New methodology for the integration of biometric features in speaker recognition systems applied to security environments

La cuestión principal abordada en esta tesis doctoral es la mejora de los sistemas biométricos de reconocimiento de personas a partir de la voz, proponiendo el uso de una nueva parametrización, que hemos denominado parametrización biométrica extendida dependiente de género (GDEBP en sus siglas en inglés). No se propone una ruptura completa respecto a los parámetros clásicos sino una nueva forma de utilizarlos y complementarlos. En concreto, proponemos el uso de parámetros diferentes dependiendo del género del locutor, ya que como es bien sabido, la voz masculina y femenina presentan características diferentes que deberán modelarse, por tanto, de diferente manera. Además complementamos los parámetros clásicos utilizados (MFFC extraídos de la señal de voz), con un nuevo conjunto de parámetros extraídos a partir de la deconstrucción de la señal de voz en sus componentes de fuente glótica (más relacionada con el proceso y órganos de fonación y por tanto con características físicas del locutor) y de tracto vocal (más relacionada con la articulación acústica y por tanto con el mensaje emitido). Para verificar la validez de esta propuesta se plantean diversos escenarios, utilizando diferentes bases de datos, para validar que la GDEBP permite generar una descripción más precisa de los locutores que los parámetros MFCC clásicos independientes del género. En concreto se plantean diferentes escenarios de identificación sobre texto restringido y texto independiente utilizando las bases de datos de HESPERIA y ALBAYZIN. El trabajo también se completa con la participación en dos competiciones internacionales de reconocimiento de locutor, NIST SRE (2010 y 2012) y MOBIO 2013. En el primer caso debido a la naturaleza de las bases de datos utilizadas se obtuvieron resultados cercanos al estado del arte, mientras que en el segundo de los casos el sistema presentado obtuvo la mejor tasa de reconocimiento para locutores femeninos. A pesar de que el objetivo principal de esta tesis no es el estudio de sistemas de clasificación, sí ha sido necesario analizar el rendimiento de diferentes sistemas de clasificación, para ver el rendimiento de la parametrización propuesta. En concreto, se ha abordado el uso de sistemas de reconocimiento basados en el paradigma GMM-UBM, supervectores e i-vectors. Los resultados que se presentan confirman que la utilización de características que permitan describir los locutores de manera más precisa es en cierto modo más importante que la elección del sistema de clasificación utilizado por el sistema. En este sentido la parametrización propuesta supone un paso adelante en la mejora de los sistemas de reconocimiento biométrico de personas por la voz, ya que incluso con sistemas de clasificación relativamente simples se consiguen tasas de reconocimiento realmente competitivas. ABSTRACT The main question addressed in this thesis is the improvement of automatic speaker recognition systems, by the introduction of a new front-end module that we have called Gender Dependent Extended Biometric Parameterisation (GDEBP). This front-end do not constitute a complete break with respect to classical parameterisation techniques used in speaker recognition but a new way to obtain these parameters while introducing some complementary ones. Specifically, we propose a gender-dependent parameterisation, since as it is well known male and female voices have different characteristic, and therefore the use of different parameters to model these distinguishing characteristics should provide a better characterisation of speakers. Additionally, we propose the introduction of a new set of biometric parameters extracted from the components which result from the deconstruction of the voice into its glottal source estimate (close related to the phonation process and the involved organs, and therefore the physical characteristics of the speaker) and vocal tract estimate (close related to acoustic articulation and therefore to the spoken message). These biometric parameters constitute a complement to the classical MFCC extracted from the power spectral density of speech as a whole. In order to check the validity of this proposal we establish different practical scenarios, using different databases, so we can conclude that a GDEBP generates a more accurate description of speakers than classical approaches based on gender-independent MFCC. Specifically, we propose scenarios based on text-constrain and text-independent test using HESPERIA and ALBAYZIN databases. This work is also completed with the participation in two international speaker recognition evaluations: NIST SRE (2010 and 2012) and MOBIO 2013, with diverse results. In the first case, due to the nature of the NIST databases, we obtain results closed to state-of-the-art although confirming our hypothesis, whereas in the MOBIO SRE we obtain the best simple system performance for female speakers. Although the study of classification systems is beyond the scope of this thesis, we found it necessary to analise the performance of different classification systems, in order to verify the effect of them on the propose parameterisation. In particular, we have addressed the use of speaker recognition systems based on the GMM-UBM paradigm, supervectors and i-vectors. The presented results confirm that the selection of a set of parameters that allows for a more accurate description of the speakers is as important as the selection of the classification method used by the biometric system. In this sense, the proposed parameterisation constitutes a step forward in improving speaker recognition systems, since even when using relatively simple classification systems, really competitive recognition rates are achieved.

