410 智能系统学报 第5卷 15 一，x重构的v 200 [10]LATASH M L,SCHOLZ J P,SCHONER G.Toward a 10 ·”,*重构的v E150 new theory of motor synergies[J].Motor Control,2007, 11(3):276-308. .100 [11]GHAHRAMANI Z.Building blocks of movement[J].Na- 02 50 0.2 0.40.60.81.0 50200250 tue,2000,407(12):682-683. 时间/s x/mm [12]HOFER J,GRUBER C,SICK B.Biometric analysis of ()协作基元重构的速系t线(b)协作基元重构的轨迹 handwriting dynamics using a script generator model[C]/ 图7重构结果 Proceedings of IEEE Mountain Workshop on Adaptive and Fig.7 Reconstruction results Learning Systems.Logan,USA,2006:36-41. [13]FLASH T,HANDZEL A.Affine differential geometry a- 4结束语 nalysis of human arm movements[J].Biological Cybernet- ic8,2007,96(6):577601. 本文将运动神经控制认知中协作基元的概念引 [14]MUSSA-IVALDI F A,BIZZI E.Motor learning through the 入到手写运动分析过程，研究手写运动数据协作基 combination of primitives[J].Philosophical Transactions: 元合成分析方法，提出了交替迭代的实现策略，是对 Biological Sciences,2000,355(1404):1755-1769. 手写运动数据分析方法的丰富和发展， [15 ]HOLTSBERG A,STERNBY J.Segmentation-based recog- nition:United States,US 2006/0110041 A1[P].2005- 运动协作基元可以看成运动发生过程中具有独 1109. 立生物运动神经控制意义的最小构成单位，手写运 [16]NOVAK K E,MILLER L E,HOUK J C.The use of over- 动协作基元合成分析方法更有助于精细地解析观测 lapping submovements in the control of rapid hand move- 数据背后手写运动发生的模式，这一方式具有相当 ments[J].Experimental Brain Research,2002,144: 的普适性，更符合生物运动神经控制规律.针对手写 351-364. [17]GLASER E M,RUCHKIN D S.Principles of neuronbio- 笔画切分的实验研究结果表明，协作基元合成分析 logical signal analysis[M].New York:Academic Press, 结果能有效揭示相邻笔画可能的重叠连接模式，可 1976:239-245. 进一步应用于模式识别、仿人机器人、辅助运动神经 [18]ROHRER B,FASOLI S,KREBS H I,et al.Movement 损伤康复诊断以及人机交互等领域 smoothness changes during stroke recovery[J].Joural of Neuroscience,2002,22(18):8297-8304. 参考文献： [19]VINJAMURI R.CRAMMOND D J.KONDZIOLKA D.et al.Extraction of sources of tremor in hand movements of [1]WOLPERT D M,GHAHRAMANI Z.Computational princi- ples of movement neuroscience[J].Nature Neuroscience, patients with movement disorders[J].IEEE Transactions on Information Technology in Biomedicine,2009,13(1): 2000,3:1212-1217. 49-56. [2]WINTER D A.Biomechanics and motor control of human [20]DIPIETRO L,KREBS H I,FASOLI S E,et al.Changing movement[M].2nd ed.New York:John Wiley and Sons, 2004:1444. motor synergies in chronic stroke[J].J.Neurophysiology, 2007,98(2):757-768. [3]JENKINS O C,MATARIC M J.Deriving action and behav- ior primitives from human motion data[C]//Proceedings of [21]LEE J,YOON H S,SOH J,et al.Using geometric extre- IEEE/RSJ International Conference on Intelligent Robots ma for segment-to-segment characteristics comparison in and Systems.Lausanne,Switzerland,2002:2551-2556 online signature verification[J.Pattern Recognition, [4]BIZZI E.Motor primitives and rehabilitation[C]//Proceed- 2004,37:93-103 作者简介： ings of Virtual Rehabilitation.Venice,Italy,2007:20-22. 刘敏，女，1976年生，博士研究 [5]SCHOMAKER L.From handwriting analysis to pen-comput- er applications[J].Electronics Communication Engineer- 生，主要研究方向为生物信息处理 ing Journal,1998,10(3):93-102. 6]MARQUARDT C,MAI N.A computational procedure for movement analysis in handwriting[J].Joural of Neuro- science Methods,1994,52(1):39-45 7]PLAMONDON R,DJIOUA M.A multi-level representation paradigm for handwriting stroke generation [J].Human Movement Science,2006,25(4/5):586-607. 王国利，男，1965年生，教授、博士 8]POLYAKOV F,DRORI R,BEN-SHAUL Y,et al.A com- 生导师，德国洪堡学者，中国人工智能 pact representation of drawing movements with sequences of 学会智能空天系统专业委员会委员，主 parabolic primitives[J].PLoS Computational Biology, 要研究方向为信息获取与信息处理 2009,5(7):1-18. 主持完成省部级科研项目6项，获得省 [9]BYE R T.The BUMP model of response planning[D]. 部级科技进步奖2次. Sydney,Australia:The University of New South Wales, 2009