Globus Pallidus Neuron Spike Time Series Prediction Based on Local-region Multi-step Forecasting Model

摘要：

Add-weighted one-rank local-regionmulti-steps forecasting model(AOLMM)isadopted to predict the neuron spikes of MPTPmonkey model of Parkinsons disease(PD).TheAOLMM based on Takens embedding theoryhas been proved as effectively predict manychaotic systems and overcome someshortcomings like Large computational quantityand cumulative error of other chaotic predictionmethods.Many previous studies havedemonstrated the existence of certain neurons inthe thalamus of PD patients especially in theGlobus Pallidus(GP)is closely related with thepathogenesis of tremor.We observed that withappropriate embedding dimension and the propermaximum forecasting step,the AOLMM canwell foretell the dynamical trend of the GPneuron spikes of the MPTP induced monkeymodel of PD.It indictates that AOLMM ispowerful to help us understand the pathologicalmechanism of PD better and clear.

作者: Yan He Jue Wang Qingfeng Wang Guangjun Zhang Julei Wang Weixin Li Mingming Zhang Guodong Gao

作者单位: key laboratory of biomedical information engineering,Ministry of Education,Xian Jiaotong University Department of Neurosurgery,Tangdu Hospital,Xian,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 224-229

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）