基于结构化Fisherface的人脸识别新方法

特征提取是人脸识别中一个关键步骤。传统的Fisherface人脸识别方法中用样本的类均值和总体均值定义相应的散布矩阵，丢失了样本个体之间的结构信息，本文提出了一种基于原始样本个体结构信息的结构化Fisherface人脸识别方法，最后得到的特征数据中保留了原始样本更多的分布信息。在ORL人脸数据库的实验结果验证了该方法的有效性。

Robust Formulations for Handling Uncertainty in Kernel Matrices

We study the problem of uncertainty in the entries of the Kernel matrix, arising in SVM formulation. Using Chance Constraint Programming and a novel large deviation inequality we derive a formulation which is robust to such noise. The resulting formulation applies when the noise is Gaussian, or has finite support. The formulation in general is non-convex, but in several cases of interest it reduces to a convex program. The problem of uncertainty in kernel matrix is motivated from the real world problem of classifying proteins when the structures are provided with some uncertainty. The formulation derived here naturally incorporates such uncertainty in a principled manner leading to significant improvements over the state of the art. 1.

Efficient Methods for Robust Classification Under Uncertainty in Kernel Matrices

In this paper we study the problem of designing SVM classifiers when the kernel matrix, K, is affected by uncertainty. Specifically K is modeled as a positive affine combination of given positive semi definite kernels, with the coefficients ranging in a norm-bounded uncertainty set. We treat the problem using the Robust Optimization methodology. This reduces the uncertain SVM problem into a deterministic conic quadratic problem which can be solved in principle by a polynomial time Interior Point (IP) algorithm. However, for large-scale classification problems, IP methods become intractable and one has to resort to first-order gradient type methods. The strategy we use here is to reformulate the robust counterpart of the uncertain SVM problem as a saddle point problem and employ a special gradient scheme which works directly on the convex-concave saddle function. The algorithm is a simplified version of a general scheme due to Juditski and Nemirovski (2011). It achieves an O(1/T-2) reduction of the initial error after T iterations. A comprehensive empirical study on both synthetic data and real-world protein structure data sets show that the proposed formulations achieve the desired robustness, and the saddle point based algorithm outperforms the IP method significantly.

Delay-dependent robust H-infinity control for uncertain systems with time-varying delay

This paper proposes a new approach for delay-dependent robust H-infinity stability analysis and control synthesis of uncertain systems with time-varying delay. The key features of the approach include the introduction of a new Lyapunov–Krasovskii functional, the construction of an augmented matrix with uncorrelated terms, and the employment of a tighter bounding technique. As a result, significant performance improvement is achieved in system analysis and synthesis without using either free weighting matrices or model transformation. Examples are given to demonstrate the effectiveness of the proposed approach.

New Approach on Robust Delay-Dependent H∞ Control for Uncertain T-S Fuzzy Systems With Interval Time-Varying Delay

This paper investigates the robust H∞ control for Takagi-Sugeno (T-S) fuzzy systems with interval time-varying delay. By employing a new and tighter integral inequality and constructing an appropriate type of Lyapunov functional, delay-dependent stability criteria are derived for the control problem. Because neither any model transformation nor free weighting matrices are employed in our theoretical derivation, the developed stability criteria significantly improve and simplify the existing stability conditions. Also, the maximum allowable upper delay bound and controller feedback gains can be obtained simultaneously from the developed approach by solving a constrained convex optimization problem. Numerical examples are given to demonstrate the effectiveness of the proposed methods.

Robust joint precoder/receive filter designs for multiuser MIMO downlink

In this paper, we consider robust joint linear precoder/receive filter designs for multiuser multi-input multi-output (MIMO) downlink that minimize the sum mean square error (SMSE) in the presence of imperfect channel state information at the transmitter (CSIT). The base station (BS) is equipped with multiple transmit antennas, and each user terminal is equipped with one or more receive antennas. We consider a stochastic error (SE) model and a norm-bounded error (NBE) model for the CSIT error. In the case of CSIT error following SE model, we compute the desired downlink precoder/receive filter matrices by solving the simpler uplink problem by exploiting the uplink-downlink duality for the MSE region. In the case of the CSIT error following the NBE model, we consider the worst-case SMSE as the objective function, and propose an iterative algorithm for the robust transceiver design. The robustness of the proposed algorithms to imperfections in CSIT is illustrated through simulations.

