Maximum likelihood Linear Programming Data Fusion for Speaker Recognition

Biometric system performance can be improved by means of data fusion. Several kinds of information can be fused in order to obtain a more accurate classification (identification or verification) of an input sample. In this paper we present a method for computing the weights in a weighted sum fusion for score combinations, by means of a likelihood model. The maximum likelihood estimation is set as a linear programming problem. The scores are derived from a GMM classifier working on a different feature extractor. Our experimental results assesed the robustness of the system in front a changes on time (different sessions) and robustness in front a change of microphone. The improvements obtained were significantly better (error bars of two standard deviations) than a uniform weighted sum or a uniform weighted product or the best single classifier. The proposed method scales computationaly with the number of scores to be fussioned as the simplex method for linear programming.

Hand detection in cluttered scene images using Fourier-Mellin invariant features

This paper proposes an automatic hand detection system that combines the Fourier-Mellin Transform along with other computer vision techniques to achieve hand detection in cluttered scene color images. The proposed system uses the Fourier-Mellin Transform as an invariant feature extractor to perform RST invariant hand detection. In a first stage of the system a simple non-adaptive skin color-based image segmentation and an interest point detector based on corners are used in order to identify regions of interest that contains possible matches. A sliding window algorithm is then used to scan the image at different scales performing the FMT calculations only in the previously detected regions of interest and comparing the extracted FM descriptor of the windows with a hand descriptors database obtained from a train image set. The results of the performed experiments suggest the use of Fourier-Mellin invariant features as a promising approach for automatic hand detection.

Hand detection in cluttered scene images using Fourier-Mellin invariant features

This paper proposes an automatic hand detection system that combines the Fourier-Mellin Transform along with other computer vision techniques to achieve hand detection in cluttered scene color images. The proposed system uses the Fourier-Mellin Transform as an invariant feature extractor to perform RST invariant hand detection. In a first stage of the system a simple non-adaptive skin color-based image segmentation and an interest point detector based on corners are used in order to identify regions of interest that contains possible matches. A sliding window algorithm is then used to scan the image at different scales performing the FMT calculations only in the previously detected regions of interest and comparing the extracted FM descriptor of the windows with a hand descriptors database obtained from a train image set. The results of the performed experiments suggest the use of Fourier-Mellin invariant features as a promising approach for automatic hand detection.

Experiencias de interoperabilidad entre CRIS y repositorios en Catalunya

Toni Prieto, Técnico IC del Servicio de Bibliotecas y Documentación (SBD) de la UPC, en su presentación 'Experiencias de interoperabilidad entre CRIS y repositorios en Catalunya', describió la integración del repositorio UPCommons y del CRIS DRAC (Descriptor de la Recerca i l'Activitat Acadèmica) de la UPC. El resultado de esta integración es un esquema integrado de archivo CRIS/IR en dos fases, envío y revisión, en el que los metadatos se introducen en DRAC -para posteriormente ser transferidos, validados y enriquecidos si procede- y el archivo de texto completo asociado se realiza en UPCommons. De manera similar funciona la integración de GIR (Gestió Integral de la Recerca, basado en Universitas XXI Investigación) y el repositorio O2 en la UOC, permitiendo la asignación del identificador handle de un ítem en O2 a una referencia en GIR. Ambos sistemas, DRAC en la UPC y GIR en la UOC, están integrados en el Proyecto CVN de generación de CVs normalizados. Se mencionaron asimismo experiencias posteriores de integración CRIS/IR actualmente en curso en la Universitat de Barcelona y en la U Pompeu Fabra, y se mostró el impacto significativo de la estrategia de integración de sistemas sobre el ritmo de incorporación de contenidos a UPCommons.

Visualizing key authenticity: turning your face into your public key

La informació biomètrica s'ha convertit en una tecnologia complementària a la criptografia que permet administrar còmodament les dades criptogràfiques. Són útils dues necessitats importants: en primer lloc, posar aquestes dades sempre a mà i, a més, fent fàcilment identificable el seu legítim propietari. En aquest article es proposa un sistema que integra la signatura biomètrica de reconeixement facial amb un esquema de signatura basat en la identitat, de manera que la cara de l'usuari esdevé la seva clau pública i la ID del sistema. D'aquesta manera, altres usuaris poden verificar els missatges utilitzant fotos del remitent, proporcionant un intercanvi raonable entre la seguretat del sistema i la usabilitat, així com una manera molt més senzilla d'autenticar claus públiques i processos de distribució.

