北京生物醫(yī)學(xué)工程

基于PCA和Fisher判別分析的鋒電位在線分類算法_________

Online spike sorting with PCA and Fisher discriminant analysis

作者：盧小銀梁振周保琢周逸峰

單位：           中國科學(xué)技術(shù)大學(xué)電子科學(xué)技術(shù)系(合肥230027)    

關(guān)鍵詞：鋒電位；在線分類；主成分分析；Fisher判別分析；模板匹配；神經(jīng)網(wǎng)絡(luò)

分類號：

出版年·卷·期（頁碼）：2013·32·2（122-126）

摘要：

目的大腦神經(jīng)元胞外單細胞動作電位(即鋒電位)的檢測與分類，是研究神經(jīng)系統(tǒng)處理信息機制的關(guān)鍵。常用方法是實驗完成后對記錄到的數(shù)據(jù)進行離線檢測與分類，然而當(dāng)需要在短時完成大量數(shù)據(jù)的處理或無線傳輸時，則需實現(xiàn)鋒電位的在線檢測與分類。方法為實現(xiàn)在線分類，本文在利用主成分分析法(principal component analysis，PCA)和K均值分類法對一定量數(shù)據(jù)進行預(yù)分類的基礎(chǔ)上，提出使用PCA結(jié)合Fisher判別分析的方法，并與基于距離的模板匹配法、BP神經(jīng)網(wǎng)絡(luò)分類法進行了分類效果和算法復(fù)雜度的比較。結(jié)果仿真結(jié)果表明，該方法相對于其它兩種方法在分類效果和算法復(fù)雜度上都具有一定的優(yōu)勢。結(jié)論此方法是實現(xiàn)鋒電位在線分類的不錯選擇。

Objective The detection and separation of neuron action potentials(spikes)is a key of information processing mechanism in the neural system research.Offline spike sorting approaches are currently used to detect and sort action potentials after experiments.Online sorting and detecting algorithms are required when researchers need to analyze or wireless transmit a large number of recordings in a short time.Methods To realize online spike sorting，we propose an algorithm combining Fisher discriminant analysis with principal component analysis(PCA)after performing a preprocessing with PCA and K-means.We test this algorithm and compare the efficiency and complexity with the other two algorithms：template matching based on distance and back propagation neural networks.Results The simulation results indicate that this method has an advantage over the other two methods in both efficiency and complexity.Conclusions This online spike sorting algorithm is effective.

參考文獻：

［1］Lewicki MS. A review of methods for spike sorting：the detection and classification of neural action potentials［J］.Network，1998，9(4):53-78.

［2］Rutishauser U, Schuman EM,Mamelak AN.Online detection and sorting of extracellularly recorded action potentials in human medial temporal lobe recordings，in vivo［J］.Journal of Neuroscience Methods，2006，154：204-224.
［3］Prinz AA, Abbott LF，Marder E.The dynamic clamp comes of age［J］.Trends Neurosci，2004，27:218-224.
［4］Zumsteg ZS, Kemere C，O’Driscoll S,et al.Power feasibility of implantable digital spike sorting circuits for neural prosthetic systems［J］.IEEE Trans Neural Syst Rehabil Eng，2005，13(3):272-279.
［5］Wold S, Esbensen K,Geladi P.Principal component analysis［J］. Chemometrics and Intelligent Lab Syst，1987，2:37-52.
［6］孫即祥. 現(xiàn)代模式識別［M］.2版.北京：高等教育出版社,2008.
Sun Jixiang.Modern pattern recognition［M］.2nd ed. Beijing：Higher Education Press，2008.
［7］史峰，王小川，郁磊，等.Matlab 神經(jīng)網(wǎng)絡(luò)30個案例分析［M］.北京：北京航空航天大學(xué)出版社，2010.
Shi Feng，Wang Xiaochuan，Yu Lei，et al.Analysis of 30 neuron networks cases in Matlab ［M］.Beijing：Beijing Aerospace University Press，2010.
［8］Luca Citi, Jacopo Carpaneto，Ken Yoshida，et al.On the use of wavelet denoising and spike sorting techniques to process electroneurographic signals recorded using intraneural electrodes［J］.Journal of Neuroscience Methods，2008，172:294-302.
［9］Geng Xinling, Hu Guangshu，Tian Xin.Neural spike sorting using mathematical morphology，multiwavelets transform and hierarchical clustering［J］.Neurocomputing，2010，73:707-715.
［10］Rodrigo Quian Quiroga，Spike sorting，Rodrigo Quian Quiroga.Scholarpedia Revision 2007，2(12):3583.
［11］Zhang Puming, Wu Jinyong，Zhou Yi，et al.Spike sorting based on automatic template reconstruction with a partial solution to the overlapping problem［J］.Journal of Neuroscience Methods，2004，135:55-65.
［12］李軍政，伍亞舟.BP網(wǎng)絡(luò)與復(fù)雜疾病相關(guān)的SNPs數(shù)據(jù)分析［J］.北京生物醫(yī)學(xué)工程，2011,30（5）：543-545.
Li Junzheng，Wu Yazhou.Back-propagation neural network and the analysis of complex disease-related SNPs［J］.Beijing Biomedical Engineering,2011,30（5）：543-545.
［13］Quiroga RQ, Nadasdy Z，Ben-Shaul Y.Unsupervised spike detection and sorting with wavelets and super paramagnetic clustering［J］.Neural Comput，2004，16:1661-1687.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

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