Représentation et identification des hypersurfaces

L’objectif à moyen terme de ce travail est d’explorer quelques formulations des problèmes d’identification de forme et de reconnaissance de surface à partir de mesures ponctuelles. Ces problèmes ont plusieurs applications importantes dans les domaines de l’imagerie médicale, de la biométrie, de la sécurité des accès automatiques et dans l’identification de structures cohérentes lagrangiennes en mécanique des fluides. Par exemple, le problème d’identification des différentes caractéristiques de la main droite ou du visage d’une population à l’autre ou le suivi d’une chirurgie à partir des données générées par un numériseur. L’objectif de ce mémoire est de préparer le terrain en passant en revue les différents outils mathématiques disponibles pour appréhender la géométrie comme variable d’optimisation ou d’identification. Pour l’identification des surfaces, on explore l’utilisation de fonctions distance ou distance orientée, et d’ensembles de niveau comme chez S. Osher et R. Fedkiw ; pour la comparaison de surfaces, on présente les constructions des métriques de Courant par A. M. Micheletti en 1972 et le point de vue de R. Azencott et A. Trouvé en 1995 qui consistent à générer des déformations d’une surface de référence via une famille de difféomorphismes. L’accent est mis sur les fondations mathématiques sous-jacentes que l’on a essayé de clarifier lorsque nécessaire, et, le cas échéant, sur l’exploration d’autres avenues.

Speaker identification using models for phonemes

Motivation for Speaker recognition work is presented in the first part of the thesis. An exhaustive survey of past work in this field is also presented. A low cost system not including complex computation has been chosen for implementation. Towards achieving this a PC based system is designed and developed. A front end analog to digital convertor (12 bit) is built and interfaced to a PC. Software to control the ADC and to perform various analytical functions including feature vector evaluation is developed. It is shown that a fixed set of phrases incorporating evenly balanced phonemes is aptly suited for the speaker recognition work at hand. A set of phrases are chosen for recognition. Two new methods are adopted for the feature evaluation. Some new measurements involving a symmetry check method for pitch period detection and ACE‘ are used as featured. Arguments are provided to show the need for a new model for speech production. Starting from heuristic, a knowledge based (KB) speech production model is presented. In this model, a KB provides impulses to a voice producing mechanism and constant correction is applied via a feedback path. It is this correction that differs from speaker to speaker. Methods of defining measurable parameters for use as features are described. Algorithms for speaker recognition are developed and implemented. Two methods are presented. The first is based on the model postulated. Here the entropy on the utterance of a phoneme is evaluated. The transitions of voiced regions are used as speaker dependent features. The second method presented uses features found in other works, but evaluated differently. A knock—out scheme is used to provide the weightage values for the selection of features. Results of implementation are presented which show on an average of 80% recognition. It is also shown that if there are long gaps between sessions, the performance deteriorates and is speaker dependent. Cross recognition percentages are also presented and this in the worst case rises to 30% while the best case is 0%. Suggestions for further work are given in the concluding chapter.

Automatic diagnosis of voltage disturbances in power distribution networks

This thesis proposes a framework for identifying the root-cause of a voltage disturbance, as well as, its source location (upstream/downstream) from the monitoring place. The framework works with three-phase voltage and current waveforms collected in radial distribution networks without distributed generation. Real-world and synthetic waveforms are used to test it. The framework involves features that are conceived based on electrical principles, and assuming some hypothesis on the analyzed phenomena. Features considered are based on waveforms and timestamp information. Multivariate analysis of variance and rule induction algorithms are applied to assess the amount of meaningful information explained by each feature, according to the root-cause of the disturbance and its source location. The obtained classification rates show that the proposed framework could be used for automatic diagnosis of voltage disturbances collected in radial distribution networks. Furthermore, the diagnostic results can be subsequently used for supporting power network operation, maintenance and planning.

Automatic internal calibration in liquid chromatography/Fourier transform ion cyclotron resonance mass spectrometry of protein digests

Accurately measured peptide masses can be used for large-scale protein identification from bacterial whole-cell digests as an alternative to tandem mass spectrometry (MS/MS) provided mass measurement errors of a few parts-per-million (ppm) are obtained. Fourier transform ion cyclotron resonance (FTICR) mass spectrometry (MS) routinely achieves such mass accuracy either with internal calibration or by regulating the charge in the analyzer cell. We have developed a novel and automated method for internal calibration of liquid chromatography (LC)/FTICR data from whole-cell digests using peptides in the sample identified by concurrent MS/MS together with ambient polydimethyl-cyclosiloxanes as internal calibrants in the mass spectra. The method reduced mass measurement error from 4.3 +/- 3.7 ppm to 0.3 +/- 2.3 ppm in an E. coli LC/FTICR dataset of 1000 MS and MS/MS spectra and is applicable to all analyses of complex protein digests by FTICRMS. Copyright (c) 2006 John Wiley & Sons, Ltd.

