Shared feature extraction for nearest neighbor face recognition

In this paper, we propose a new supervised linearfeature extraction technique for multiclass classification problemsthat is specially suited to the nearest neighbor classifier (NN).The problem of finding the optimal linear projection matrix isdefined as a classification problem and the Adaboost algorithmis used to compute it in an iterative way. This strategy allowsthe introduction of a multitask learning (MTL) criterion in themethod and results in a solution that makes no assumptions aboutthe data distribution and that is specially appropriated to solvethe small sample size problem. The performance of the methodis illustrated by an application to the face recognition problem.The experiments show that the representation obtained followingthe multitask approach improves the classic feature extractionalgorithms when using the NN classifier, especially when we havea few examples from each class

On Convergence Properties of the EM Algorithm for Gaussian Mixtures

"Expectation-Maximization'' (EM) algorithm and gradient-based approaches for maximum likelihood learning of finite Gaussian mixtures. We show that the EM step in parameter space is obtained from the gradient via a projection matrix $P$, and we provide an explicit expression for the matrix. We then analyze the convergence of EM in terms of special properties of $P$ and provide new results analyzing the effect that $P$ has on the likelihood surface. Based on these mathematical results, we present a comparative discussion of the advantages and disadvantages of EM and other algorithms for the learning of Gaussian mixture models.

Modal contribution and state space order selection in operational modal analysis

The estimation of modal parameters of a structure from ambient measurements has attracted the attention of many researchers in the last years. The procedure is now well established and the use of state space models, stochastic system identification methods and stabilization diagrams allows to identify the modes of the structure. In this paper the contribution of each identified mode to the measured vibration is discussed. This modal contribution is computed using the Kalman filter and it is an indicator of the importance of the modes. Also the variation of the modal contribution with the order of the model is studied. This analysis suggests selecting the order for the state space model as the order that includes the modes with higher contribution. The order obtained using this method is compared to those obtained using other well known methods, like Akaike criteria for time series or the singular values of the weighted projection matrix in the Stochastic Subspace Identification method. Finally, both simulated and measured vibration data are used to show the practicability of the derived technique. Finally, it is important to remark that the method can be used with any identification method working in the state space model.

Age regression from soft aligned face images using low computational resources

The initial step in most facial age estimation systems consists of accurately aligning a model to the output of a face detector (e.g. an Active Appearance Model). This fitting process is very expensive in terms of computational resources and prone to get stuck in local minima. This makes it impractical for analysing faces in resource limited computing devices. In this paper we build a face age regressor that is able to work directly on faces cropped using a state-of-the-art face detector. Our procedure uses K nearest neighbours (K-NN) regression with a metric based on a properly tuned Fisher Linear Discriminant Analysis (LDA) projection matrix. On FG-NET we achieve a state-of-the-art Mean Absolute Error (MAE) of 5.72 years with manually aligned faces. Using face images cropped by a face detector we get a MAE of 6.87 years in the same database. Moreover, most of the algorithms presented in the literature have been evaluated on single database experiments and therefore, they report optimistically biased results. In our cross-database experiments we get a MAE of roughly 12 years, which would be the expected performance in a real world application.

Use of an Inverse Method for Time Series to Estimate the Dynamics of and Management Strategies for the Box Jellyfish Carybdea marsupialis

Frequently, population ecology of marine organisms uses a descriptive approach in which their sizes and densities are plotted over time. This approach has limited usefulness for design strategies in management or modelling different scenarios. Population projection matrix models are among the most widely used tools in ecology. Unfortunately, for the majority of pelagic marine organisms, it is difficult to mark individuals and follow them over time to determine their vital rates and built a population projection matrix model. Nevertheless, it is possible to get time-series data to calculate size structure and densities of each size, in order to determine the matrix parameters. This approach is known as a “demographic inverse problem” and it is based on quadratic programming methods, but it has rarely been used on aquatic organisms. We used unpublished field data of a population of cubomedusae Carybdea marsupialis to construct a population projection matrix model and compare two different management strategies to lower population to values before year 2008 when there was no significant interaction with bathers. Those strategies were by direct removal of medusae and by reducing prey. Our results showed that removal of jellyfish from all size classes was more effective than removing only juveniles or adults. When reducing prey, the highest efficiency to lower the C. marsupialis population occurred when prey depletion affected prey of all medusae sizes. Our model fit well with the field data and may serve to design an efficient management strategy or build hypothetical scenarios such as removal of individuals or reducing prey. TThis This sdfsdshis method is applicable to other marine or terrestrial species, for which density and population structure over time are available.