6.2

Airborne particles can come from a variety of sources and contain variable chemical constituents. Some particles are formed by natural processes, such as volcanoes, erosion, sea spray, and forest fires, while other are formed by anthropogenic processes, such as industrial- and motor vehicle-related combustion, road-related wear, and mining. In general, larger particles (those greater than 2.5 μm) are formed by mechanical processes, while those less than 2.5 μm are formed by combustion processes. The chemical composition of particles is highly influenced by the source: for combustion-related particles, factors such as temperature of combustion, fuel type, and presence of oxygen or other gases can also have a large impact on PM composition. These differences can often be observed at a regional level, such as the greater sulphate-composition of PM in regions that burn coal for electricity production (which contains sulphur) versus regions that do not. Most countries maintain air monitoring networks, and studies based on the resulting data are the most common basis for epidemiology studies on the health effects of PM. Data from these monitoring stations can be used to evaluate the relationship between community-level exposure to ambient particles and health outcomes (i.e., morbidity or mortality from various causes). Respiratory and cardiovascular outcomes are the most commonly assessed, although studies have also considered other related specific outcomes such as diabetes and congenital heart disease. The data on particle characteristics is usually not very detailed and most often includes some combination of PM2.5, PM10, sulphate, and NO2. Other descriptors that are less commonly found include particle number (ultrafine particles), metal components of PM, local traffic intensity, and EC/OC. Measures of association are usually reported per 10 μg/m3 or interquartile range increase in pollutant concentration. As the exposure data are taken from regional monitoring stations, the measurements are not representative of an individual's exposure. Particle size is an important descriptor for understanding where in the human respiratory system the particles will deposit: as a general rule, smaller particles penetrate to deeper regions of the lungs. Initial studies on the health effects of particulate matter focused on mass of the particles, including either all particles (often termed total suspended particulate or TSP) or PM10 (all particles with an aerodynamic diameter less than 10 μm). More recently, studies have considered both PM10 and PM2.5, with the latter corresponding more directly to combustion-related processes. UFPs are a dominant source of particles in terms of PNC, yet are negligible in terms of mass. Very few epidemiology studies have measured the effect of UFPs on health; however, the numbers of studies on this topic are increasing. In addition to size, chemical composition is of importance when understanding the toxicity of particles. Some studies consider the composition of particles in addition to mass; however this is not common, in part due the cost and labour involved in such analyses.

Selection of the most informative morphoagronomic descriptors for cassava germplasm

The objective of this work was to select the most informative morphoagronomic descriptors for cassava (Manihot esculenta) germplasm and to evaluate the ability of different methods to select the descriptors. Ninety-five accessions were characterized using 51 morphoagronomic descriptors. Data were subjected to a multiple correspondence analysis (MCA), whose information was used in the following four methods of descriptor selection: reverse order of the descriptor for the pth factorial axis of the MCA (Jolliffe); sequential, multiple correspondence analysis (SMCA); mean of the contribution orders of the descriptor in the first three factorial axes (C3PA); and C3PA method weighted by the respective eigenvalues of the full analysis (C3PAWeig). The correlations between the dissimilarity matrix with all descriptors and the most informative descriptors were high and significant (0.75, 0.77, 0.83, and 0.84 for C3PAWeig, C3PA, SMCA, and Jolliffe, respectively). The less informative descriptors were discarded, considering those common among the selection methods and relevant for the breeding interests. Therefore, 32 morphoagronomic descriptors with correlation between the dissimilarity matrices (r=0.81) were selected, due to their high capacity to discriminate cassava germplasm and to their ability to maintain some preliminary agronomic traits, useful for the initial characterization of the germplasm.

Fish oil replacement by soybean oil in the diet of fat snook juveniles

The objective of this work was to evaluate fish oil replacement by soybean oil in diets, as for the effects on the performance and body composition of juveniles of fat snook (Centropomus parallelus). The experiment was carried out in a randomized block design, with three treatments (lipid sources) and six replicates, in a 60-day period. Fat snook juveniles (24.17±0.28g) were distributed in 18 experimental tanks of 200 L each, equipped with aeration and heating systems, under continuous water renovation (800% per day). Three isoproteic (44% CP) and isoenergetic (4,635 kcal CE kg-1) diets were formulated to comprise three replacement rates (0, 50, and 100%) of fish oil by soybean oil. Biometric analyses were done to evaluate fish performance, and two entire specimens from each replicate were used for body composition analyses. The zootechnical indices of weight gain (38.68±5.41 g), feed conversion (1.38±0.10), and specific growth at 1.70±0.18% weight gain per day were considered satisfactory. Lipid source substitution does not affect the performance and body composition of fat snook juveniles, which suggests that soybean oil can replace fish oil in diet formulation.