Patterns in permuted binary matrices

Reorganizing a dataset so that its hidden structure can be observed is useful in any data analysis task. For example, detecting a regularity in a dataset helps us to interpret the data, compress the data, and explain the processes behind the data. We study datasets that come in the form of binary matrices (tables with 0s and 1s). Our goal is to develop automatic methods that bring out certain patterns by permuting the rows and columns. We concentrate on the following patterns in binary matrices: consecutive-ones (C1P), simultaneous consecutive-ones (SC1P), nestedness, k-nestedness, and bandedness. These patterns reflect specific types of interplay and variation between the rows and columns, such as continuity and hierarchies. Furthermore, their combinatorial properties are interlinked, which helps us to develop the theory of binary matrices and efficient algorithms. Indeed, we can detect all these patterns in a binary matrix efficiently, that is, in polynomial time in the size of the matrix. Since real-world datasets often contain noise and errors, we rarely witness perfect patterns. Therefore we also need to assess how far an input matrix is from a pattern: we count the number of flips (from 0s to 1s or vice versa) needed to bring out the perfect pattern in the matrix. Unfortunately, for most patterns it is an NP-complete problem to find the minimum distance to a matrix that has the perfect pattern, which means that the existence of a polynomial-time algorithm is unlikely. To find patterns in datasets with noise, we need methods that are noise-tolerant and work in practical time with large datasets. The theory of binary matrices gives rise to robust heuristics that have good performance with synthetic data and discover easily interpretable structures in real-world datasets: dialectical variation in the spoken Finnish language, division of European locations by the hierarchies found in mammal occurrences, and co-occuring groups in network data. In addition to determining the distance from a dataset to a pattern, we need to determine whether the pattern is significant or a mere occurrence of a random chance. To this end, we use significance testing: we deem a dataset significant if it appears exceptional when compared to datasets generated from a certain null hypothesis. After detecting a significant pattern in a dataset, it is up to domain experts to interpret the results in the terms of the application.

What is the weakest topology in which feedback stability is robust?

Mathematical theorems in control theory are only of interest in so far as their assumptions relate to practical situations. The space of systems with transfer functions in ℋ∞, for example, has many advantages mathematically, but includes large classes of non-physical systems, and one must be careful in drawing inferences from results in that setting. Similarly, the graph topology has long been known to be the weakest, or coarsest, topology in which (1) feedback stability is a robust property (i.e. preserved in small neighbourhoods) and (2) the map from open-to-closed-loop transfer functions is continuous. However, it is not known whether continuity is a necessary part of this statement, or only required for the existing proofs. It is entirely possible that the answer depends on the underlying classes of systems used. The class of systems we concern ourselves with here is the set of systems that can be approximated, in the graph topology, by real rational transfer function matrices. That is, lumped parameter models, or those distributed systems for which it makes sense to use finite element methods. This is precisely the set of systems that have continuous frequency responses in the extended complex plane. For this class, we show that there is indeed a weaker topology; in which feedback stability is robust but for which the maps from open-to-closed-loop transfer functions are not necessarily continuous. © 2013 Copyright Taylor and Francis Group, LLC.

Discovering subgroups of patients from DNA copy number data using NMF on compacted matrices

In the study of complex genetic diseases, the identification of subgroups of patients sharing similar genetic characteristics represents a challenging task, for example, to improve treatment decision. One type of genetic lesion, frequently investigated in such disorders, is the change of the DNA copy number (CN) at specific genomic traits. Non-negative Matrix Factorization (NMF) is a standard technique to reduce the dimensionality of a data set and to cluster data samples, while keeping its most relevant information in meaningful components. Thus, it can be used to discover subgroups of patients from CN profiles. It is however computationally impractical for very high dimensional data, such as CN microarray data. Deciding the most suitable number of subgroups is also a challenging problem. The aim of this work is to derive a procedure to compact high dimensional data, in order to improve NMF applicability without compromising the quality of the clustering. This is particularly important for analyzing high-resolution microarray data. Many commonly used quality measures, as well as our own measures, are employed to decide the number of subgroups and to assess the quality of the results. Our measures are based on the idea of identifying robust subgroups, inspired by biologically/clinically relevance instead of simply aiming at well-separated clusters. We evaluate our procedure using four real independent data sets. In these data sets, our method was able to find accurate subgroups with individual molecular and clinical features and outperformed the standard NMF in terms of accuracy in the factorization fitness function. Hence, it can be useful for the discovery of subgroups of patients with similar CN profiles in the study of heterogeneous diseases.

