51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频

目的 為抑制高強(qiáng)度背景噪聲及信號(hào)疊加的干擾，提高峰電位的檢出率和分類的正確性，本文提出一種新的無監(jiān)督方法。方法 首先，應(yīng)用數(shù)學(xué)形態(tài)學(xué)的復(fù)合操作對(duì)信號(hào)進(jìn)行降噪，采用定閾值提取峰電位。然后，小波變換和核主成分分析法(kernel principal components analysis,KPCA)相結(jié)合，對(duì)已提取的峰電位波形進(jìn)行特征提取。最后，用改進(jìn)的最小距離法實(shí)現(xiàn)峰電位分類。結(jié)果 仿真實(shí)驗(yàn)結(jié)果表明，此方法對(duì)于不同噪聲強(qiáng)度的信號(hào)，峰電位檢出率達(dá)94%，總分類正確率91%以上，其中大量疊加信號(hào)的分類正確率88%以上。結(jié)論 本方法能在有效抑制噪聲的基礎(chǔ)上，準(zhǔn)確提取峰電位并有效分類。

［1］Quiroga RQ.Spike sorting,Rodrigo Quian Quiroga［J］. Scholarpedia Revision，2007，#377642(12):3583.
［2］Lewicki MS. A review of methods for spike sorting:the detection and classification of neural action potentials［J］.Network,1998,9(4):53-78.
［3］Zhang PM,Wu JY,Zhou Y,et al. Spike sorting based on automatic template reconstruction with a partial solution to the overlapping problem［J］. J Neuroscience Methods,2004,135(1-2):55-65.
［4］James CJ,Hesse CW. Independent component analysis for biomedical signals. Physiol Meas,2005,26(1):R15-19.
［5］Xu GH,Wang J,Zhang Q,et al.A spike detection method in EEG based on improved morphological filter［J］.Computers in Biology and Medicine，2007,37：1647-1652.
［6］Kim KH,Kim SJ.A wavelet based method for action potential detection from extracellular neural signal recording with low signal-to-noise ratio［J］. IEEE Transactions on Biomedical Engineering, 2003,50(8):999-1011.
［7］Lu CD,Zhang TY,Du XZ,et al.A robust kernel PCA algorithm,proceedings of the third international conference on machine learning and cybernetics［C］.Shanghai:［s.n.］,2004:26-29.
［8］趙峰,張軍英.一種KPCA的快速算法［J］.控制與決策,2007,22(9):1044-1048.
Zhao Feng,Zhang Junying. Fast algorithm about KPCA［J］. Control and Decision,2007,22(9):1044-1048.
［9］汪增福.模式識(shí)別［M］.合肥:中國(guó)科學(xué)技術(shù)大學(xué)出版社,2010.
［10］Quiroga RQ,ZNadasdy,Ben-Shaul Y.Unsupervised spike detection and sorting with wavelets and super paramagnetic clustering［J］.Neural Comput，2004（16）:1661-1687.