Identification of nonlinear systems using generalized kernel models

Nonlinear system identification is considered using a generalized kernel regression model. Unlike the standard kernel model, which employs a fixed common variance for all the kernel regressors, each kernel regressor in the generalized kernel model has an individually tuned diagonal covariance matrix that is determined by maximizing the correlation between the training data and the regressor using a repeated guided random search based on boosting optimization. An efficient construction algorithm based on orthogonal forward regression with leave-one-out (LOO) test statistic and local regularization (LR) is then used to select a parsimonious generalized kernel regression model from the resulting full regression matrix. The proposed modeling algorithm is fully automatic and the user is not required to specify any criterion to terminate the construction procedure. Experimental results involving two real data sets demonstrate the effectiveness of the proposed nonlinear system identification approach.

Comparison of bottom-up protein identification methods

With the rapid development of proteomics, a number of different methods appeared for the basic task of protein identification. We made a simple comparison between a common liquid chromatography-tandem mass spectrometry (LC-MS/MS) workflow using an ion trap mass spectrometer and a combined LC-MS and LC-MS/MS method using Fourier transform ion cyclotron resonance (FTICR) mass spectrometry and accurate peptide masses. To compare the two methods for protein identification, we grew and extracted proteins from E. coli using established protocols. Cystines were reduced and alkylated, and proteins digested by trypsin. The resulting peptide mixtures were separated by reversed-phase liquid chromatography using a 4 h gradient from 0 to 50% acetonitrile over a C18 reversed-phase column. The LC separation was coupled on-line to either a Bruker Esquire HCT ion trap or a Bruker 7 tesla APEX-Qe Qh-FTICR hybrid mass spectrometer. Data-dependent Qh-FTICR-MS/MS spectra were acquired using the quadrupole mass filter and collisionally induced dissociation into the external hexapole trap. Proteins were in both schemes identified by Mascot MS/MS ion searches and the peptides identified from these proteins in the FTICR MS/MS data were used for automatic internal calibration of the FTICR-MS data, together with ambient polydimethylcyclosiloxane ions.

Linear-wavelet models for system identification

A model structure comprising a wavelet network and a linear term is proposed for nonlinear system identification. It is shown that under certain conditions wavelets are orthogonal to linear functions and, as a result, the two parts of the model can be identified separately. The linear-wavelet model is compared to a standard wavelet network using data from a simulated fermentation process. The results show that the linear-wavelet model yields a smaller modelling error when compared to a wavelet network using the same number of regressors.

Fractal dimension applied to plant identification

This article discusses methods to identify plants by analysing leaf complexity based on estimating their fractal dimension. Leaves were analyzed according to the complexity of their internal and external shapes. A computational program was developed to process, analyze and extract the features of leaf images, thereby allowing for automatic plant identification. Results are presented from two experiments, the first to identify plant species from the Brazilian Atlantic forest and Brazilian Cerrado scrublands, using fifty leaf samples from ten different species, and the second to identify four different species from genus Passiflora, using twenty leaf samples for each class. A comparison is made of two methods to estimate fractal dimension (box-counting and multiscale Minkowski). The results are discussed to determine the best approach to analyze shape complexity based on the performance of the technique, when estimating fractal dimension and identifying plants. (C) 2008 Elsevier Inc. All rights reserved.

New Improvements in Automatic Structure Elucidation Using the LSD (Logic for Structure Determination) and the SISTEMAT Expert Systems

This article describes the integration of the LSD (Logic for Structure Determination) and SISTEMAT expert systems that were both designed for the computer-assisted structure elucidation of small organic molecules. A first step has been achieved towards the linking of the SISTEMAT database with the LSD structure generator. The skeletal descriptions found by the SISTEMAT programs are now easily transferred to LSD as substructural constraints. Examples of the synergy between these expert systems are given for recently reported natural products.

