Signals from multi-sensor systems are often mixtures of （statistically） independent sources by unknown mixing method. Blind source separation（BSS） and independent component analysis（ICA） are the methods to ident...Signals from multi-sensor systems are often mixtures of （statistically） independent sources by unknown mixing method. Blind source separation（BSS） and independent component analysis（ICA） are the methods to identify/recover the channels and the sources. BSS/ICA of nonlinear mixing models are difficult problems. For instance, the post-nonlinear model has been studied by several authors. It is noticed that in most cases, the proposed models are always with an invertible mixing. According to this fact there is an interesting question, how about the situation of the non-invertible non-linear mixing in BSS or ICA？ A new simple non-linear mixing model is proposed with a kind of non-invertible mixing, the folding mixing, and method to identify its channel, blindly.展开更多
Certain locally optimal tests for deterministic components in vector time series have associated sampling distributions determined by a linear combination of Beta variates. Such distributions are nonstandard and must ...Certain locally optimal tests for deterministic components in vector time series have associated sampling distributions determined by a linear combination of Beta variates. Such distributions are nonstandard and must be tabulated by Monte Carlo simulation. In this paper, we provide closed form expressions for the mean and variance of several multivariate test statistics, moments that can be used to approximate unknown distributions. In particular, we find that the two-moment Inverse Gaussian approximation provides a simple and fast method to compute accurate quantiles and p-values in small and asymptotic samples. To illustrate the scope of this approximation we review some standard tests for deterministic trends and/or seasonal patterns in VARIMA and structural time series models.展开更多
基金This project was supported by the Talent Foundation of Anhui Province(2004Z025)
文摘Signals from multi-sensor systems are often mixtures of （statistically） independent sources by unknown mixing method. Blind source separation（BSS） and independent component analysis（ICA） are the methods to identify/recover the channels and the sources. BSS/ICA of nonlinear mixing models are difficult problems. For instance, the post-nonlinear model has been studied by several authors. It is noticed that in most cases, the proposed models are always with an invertible mixing. According to this fact there is an interesting question, how about the situation of the non-invertible non-linear mixing in BSS or ICA？ A new simple non-linear mixing model is proposed with a kind of non-invertible mixing, the folding mixing, and method to identify its channel, blindly.
文摘Certain locally optimal tests for deterministic components in vector time series have associated sampling distributions determined by a linear combination of Beta variates. Such distributions are nonstandard and must be tabulated by Monte Carlo simulation. In this paper, we provide closed form expressions for the mean and variance of several multivariate test statistics, moments that can be used to approximate unknown distributions. In particular, we find that the two-moment Inverse Gaussian approximation provides a simple and fast method to compute accurate quantiles and p-values in small and asymptotic samples. To illustrate the scope of this approximation we review some standard tests for deterministic trends and/or seasonal patterns in VARIMA and structural time series models.