Endolymphatic sac tumor : A report of 2 cases with long term follow-up

Trabalho Final do Curso de Mestrado Integrado em Medicina, Faculdade de Medicina, Universidade de Lisboa, 2014

Optimal image colour extraction by differential evolution

Differential evolution is an optimisation technique that has been successfully employed in various applications. In this paper, we apply differential evolution to the problem of extracting the optimal colours of a colour map for quantised images. The choice of entries in the colour map is crucial for the resulting image quality as it forms a look-up table that is used for all pixels in the image. We show that differential evolution can be effectively employed as a method for deriving the entries in the map. In order to optimise the image quality, our differential evolution approach is combined with a local search method that is guaranteed to find the local optimal colour map. This hybrid approach is shown to outperform various commonly used colour quantisation algorithms on a set of standard images. Copyright © 2010 Inderscience Enterprises Ltd.

Event mining for system and service management

Modern IT infrastructures are constructed by large scale computing systems and administered by IT service providers. Manually maintaining such large computing systems is costly and inefficient. Service providers often seek automatic or semi-automatic methodologies of detecting and resolving system issues to improve their service quality and efficiency. This dissertation investigates several data-driven approaches for assisting service providers in achieving this goal. The detailed problems studied by these approaches can be categorized into the three aspects in the service workflow: 1) preprocessing raw textual system logs to structural events; 2) refining monitoring configurations for eliminating false positives and false negatives; 3) improving the efficiency of system diagnosis on detected alerts. Solving these problems usually requires a huge amount of domain knowledge about the particular computing systems. The approaches investigated by this dissertation are developed based on event mining algorithms, which are able to automatically derive part of that knowledge from the historical system logs, events and tickets. ^ In particular, two textual clustering algorithms are developed for converting raw textual logs into system events. For refining the monitoring configuration, a rule based alert prediction algorithm is proposed for eliminating false alerts (false positives) without losing any real alert and a textual classification method is applied to identify the missing alerts (false negatives) from manual incident tickets. For system diagnosis, this dissertation presents an efficient algorithm for discovering the temporal dependencies between system events with corresponding time lags, which can help the administrators to determine the redundancies of deployed monitoring situations and dependencies of system components. To improve the efficiency of incident ticket resolving, several KNN-based algorithms that recommend relevant historical tickets with resolutions for incoming tickets are investigated. Finally, this dissertation offers a novel algorithm for searching similar textual event segments over large system logs that assists administrators to locate similar system behaviors in the logs. Extensive empirical evaluation on system logs, events and tickets from real IT infrastructures demonstrates the effectiveness and efficiency of the proposed approaches.^

Trissoralen um medicamento de baixa dosagem: estudos termoanalíticos da compatibilidade do fármaco-excipientes e determinação de parâmetros de qualidade para cápsulas magistrais

The trioxsalen (Tri) is a low-dose drug used in the treatment of psoriasis and other skin diseases. The aim of the study was applying the thermal analysis and complementary techniques for characterization, evaluation of the trioxsalen stability and components of manipulated pharmaceutical formulations. The thermal behavior of the Tri by TG/DTG-DTA in dynamic atmosphere of synthetic air and nitrogen showed the same profile with a melting peak followed by a volatilization-related event. From the curves TG / DTG is observed a single stage of mass loss. By heating the drug in the stove at temperatures of 80, 240 and 260 °C, it had no change in chemical structure through the techniques of XRD, HPLC, MIR, OM and SEM. From the non-isothermal and isothermal TG kinetic studies was possible to calculate the activation energy and reaction order for the Tri. The drug showed good thermal stability. Studies on drug-excipient compatibility showed interaction of trissoralen with sodium lauryl sulfate 1:1. There was no interaction with aerosol, pregelatinized starch, sodium starch glycolate, cellulose, croscarmellose sodium, magnesium stearate, lactose and mannitol.The characterization of three trioxsalen formulations at concentrations of 2.5, 5, 7.5, 10, 12.5 and 15 mg was performed by DSC, TG / DTG, XRD, NIR and MIR. The PCA classification method based on spectral data from the NIR and MIR of trissoralen formulations allows successful differentiation into three groups. The formulation 3 was the one that best showed analytical profile with the following composition of aerosil excipients, pre-gelatinized starch and cellulose. The activation energy of the volatilization process of the drug was determined in binary mixtures and formulation 3 through fitting and isoconversional methods. The binary mixture with sodium starch glycolate and lactose showed differences in kinetic parameters compared to the drug isolated. The thermoanalytical techniques (DSC and TG / DTG) were shown to be promising methodologies for quantifying trioxsalen obtained by the linearity, selectivity, no use solvents, without sample preparation, speed and practicality.