Numerical methods for solar tomography in the STEREO era

In this thesis, we propose several advances in the numerical and computational algorithms that are used to determine tomographic estimates of physical parameters in the solar corona. We focus on methods for both global dynamic estimation of the coronal electron density and estimation of local transient phenomena, such as coronal mass ejections, from empirical observations acquired by instruments onboard the STEREO spacecraft. We present a first look at tomographic reconstructions of the solar corona from multiple points-of-view, which motivates the developments in this thesis. In particular, we propose a method for linear equality constrained state estimation that leads toward more physical global dynamic solar tomography estimates. We also present a formulation of the local static estimation problem, i.e., the tomographic estimation of local events and structures like coronal mass ejections, that couples the tomographic imaging problem to a phase field based level set method. This formulation will render feasible the 3D tomography of coronal mass ejections from limited observations. Finally, we develop a scalable algorithm for ray tracing dense meshes, which allows efficient computation of many of the tomographic projection matrices needed for the applications in this thesis.

A low-cost 3D reconstruction system using a single-shot projection of a pattern matrix

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Expokit: A software package for computing matrix exponentials

Expokit provides a set of routines aimed at computing matrix exponentials. More precisely, it computes either a small matrix exponential in full, the action of a large sparse matrix exponential on an operand vector, or the solution of a system of linear ODEs with constant inhomogeneity. The backbone of the sparse routines consists of matrix-free Krylov subspace projection methods (Arnoldi and Lanczos processes), and that is why the toolkit is capable of coping with sparse matrices of large dimension. The software handles real and complex matrices and provides specific routines for symmetric and Hermitian matrices. The computation of matrix exponentials is a numerical issue of critical importance in the area of Markov chains and furthermore, the computed solution is subject to probabilistic constraints. In addition to addressing general matrix exponentials, a distinct attention is assigned to the computation of transient states of Markov chains.

Estimation of the Spatial Weights Matrix under Structural Constraints

While estimates of models with spatial interaction are very sensitive to the choice of spatial weights, considerable uncertainty surrounds de nition of spatial weights in most studies with cross-section dependence. We show that, in the spatial error model the spatial weights matrix is only partially identi ed, and is fully identifi ed under the structural constraint of symmetry. For the spatial error model, we propose a new methodology for estimation of spatial weights under the assumption of symmetric spatial weights, with extensions to other important spatial models. The methodology is applied to regional housing markets in the UK, providing an estimated spatial weights matrix that generates several new hypotheses about the economic and socio-cultural drivers of spatial di¤usion in housing demand.

Localized matrix metalloproteinase (MMP)-2 and MMP-9 activity in the rat ventral prostate during the first week of postnatal development

The initial events in prostatic morphogenesis involve cell proliferation, epithelial canalization and outgrowth toward the stroma. We have hypothesized that stromal rearrangement takes place at the sites of epithelial growth and branching and that this rearrangement involves the action of gelatinases matrix metalloproteinase (MMP)-2 and MMP-9. Thus, the purpose of the present study was to characterize structural aspects of epithelial growth during the first week of postnatal development of the rat ventral prostate and to investigate the expression, localization and activity of MMP-2 and MMP-9 during this period by histological, ultrastructural and immunocytochemical analysis, in addition to gel zymography, in situ zymography and Western blotting. An increasing complexity of prostatic architeture was observed within the first postnatal week. Concurrently, the stroma became more organized and some cells differentiated into smooth muscle cells. Reticulin fibers appeared in a basket-like arrangement around both growing tips and epithelial sprouts, associated with a fainter staining for laminin. MMP-2 and MMP-9 activities were detected. MMP-2/MMP-9 expression decreased during the first week. Developing epithelial cords showed strong and difuse gelatinolytic activity. This activity coincided with the distribution of MMP-2 as determined by immunocytochemistry. on the other hand, MMP-9 was rather concentrated at the epithelial tips. These results suggest that gelatinolytic activity (with contribution of both MMP-2 and MMP-9) in the epithelium and at the epithelium-stroma interface are at least in part responsible for the tissue remodeling that allows epithelial growth and its projection into the surrounding stroma.

Spurious transients of projection methods in microflow simulations

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Homogeneous links and the Seifert matrix

Homogeneous links were introduced by Peter Cromwell, who pr oved that the projection surface of these links, that given by the Seifert al- gorithm, has minimal genus. Here we provide a different proof , with a geometric rather than combinatorial flavor. To do this, we fir st show a direct relation between the Seifert matrix and the decompo sition into blocks of the Seifert graph. Precisely, we prove that the Sei fert matrix can be arranged in a block triangular form, with small boxes in th e diagonal corresponding to the blocks of the Seifert graph. Then we pro ve that the boxes in the diagonal has non-zero determinant, by looking a t an explicit matrix of degrees given by the planar structure of the Seifer t graph. The paper contains also a complete classification of the homogen eous knots of genus one.

