered on solving the problems introduced by the increment on the interelectrode distance and the procedure to detect stable frames.The results showed that spatial patterns of beta and gamma activity can also be extracted from the EEG signal by using stable frames as time markers for feature extraction.This adapted technique makes it possible to take advantage of the cognitive and phenomenological awareness of a normal healthy subject.