The use of positional scanning synthetic combinatorial libraries (PS-SCL) to study T Lympohcyte specificity and degeneracy

Les cellules CD8? T cytolytiques (CTL) sont les principaux effecteurs du système immunitaire adaptatif contre les infections et les tumeurs. La récente identification d?antigènes tumoraux humains reconnus par des cellules T cytolytiques est la base pour le, développement des vaccins antigène spécifiques contre le cancer. Le nombre d?antigènes tumoraux reconnus par des CTL que puisse être utilisé comme cible pour la vaccination des patients atteints du cancer est encore limité. Une nouvelle technique, simple et rapide, vient d?être proposée pour l?identification d?antigènes reconnus par des CTL. Elle se base sur l?utilisation de librairies combinatoriales de peptides arrangées en un format de "scanning" ou balayage par position (PS-SCL). La première partie de cette étude a consisté à valider cette nouvelle technique par une analyse détaillée de la reconnaissance des PS-SCL par différents clones de CTL spécifiques pour des antigènes associés à la tumeur (TAA) connus ainsi que par des clones de spécificité inconnue. Les résultats de ces analyses révèlent que pour tous les clones, la plupart des acides aminés qui composent la séquence du peptide antigénique naturel ont été identifiés par l?utilisation des PS-SCL. Les résultats obtenus ont permis d?identifier des peptides analogues ayant une antigènicité augmentée par rapport au peptide naturel, ainsi que des peptides comportant de multiples modifications de séquence, mais présentant la même réactivité que le peptide naturel. La deuxième partie de cette étude a consisté à effectuer des analyses biométriques des résultats complexes générés par la PS-SCL. Cette approche a permis l?identification des séquences correspondant aux épitopes naturels à partir de bases de données de peptides publiques. Parmi des milliers de peptides, les séquences naturelles se trouvent comprises dans les 30 séquences ayant les scores potentiels de stimulation les plus élevés pour chaque TAA étudié. Mais plus important encore, l?utilisation des PS-SCL avec un clone réactif contre des cellules tumorales mais de spécificité inconnue nous a permis d?identifier I?epitope reconnu par ce clone. Les données présentées ici encouragent l?utilisation des PS-SCL pour l?identification et l?optimisation d?épitopes pour des CTL réactifs anti-tumoraux, ainsi que pour l?étude de la reconnaissance dégénérée d?antigènes par les CTL.<br/><br/>CD8+ cytolytic T lymphocytes (CTL) are the main effector cells of the adaptive immune system against infection and tumors. The recent identification of moleculariy defined human tumor Ags recognized by autologous CTL has opened new opportunities for the development of Ag-specific cancer vaccines. Despite extensive work, however, the number of CTL-defined tumor Ags that are suitable targets for the vaccination of cancer patients is still limited, especially because of the laborious and time consuming nature of the procedures currentiy used for their identification. The use of combinatorial peptide libraries in positionai scanning format (Positional Scanning Synthetic Combinatorial Libraries, PS-SCL)' has recently been proposed as an alternative approach for the identification of these epitopes. To validate this approach, we analyzed in detail the recognition of PS-SCL by tumor-reactive CTL clones specific for multiple well-defined tumor-associated Ags (TAA) as well as by tumor-reactive CTL clones of unknown specificity. The results of these analyses revealed that for all the TAA-specific clones studied most of the amino acids composing the native antigenic peptide sequences could be identified through the use of PS-SCL. Based on the data obtained from the screening of PS-SCL, we could design peptide analogs of increased antigenicity as well as cross-reactive analog peptides containing multiple amino acid substitutions. In addition, the resuits of PS-SCL-screening combined with a recently developed biometric data analysis (PS-SCL-based biometric database analysis) allowed the identification of the native peptides in public protein databases among the 30 most active sequences, and this was the case for all the TAA studied. More importantiy, the screening of PS- SCL with a tumor-reactive CTL clone of unknown specificity resulted in the identification of the actual epitope. Overall, these data encourage the use of PS-SCL not oniy for the identification and optimization of tumor-associated CTL epitopes, but also for the analysis of degeneracy in T lymphocyte receptor (TCR) recognition of tumor Ags.<br/><br/>Les cellules T CD8? cytolytiques font partie des globules blancs du sang et sont les principales responsables de la lutte contre les infections et les tumeurs. Les immunologistes cherchent depuis des années à identifier des molécules exprimées et présentées à la surface des tumeurs qui puissent être reconnues par des cellules T CD8? cytolytiques capables ensuite de tuer ces tumeurs de façon spécifique. Ce type de molécules représente la base pour le développement de vaccins contre le cancer puisqu?elles pourraient être injectées aux patients afin d?induire une réponse anti- tumorale. A présent, il y a très peu de molécules capables de stimuler le système immunitaire contre les tumeurs qui sont connues parce que les techniques développées à ce jour pour leur identification sont complexes et longues. Une nouvelle technique vient d?être proposée pour l?identification de ce type de molécules qui se base sur l?utilisation de librairies de peptides. Ces librairies représentent toutes les combinaisons possibles des composants de base des molécules recherchées. La première partie de cette étude a consisté à valider cette nouvelle technique en utilisant des cellules T CD8? cytolytiques capables de tuer des cellules tumorales en reconnaissant une molécule connue présente à leur surface. On a démontré que l?utilisation des librairies permet d?identifier la plupart des composants de base de la molécule reconnue par les cellules T CD8? cytolytiques utilisées. La deuxième partie de cette étude a consisté à effectuer une recherche des molécules potentiellement actives dans des protéines présentes dans des bases des données en utilisant un programme informatique qui permet de classer les molécules sur la base de leur activité biologique. Parmi des milliers de molécules de la base de données, celles reconnues par nos cellules T CD8? cytolytiques ont été trouvées parmi les plus actives. Plus intéressant encore, la combinaison de ces deux techniques nous a permis d?identifier la molécule reconnue par une population de cellules T CD8? cytolytiques ayant une activité anti-tumorale, mais pour laquelle on ne connaissait pas la spécificité. Nos résultats encouragent l?utilisation des librairies pour trouver et optimiser des molécules reconnues spécifiquement par des cellules T CD8? cytolytiques capables de tuer des tumeurs.