High-amylose carboxymethyl starch matrices for oral sustained drug-release : in vitro and in vivo evaluation

Les amidons non modifiées et modifiés représentent un groupe d’excipients biodégradables et abondants particulièrement intéressant. Ils ont été largement utilisés en tant qu’excipients à des fins diverses dans des formulations de comprimés, tels que liants et/ou agents de délitement. Le carboxyméthylamidon sodique à haute teneur en amylose atomisé (SD HASCA) a été récemment proposé comme un excipient hydrophile à libération prolongée innovant dans les formes posologiques orales solides. Le carboxyméthylamidon sodique à haute teneur en amylose amorphe (HASCA) a d'abord été produit par l'éthérification de l'amidon de maïs à haute teneur en amylose avec le chloroacétate. HASCA a été par la suite séché par atomisation pour obtenir le SD HASCA. Ce nouvel excipient a montré des propriétés présentant certains avantages dans la production de formes galéniques à libération prolongée. Les comprimés matriciels produits à partir de SD HASCA sont peu coûteux, simples à formuler et faciles à produire par compression directe. Le principal objectif de cette recherche était de poursuivre le développement et l'optimisation des comprimés matriciels utilisant SD HASCA comme excipient pour des formulations orales à libération prolongée. A cet effet, des tests de dissolution simulant les conditions physiologiques du tractus gastro-intestinal les plus pertinentes, en tenant compte de la nature du polymère à l’étude, ont été utilisés pour évaluer les caractéristiques à libération prolongée et démontrer la performance des formulations SD HASCA. Une étude clinique exploratoire a également été réalisée pour évaluer les propriétés de libération prolongée de cette nouvelle forme galénique dans le tractus gastro-intestinal. Le premier article présenté dans cette thèse a évalué les propriétés de libération prolongée et l'intégrité physique de formulations contenant un mélange comprimé de principe actif, de chlorure de sodium et de SD HASCA, dans des milieux de dissolution biologiquement pertinentes. L'influence de différentes valeurs de pH acide et de temps de séjour dans le milieu acide a été étudiée. Le profil de libération prolongée du principe actif à partir d'une formulation de SD HASCA optimisée n'a pas été significativement affecté ni par la valeur de pH acide ni par le temps de séjour dans le milieu acide. Ces résultats suggèrent une influence limitée de la variabilité intra et interindividuelle du pH gastrique sur la cinétique de libération à partir de matrices de SD HASCA. De plus, la formulation optimisée a gardé son intégrité pendant toute la durée des tests de dissolution. L’étude in vivo exploratoire a démontré une absorption prolongée du principe actif après administration orale des comprimés matriciels de SD HASCA et a montré que les comprimés ne se sont pas désintégrés en passant par l'estomac et qu’ils ont résisté à l’hydrolyse par les α-amylases dans l'intestin. Le deuxième article présente le développement de comprimés SD HASCA pour une administration orale une fois par jour et deux fois par jour contenant du chlorhydrate de tramadol (100 mg et 200 mg). Ces formulations à libération prolongée ont présenté des valeurs de dureté élevées sans nécessiter l'ajout de liants, ce qui facilite la production et la manipulation des comprimés au niveau industriel. La force de compression appliquée pour produire les comprimés n'a pas d'incidence significative sur les profils de libération du principe actif. Le temps de libération totale à partir de comprimés SD HASCA a augmenté de manière significative avec le poids du comprimé et peut, de ce fait, être utilisé pour moduler le temps de libération à partir de ces formulations. Lorsque les comprimés ont été exposés à un gradient de pH et à un milieu à 40% d'éthanol, un gel très rigide s’est formé progressivement sur leur surface amenant à la libération prolongée du principe actif. Ces propriétés ont indiqué que SD HASCA est un excipient robuste pour la production de formes galéniques orales à libération prolongée, pouvant réduire la probabilité d’une libération massive de principe actif et, en conséquence, des effets secondaires, même dans le cas de co-administration avec une forte dose d'alcool. Le troisième article a étudié l'effet de α-amylase sur la libération de principe actif à partir de comprimés SD HASCA contenant de l’acétaminophène et du chlorhydrate de tramadol qui ont été développés dans les premières étapes de cette recherche (Acetaminophen SR et Tramadol SR). La modélisation mathématique a montré qu'une augmentation de la concentration d’α-amylase a entraîné une augmentation de l'érosion de polymère par rapport à la diffusion de principe actif comme étant le principal mécanisme contrôlant la libération de principe actif, pour les deux formulations et les deux temps de résidence en milieu acide. Cependant, même si le mécanisme de libération peut être affecté, des concentrations d’α-amylase allant de 0 UI/L à 20000 UI/L n'ont pas eu d'incidence significative sur les profils de libération prolongée à partir de comprimés SD HASCA, indépendamment de la durée de séjour en milieu acide, le principe actif utilisé, la teneur en polymère et la différente composition de chaque formulation. Le travail présenté dans cette thèse démontre clairement l'utilité de SD HASCA en tant qu'un excipient à libération prolongée efficace.