Automatic Classification of Three-Phase Flow Patterns of Heavy Oil in a Horizontal Pipe Using Support Vector Machines

The pipe flow of a viscous-oil-gas-water mixture such as that involved in heavy oil production is a rather complex thereto-fluid dynamical problem. Considering the complexity of three-phase flow, it is of fundamental importance the introduction of a flow pattern classification tool to obtain useful information about the flow structure. Flow patterns are important because they indicate the degree of mixing during flow and the spatial distribution of phases. In particular, the pressure drop and temperature evolution along the pipe is highly dependent on the spatial configuration of the phases. In this work we investigate the three-phase water-assisted flow patterns, i.e. those configurations where water is injected in order to reduce friction caused by the viscous oil. Phase flow rates and pressure drop data from previous laboratory experiments in a horizontal pipe are used for flow pattern identification by means of the 'support vector machine' technique (SVM).

Automated NMR structure determination and disulfide bond identification of the myotoxin crotamine from Crotalus durissus terrificus

Crotamine is one of four major components of the venom of the South American rattlesnake Crotalus durissus terrificus. Similar to its counterparts in the family of the myotoxins, it induces myonecrosis of skeletal muscle cells. This paper describes a new NMR structure determination of crotamine in aqueous solution at pH 5.8 and 20 degrees C, using standard homonuclear (1)H NMR spectroscopy at 900 MHz and the automated structure calculation software ATNOS/CANDID/DYANA. The automatic NOESY spectral analysis included the identification of a most likely combination of the six cysteines into three disulfide bonds, i.e. Cys4-Cys36, Cys11-Cys30 and Cys18-Cys37; thereby a generally applicable new computational protocol is introduced to determine unknown disulfide bond connectivities in globular proteins. A previous NMR structure determination was thus confirmed and the structure refined. Crotamine contains an alpha-helix with residues 1-7 and a two-stranded anti-parallel beta-sheet with residues 9-13 and 34-38 as the only regular secondary structures. These are connected with each other and the remainder of the polypeptide chain by the three disulfide bonds, which also form part of a central hydrophobic core. A single conformation was observed, with Pro13 and Pro21 in the trans and Pro20 in the cis-form. The global fold and the cysteine-pairing pattern of crotamine are similar to the beta-defensin fold, although the two proteins have low sequence homology, and display different biological activities. (c) 2005 Elsevier Ltd. All rights reserved.

Fusion of fingerprint recognition methods for robust human identification

Biometrics is one of the biggest tendencies in human identification. The fingerprint is the most widely used biometric. However considering the automatic fingerprint recognition a completely solved problem is a common mistake. The most popular and extensively used methods, the minutiae-based, do not perform well on poor-quality images and when just a small area of overlap between the template and the query images exists. The use of multibiometrics is considered one of the keys to overcome the weakness and improve the accuracy of biometrics systems. This paper presents the fusion of a minutiae-based and a ridge-based fingerprint recognition method at rank, decision and score level. The fusion techniques implemented leaded to a reduction of the Equal Error Rate by 31.78% (from 4.09% to 2.79%) and a decreasing of 6 positions in the rank to reach a Correct Retrieval (from rank 8 to 2) when assessed in the FVC2002-DB1A database. © 2008 IEEE.

Fast non-technical losses identification through Optimum-Path Forest

Fraud detection in energy systems by illegal consumers is the most actively pursued study in non-technical losses by electric power companies. Commonly used supervised pattern recognition techniques, such as Artificial Neural Networks and Support Vector Machines have been applied for automatic commercial frauds identification, however they suffer from slow convergence and high computational burden. We introduced here the Optimum-Path Forest classifier for a fast non-technical losses recognition, which has been demonstrated to be superior than neural networks and similar to Support Vector Machines, but much faster. Comparisons among these classifiers are also presented. © 2009 IEEE.

Parkinson's disease identification through Optimum-Path Forest

Artificial intelligence techniques have been extensively used for the identification of several disorders related with the voice signal analysis, such as Parkinson's disease (PD). However, some of these techniques flaw by assuming some separability in the original feature space or even so in the one induced by a kernel mapping. In this paper we propose the PD automatic recognition by means of Optimum-Path Forest (OPF), which is a new recently developed pattern recognition technique that does not assume any shape/separability of the classes/feature space. The experiments showed that OPF outperformed Support Vector Machines, Artificial Neural Networks and other commonly used supervised classification techniques for PD identification. © 2010 IEEE.