Supervised localimage feature detection

This thesis is about detection of local image features. The research topic belongs to the wider area of object detection, which is a machine vision and pattern recognition problem where an object must be detected (located) in an image. State-of-the-art object detection methods often divide the problem into separate interest point detection and local image description steps, but in this thesis a different technique is used, leading to higher quality image features which enable more precise localization. Instead of using interest point detection the landmark positions are marked manually. Therefore, the quality of the image features is not limited by the interest point detection phase and the learning of image features is simplified. The approach combines both interest point detection and local description into one phase for detection. Computational efficiency of the descriptor is therefore important, leaving out many of the commonly used descriptors as unsuitably heavy. Multiresolution Gabor features has been the main descriptor in this thesis and improving their efficiency is a significant part. Actual image features are formed from descriptors by using a classifierwhich can then recognize similar looking patches in new images. The main classifier is based on Gaussian mixture models. Classifiers are used in one-class classifier configuration where there are only positive training samples without explicit background class. The local image feature detection method has been tested with two freely available face detection databases and a proprietary license plate database. The localization performance was very good in these experiments. Other applications applying the same under-lying techniques are also presented, including object categorization and fault detection.

ÄÄNEEN PERUSTUVA KÄYTTÄJÄN TODENTAMINEN PUHELINVERKON LISÄARVOPALVELUISSA

Tässä diplomityössä perehdytään puhujantunnistukseen ja sen käyttökelpoisuuteen käyttäjän henkilöllisyyden todentamisessa osana puhelinverkon lisäarvopalveluja. Puhelimitse ohjattavat palvelut ovat yleensä perustuneet puhelimen näppäimillä lähetettäviin äänitaajuusvalintoihin. Käyttäjän henkilöllisyydestä on voitu varmistua esimerkiksi käyttäjätunnuksen ja salaisen tunnusluvun perusteella. Tulevaisuudessa palvelut voivat perustua puheentunnistukseen, jolloin myös käyttäjän todentaminen äänen perusteella vaikuttaa järkevältä. Työssä esitellään aluksi erilaisia biometrisiä tunnistamismenetelmiä. Työssä perehdytään tarkemmin äänen perusteella tapahtuvaan puhujan todentamiseen. Työn käytännön osuudessa toteutettiin puhelinverkon palveluihin soveltuva puhujantodennussovelluksen prototyyppi. Työn tarkoituksena oli selvittää teknologian käyttömahdollisuuksia sekä kerätä kokemusta puhujantodennuspalvelun toteuttamisesta tulevaisuutta silmällä pitäen. Prototyypin toteutuksessa ohjelmointikielenä käytettiin Javaa.