A robust non-orthogonal space-time block code for four transmit antennas

Several non-orthogonal space-time block coding (NO-STBC) schemes have recently been proposed to achieve full rate transmission. Some of these schemes, however, suffer from weak robustness: their channel matrices will become ill conditioned in the case of highly correlated channels (HCC). To address this issue, this paper derives a family of robust NO-STBC schemes for four Tx antennas based on the worst case of HCC. These codes turned out to be a superset of Jafarkhani's quasi-orthogonal STBC codes. A computationally affordable linear decoder is also proposed. Although these codes achieve a similar performance to the non-robust schemes under normal channel conditions, they offer a strong robustness against HCC (although possibly yielding a poorer performance). Finally, computer simulations are presented to verify the algorithm design.

Robust pole assignment in linear state feedback

Numerical methods are described for determining robust, or well-conditioned, solutions to the problem of pole assignment by state feedback. The solutions obtained are such that the sensitivity of the assigned poles to perturbations in the system and gain matrices is minimized. It is shown that for these solutions, upper bounds on the norm of the feedback matrix and on the transient response are also minimized and a lower bound on the stability margin is maximized. A measure is derived which indicates the optimal conditioning that may be expected for a particular system with a given set of closed-loop poles, and hence the suitability of the given poles for assignment.

Robust inference in an heteroscedastic measurement error model

In this paper we deal with robust inference in heteroscedastic measurement error models Rather than the normal distribution we postulate a Student t distribution for the observed variables Maximum likelihood estimates are computed numerically Consistent estimation of the asymptotic covariance matrices of the maximum likelihood and generalized least squares estimators is also discussed Three test statistics are proposed for testing hypotheses of interest with the asymptotic chi-square distribution which guarantees correct asymptotic significance levels Results of simulations and an application to a real data set are also reported (C) 2009 The Korean Statistical Society Published by Elsevier B V All rights reserved

M-Functionals of Multivariate Scatter

This survey provides a self-contained account of M-estimation of multivariate scatter. In particular, we present new proofs for existence of the underlying M-functionals and discuss their weak continuity and differentiability. This is done in a rather general framework with matrix-valued random variables. By doing so we reveal a connection between Tyler's (1987) M-functional of scatter and the estimation of proportional covariance matrices. Moreover, this general framework allows us to treat a new class of scatter estimators, based on symmetrizations of arbitrary order. Finally these results are applied to M-estimation of multivariate location and scatter via multivariate t-distributions.

The development of direct ultra-fast PCR for forensic genotyping using short channel microfluidic systems with enhanced sieving matrices

There are situations in which it is very important to quickly and positively identify an individual. Examples include suspects detained in the neighborhood of a bombing or terrorist incident, individuals detained attempting to enter or leave the country, and victims of mass disasters. Systems utilized for these purposes must be fast, portable, and easy to maintain. The goal of this project was to develop an ultra fast, direct PCR method for forensic genotyping of oral swabs. The procedure developed eliminates the need for cellular digestion and extraction of the sample by performing those steps in the PCR tube itself. Then, special high-speed polymerases are added which are capable of amplifying a newly developed 7 loci multiplex in under 16 minutes. Following the amplification, a postage stamp sized microfluidic device equipped with specially designed entangled polymer separation matrix, yields a complete genotype in 80 seconds. The entire process is rapid and reliable, reducing the time from sample to genotype from 1-2 days to under 20 minutes. Operation requires minimal equipment and can be easily performed with a small high-speed thermal-cycler, reagents, and a microfluidic device with a laptop. The system was optimized and validated using a number of test parameters and a small test population. The overall precision was better than 0.17 bp and provided a power of discrimination greater than 1 in 106. The small footprint, and ease of use will permit this system to be an effective tool to quickly screen and identify individuals detained at ports of entry, police stations and remote locations. The system is robust, portable and demonstrates to the forensic community a simple solution to the problem of rapid determination of genetic identity.