Quantitative Proteomic Analysis Reveals Metabolic Alterations, Calcium Dysregulation, And Increased Expression Of Extracellular Matrix Proteins In Laminin α2 Chain-deficient Muscle.

Congenital muscular dystrophy with laminin α2 chain deficiency (MDC1A) is one of the most severe forms of muscular disease and is characterized by severe muscle weakness and delayed motor milestones. The genetic basis of MDC1A is well known, yet the secondary mechanisms ultimately leading to muscle degeneration and subsequent connective tissue infiltration are not fully understood. In order to obtain new insights into the molecular mechanisms underlying MDC1A, we performed a comparative proteomic analysis of affected muscles (diaphragm and gastrocnemius) from laminin α2 chain-deficient dy(3K)/dy(3K) mice, using multidimensional protein identification technology combined with tandem mass tags. Out of the approximately 700 identified proteins, 113 and 101 proteins, respectively, were differentially expressed in the diseased gastrocnemius and diaphragm muscles compared with normal muscles. A large portion of these proteins are involved in different metabolic processes, bind calcium, or are expressed in the extracellular matrix. Our findings suggest that metabolic alterations and calcium dysregulation could be novel mechanisms that underlie MDC1A and might be targets that should be explored for therapy. Also, detailed knowledge of the composition of fibrotic tissue, rich in extracellular matrix proteins, in laminin α2 chain-deficient muscle might help in the design of future anti-fibrotic treatments. All MS data have been deposited in the ProteomeXchange with identifier PXD000978 (http://proteomecentral.proteomexchange.org/dataset/PXD000978).

Matrix Metalloproteinases And Left Ventricular Function And Structure In Spinal Cord Injured Subjects.

Subjects with spinal cord injury (SCI) exhibit impaired left ventricular (LV) diastolic function, which has been reported to be attenuated by regular physical activity. This study investigated the relationship between circulating matrix metalloproteinases (MMPs) and tissue inhibitors of MMPs (TIMPs) and echocardiographic parameters in SCI subjects and the role of physical activity in this regard. Forty-two men with SCI [19 sedentary (S-SCI) and 23 physically-active (PA-SCI)] were evaluated by clinical, anthropometric, laboratory, and echocardiographic analysis. Plasmatic pro-MMP-2, MMP-2, MMP-8, pro-MMP-9, MMP-9, TIMP-1 and TIMP-2 levels were determined by enzyme-linked immunosorbent assay and zymography. PA-SCI subjects presented lower pro-MMP-2 and pro-MMP-2/TIMP-2 levels and improved markers of LV diastolic function (lower E/Em and higher Em and E/A values) than S-SCI ones. Bivariate analysis showed that pro-MMP-2 correlated inversely with Em and directly with E/Em, while MMP-9 correlated directly with LV mass index and LV end-diastolic diameter in the whole sample. Following multiple regression analysis, pro-MMP-2, but not physical activity, remained associated with Em, while MMP-9 was associated with LV mass index in the whole sample. These findings suggest differing roles for MMPs in LV structure and function regulation and an interaction among pro-MMP-2, diastolic function and physical activity in SCI subjects.

Petroleomics By Electrospray Ionization Ft-icr Mass Spectrometry Coupled To Partial Least Squares With Variable Selection Methods: Prediction Of The Total Acid Number Of Crude Oils.

Negative-ion mode electrospray ionization, ESI(-), with Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) was coupled to a Partial Least Squares (PLS) regression and variable selection methods to estimate the total acid number (TAN) of Brazilian crude oil samples. Generally, ESI(-)-FT-ICR mass spectra present a power of resolution of ca. 500,000 and a mass accuracy less than 1 ppm, producing a data matrix containing over 5700 variables per sample. These variables correspond to heteroatom-containing species detected as deprotonated molecules, [M - H](-) ions, which are identified primarily as naphthenic acids, phenols and carbazole analog species. The TAN values for all samples ranged from 0.06 to 3.61 mg of KOH g(-1). To facilitate the spectral interpretation, three methods of variable selection were studied: variable importance in the projection (VIP), interval partial least squares (iPLS) and elimination of uninformative variables (UVE). The UVE method seems to be more appropriate for selecting important variables, reducing the dimension of the variables to 183 and producing a root mean square error of prediction of 0.32 mg of KOH g(-1). By reducing the size of the data, it was possible to relate the selected variables with their corresponding molecular formulas, thus identifying the main chemical species responsible for the TAN values.