Reducción del vector de características de reconocimiento facial

In this present work, we are proposing a characteristics reduction system for a facial biometric identification system, using transformed domains such as discrete cosine transformed (DCT) and discrete wavelets transformed (DWT) as parameterization; and Support Vector Machines (SVM) and Neural Network (NN) as classifiers. The size reduction has been done with Principal Component Analysis (PCA) and with Independent Component Analysis (ICA). This system presents a similar success results for both DWT-SVM system and DWT-PCA-SVM system, about 98%. The computational load is improved on training mode due to the decreasing of input’s size and less complexity of the classifier.

Protein pocket and ligand shape comparison and its application in virtual screening.

Understanding molecular recognition is one major requirement for drug discovery and design. Physicochemical and shape complementarity between two binding partners is the driving force during complex formation. In this study, the impact of shape within this process is analyzed. Protein binding pockets and co-crystallized ligands are represented by normalized principal moments of inertia ratios (NPRs). The corresponding descriptor space is triangular, with its corners occupied by spherical, discoid, and elongated shapes. An analysis of a selected set of sc-PDB complexes suggests that pockets and bound ligands avoid spherical shapes, which are, however, prevalent in small unoccupied pockets. Furthermore, a direct shape comparison confirms previous studies that on average only one third of a pocket is filled by its bound ligand, supplemented by a 50 % subpocket coverage. In this study, we found that shape complementary is expressed by low pairwise shape distances in NPR space, short distances between the centers-of-mass, and small deviations in the angle between the first principal ellipsoid axes. Furthermore, it is assessed how different binding pocket parameters are related to bioactivity and binding efficiency of the co-crystallized ligand. In addition, the performance of different shape and size parameters of pockets and ligands is evaluated in a virtual screening scenario performed on four representative targets.

Comparing multiple criteria for species identification in two recently diverged seabirds

Correct species identification is a crucial issue in systematics with key implications for prioritising conservation effort. However, it can be particularly challenging in recently diverged species due to their strong similarity and relatedness. In such cases, species identification requires multiple and integrative approaches. In this study we used multiple criteria, namely plumage colouration, biometric measurements, geometric morphometrics, stable isotopes analysis (SIA) and genetics (mtDNA), to identify the species of 107 bycatch birds from two closely related seabird species, the Balearic (Puffinus mauretanicus) and Yelkouan (P. yelkouan) shearwaters. Biometric measurements, stable isotopes and genetic data produced two stable clusters of bycatch birds matching the two study species, as indicated by reference birds of known origin. Geometric morphometrics was excluded as a species identification criterion since the two clusters were not stable. The combination of plumage colouration, linear biometrics, stable isotope and genetic criteria was crucial to infer the species of 103 of the bycatch specimens. In the present study, particularly SIA emerged as a powerful criterion for species identification, but temporal stability of the isotopic values is critical for this purpose. Indeed, we found some variability in stable isotope values over the years within each species, but species differences explained most of the variance in the isotopic data. Yet this result pinpoints the importance of examining sources of variability in the isotopic data in a case-by-case basis prior to the cross-application of the SIA approach to other species. Our findings illustrate how the integration of several methodological approaches can help to correctly identify individuals from recently diverged species, as each criterion measures different biological phenomena and species divergence is not expressed simultaneously in all biological traits.

Features extraction based on the Discrete Hartley Transform for closed contour

In this paper the authors propose a new closed contour descriptor that could be seen as a Feature Extractor of closed contours based on the Discrete Hartley Transform (DHT), its main characteristic is that uses only half of the coefficients required by Elliptical Fourier Descriptors (EFD) to obtain a contour approximation with similar error measure. The proposed closed contour descriptor provides an excellent capability of information compression useful for a great number of AI applications. Moreover it can provide scale, position and rotation invariance, and last but not least it has the advantage that both the parameterization and the reconstructed shape from the compressed set can be computed very efficiently by the fast Discrete Hartley Transform (DHT) algorithm. This Feature Extractor could be useful when the application claims for reversible features and when the user needs and easy measure of the quality for a given level of compression, scalable from low to very high quality.