Supervised Gaussian Process Latent Variable Model for Dimensionality Reduction

The Gaussian process latent variable model (GP-LVM) has been identified to be an effective probabilistic approach for dimensionality reduction because it can obtain a low-dimensional manifold of a data set in an unsupervised fashion. Consequently, the GP-LVM is insufficient for supervised learning tasks (e. g., classification and regression) because it ignores the class label information for dimensionality reduction. In this paper, a supervised GP-LVM is developed for supervised learning tasks, and the maximum a posteriori algorithm is introduced to estimate positions of all samples in the latent variable space. We present experimental evidences suggesting that the supervised GP-LVM is able to use the class label information effectively, and thus, it outperforms the GP-LVM and the discriminative extension of the GP-LVM consistently. The comparison with some supervised classification methods, such as Gaussian process classification and support vector machines, is also given to illustrate the advantage of the proposed method.

T-Kernel在Blackfin处理器上的移植分析

T-Kernel是日本T-Engine组织推出的开源免费的嵌入式实时操作系统(RTOS),以其强实时小体积内核著称。本文针对T-Kernel在Blackfin处理器(BF533)上的移植过程进行了分析,给出了中断管理,任务切换和系统调用入口的实现方法,并进行了稳定性和实时性测试,保证了移植系统的性能。

开源RTOS T-Kernel在Blackfin处理器上的移植

随着嵌入式计算技术的飞速发展,多种功能强大的微处理器和相应嵌入式操作系统也相继问世。选择合适的嵌入式操作系统和处理器平台进行移植成为嵌入式开发的重要技术环节。本文介绍了开源嵌入式实时操作系统RTOS(Real Time Operating System)T-Kernel和Blackfin(BF)533处理器及其开发环境VisualDSP++4.5Environment,给出了中断管理、任务切换和系统调用入口三个模块的移植方法,并讨论了相应的系统稳定性和实时性测试方法。日本T-Engine组织推出的T-Kernel RTOS拥有高实时性、小体积的内核,并强调对底层处理器全面封装;ADI Blackfin系列微处理器同时具有DSP和MCU的特点,非常适合于移植RTOS。因此T-Kernel在BF533上的移植是一个典型的开发应用实例,其移植分析方法对于其他嵌入式RTOS移植也具有参考价值。

Deconvolution of overlapped peaks based on the exponentially modified Gaussian model in comprehensive two-dimensional gas chromatography

Comprehensive two-dimensional gas chromatography (GC x GC) has attracted much attention for the analys is of complex samples. Even with a large peak capacity in GC x GC, peak overlapping is often met. In this paper, a new method was developed to resolve overlapped peaks based on the mass conservation and the exponentially modified Gaussian (EMG) model. Linear relationships between the calculated sigma, tau of primary peaks with the corresponding retention time (t(R)) were obtained, and the correlation coefficients were over 0.99. Based on such relationships, the elution profile of each compound in overlapped peaks could be simulated, even for the peak never separated on the second-dimension. The proposed method has proven to offer more accurate peak area than the general data processing method. (c) 2005 Elsevier B.V. All rights reserved.

Active Hidden Models for Tracking with Kernel Projections

We introduce Active Hidden Models (AHM) that utilize kernel methods traditionally associated with classification. We use AHMs to track deformable objects in video sequences by leveraging kernel projections. We introduce the "subset projection" method which improves the efficiency of our tracking approach by a factor of ten. We successfully tested our method on facial tracking with extreme head movements (including full 180-degree head rotation), facial expressions, and deformable objects. Given a kernel and a set of training observations, we derive unbiased estimates of the accuracy of the AHM tracker. Kernels are generally used in classification methods to make training data linearly separable. We prove that the optimal (minimum variance) tracking kernels are those that make the training observations linearly dependent.

Bayesian Gaussian Copula Factor Models for Mixed Data.

Gaussian factor models have proven widely useful for parsimoniously characterizing dependence in multivariate data. There is a rich literature on their extension to mixed categorical and continuous variables, using latent Gaussian variables or through generalized latent trait models acommodating measurements in the exponential family. However, when generalizing to non-Gaussian measured variables the latent variables typically influence both the dependence structure and the form of the marginal distributions, complicating interpretation and introducing artifacts. To address this problem we propose a novel class of Bayesian Gaussian copula factor models which decouple the latent factors from the marginal distributions. A semiparametric specification for the marginals based on the extended rank likelihood yields straightforward implementation and substantial computational gains. We provide new theoretical and empirical justifications for using this likelihood in Bayesian inference. We propose new default priors for the factor loadings and develop efficient parameter-expanded Gibbs sampling for posterior computation. The methods are evaluated through simulations and applied to a dataset in political science. The models in this paper are implemented in the R package bfa.

Task-driven adaptive statistical compressive sensing of gaussian mixture models

A framework for adaptive and non-adaptive statistical compressive sensing is developed, where a statistical model replaces the standard sparsity model of classical compressive sensing. We propose within this framework optimal task-specific sensing protocols specifically and jointly designed for classification and reconstruction. A two-step adaptive sensing paradigm is developed, where online sensing is applied to detect the signal class in the first step, followed by a reconstruction step adapted to the detected class and the observed samples. The approach is based on information theory, here tailored for Gaussian mixture models (GMMs), where an information-theoretic objective relationship between the sensed signals and a representation of the specific task of interest is maximized. Experimental results using synthetic signals, Landsat satellite attributes, and natural images of different sizes and with different noise levels show the improvements achieved using the proposed framework when compared to more standard sensing protocols. The underlying formulation can be applied beyond GMMs, at the price of higher mathematical and computational complexity. © 1991-2012 IEEE.

The abelianization of the Johnson kernel

We prove that the first complex homology of the Johnson subgroup of the Torelli group Tg is a non-trivial, unipotent Tg-module for all g ≥ 4 and give an explicit presentation of it as a Sym H 1(Tg,C)-module when g ≥ 6. We do this by proving that, for a finitely generated group G satisfying an assumption close to formality, the triviality of the restricted characteristic variety implies that the first homology of its Johnson kernel is a nilpotent module over the corresponding Laurent polynomial ring, isomorphic to the infinitesimal Alexander invariant of the associated graded Lie algebra of G. In this setup, we also obtain a precise nilpotence test. © European Mathematical Society 2014.

Experimentally realizable characterizations of continuous- variable Gaussian states

Measures of entanglement, fidelity, and purity are basic yardsticks in quantum-information processing. We propose how to implement these measures using linear devices and homodyne detectors for continuous-variable Gaussian states. In particular, the test of entanglement becomes simple with some prior knowledge that is relevant to current experiments.

Nonclassicality of a photon-subtracted Gaussian field

We investigate the nonclassicality of a photon-subtracted Gaussian field, which was produced in a recent experiment, using negativity of the Wigner function and the nonexistence of well-behaved positive P function. We obtain the condition to see negativity of the Wigner function for the case including the mixed Gaussian incoming field, the threshold photodetection and the inefficient homodyne measurement. We show how similar the photon-subtracted state is to a superposition of coherent states.

Entanglement of a two-mode squeezed state in a phase-sensitive Gaussian environment

Some non-classical properties such as squeezing, sub-Poissonian photon statistics or oscillations in photon-number distributions may survive longer in a phase-sensitive environment than in a phase-insensitive environment. We examine if entanglement, which is an inter-mode non-classical feature, can also survive longer in a phase-sensitive environment. Differently from the single-mode case, we find that making the environment phase-sensitive does not aid in prolonging the inter-mode non-classical nature, i.e. entanglement.