Model selection for the extraction of movement primitives.

Model selection for the extraction of movement primitives.
复制标题

DOI:
10.3389/fncom.2013.00185
复制
发表时间:
2013
影响因子:
3.2
通讯作者:
Giese MA
Giese MA
中科院分区:
医学4区
文献类型:
--
作者:
Endres DM;Chiovetto E;Giese MA

文献摘要

参考文献

被引文献

相似文献

为了从肌电和运动学数据中提取运动基元,已有大量的盲源分离方法被用于电机控制研究。常用的例子有主成分分析(PCA)、独立成分分析(ICA)、消声分离和时变协同模型(d‘Avella and Tresch)。然而,选择这些模型的参数,或者实际上选择模型的类型,通常是以启发式的方式完成的,既受结果预期的驱动,也受数据的驱动。我们提出了一种客观标准,允许选择模型类型、基元数量和时间光滑性先验。我们的方法是基于对给定盲源分离模型参数的后验分布的拉普拉斯近似,该模型被重新表述为贝叶斯生成模型。我们首先在地面真实数据上验证了我们的准则,表明它的性能至少与传统的模型选择准则[贝叶斯信息准则,BIC(Schwarz)和Akaike信息准则(AIC)(Akaike,)]一样好。然后,我们对人体步态数据进行了分析,发现具有时间平滑约束的消声混合模型能够最好地解释这些数据。
A wide range of blind source separation methods have been used in motor control research for the extraction of movement primitives from EMG and kinematic data. Popular examples are principal component analysis (PCA), independent component analysis (ICA), anechoic demixing, and the time-varying synergy model (d'Avella and Tresch,). However, choosing the parameters of these models, or indeed choosing the type of model, is often done in a heuristic fashion, driven by result expectations as much as by the data. We propose an objective criterion which allows to select the model type, number of primitives and the temporal smoothness prior. Our approach is based on a Laplace approximation to the posterior distribution of the parameters of a given blind source separation model, re-formulated as a Bayesian generative model. We first validate our criterion on ground truth data, showing that it performs at least as good as traditional model selection criteria [Bayesian information criterion, BIC (Schwarz,) and the Akaike Information Criterion (AIC) (Akaike,)]. Then, we analyze human gait data, finding that an anechoic mixture model with a temporal smoothness constraint on the sources can best account for the data.
DOI: 10.1523/jneurosci.0830-06.2006
发表时间: 2006-07-26
影响因子: 5.3
作者:
d'Avella, Andrea;Portone, Alessandro;Lacquaniti, Francesco
通讯作者: Lacquaniti, Francesco
DOI: 10.3389/fncom.2013.00011
发表时间: 2013
影响因子: 3.2
作者:
Chiovetto E;Berret B;Delis I;Panzeri S;Pozzo T
通讯作者: Pozzo T
DOI: 10.1007/s00221-012-3030-y
发表时间: 2012-05-01
影响因子: 2
作者:
Chiovetto, Enrico;Patane, Laura;Pozzo, Thierry
通讯作者: Pozzo, Thierry
DOI: 10.1016/j.brainresrev.2007.08.004
发表时间: 2008-01-01
影响因子: --
作者:
Bizzi, E.;Cheung, V. C. K.;Tresch, M.
通讯作者: Tresch, M.
DOI: 10.1038/29528
发表时间: 1998-08-20
期刊: NATURE
影响因子: 64.8
作者:
Harris, CM;Wolpert, DM
通讯作者: Wolpert, DM