Permanent open water surfaces in central Siberia from ENVISAT ASAR wide swath data 2003/2004, link to shapefile

Permanent water bodies not only store dissolved CO2 but are essential for the maintenance of wetlands in their proximity. From the viewpoint of greenhouse gas (GHG) accounting wetland functions comprise sequestration of carbon under anaerobic conditions and methane release. The investigated area in central Siberia covers boreal and sub-arctic environments. Small inundated basins are abundant on the sub-arctic Taymir lowlands but also in parts of severe boreal climate where permafrost ice content is high and feature important freshwater ecosystems. Satellite radar imagery (ENVISAT ScanSAR), acquired in summer 2003 and 2004, has been used to derive open water surfaces with 150 m resolution, covering an area of approximately 3 Mkm**2. The open water surface maps were derived using a simple threshold-based classification method. The results were assessed with Russian forest inventory data, which includes detailed information about water bodies. The resulting classification has been further used to estimate the extent of tundra wetlands and to determine their importance for methane emissions. Tundra wetlands cover 7% (400,000 km**2) of the study region and methane emissions from hydromorphic soils are estimated to be 45,000 t/d for the Taymir peninsula.

The High-Redshift Quasar Luminosity Function from Multi-Epoch Imaging Surveys

Thesis (Ph.D.)--University of Washington, 2016-08

Mesh partitioning: A multilevel balancing and refinement algorithm

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. In this paper we present an enhancement of the technique which uses imbalance to achieve higher quality partitions. We also present a formulation of the Kernighan-Lin partition optimisation algorithm which incorporates load-balancing. The resulting algorithm is tested against a different but related state-of the-art partitioner and shown to provide improved results.

Multilevel mesh partitioning for optimising domain shape

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem for mapping meshes onto parallel computers. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. To date these algorithms have been used almost exclusively to minimise the cut-edge weight in the graph with the aim of minimising the parallel communication overhead. However it has been shown that for certain classes of problem, the convergence of the underlying solution algorithm is strongly influenced by the shape or aspect ratio of the subdomains. In this paper therefore, we modify the multilevel algorithms in order to optimise a cost function based on aspect ratio. Several variants of the algorithms are tested and shown to provide excellent results.

Multilevel mesh partitioning for optimising subdomain aspect ratio

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem for mapping meshes onto parallel computers. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. To date these algorithms have been used almost exclusively to minimise the cut-edge weight in the graph with the aim of minimising the parallel communication overhead. However it has been shown that for certain classes of problem, the convergence of the underlying solution algorithm is strongly influenced by the shape or aspect ratio of the subdomains. In this paper therefore, we modify the multilevel algorithms in order to optimise a cost function based on aspect ratio. Several variants of the algorithms are tested and shown to provide excellent results.

Multilevel mesh partitioning for aspect ratio

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. To date these algorithms have been used almost exclusively to minimise the cut-edge weight, however it has been shown that for certain classes of solution algorithm, the convergence of the solver is strongly influenced by the subdomain aspect ratio. In this paper therefore, we modify the multilevel algorithms in order to optimise a cost function based on aspect ratio. Several variants of the algorithms are tested and shown to provide excellent results.

Transformada wavelet aplicada a análise automática de oscilografias de curta duração em unidades geradoras

The focus of this work is the automatic analysis of disturbance records for electrical power generating units. The main proposition is a method based on wavelet transform applied to short-term disturbance records (waveform records). The goal of the method is to detect the time instants of recorded disturbances and extract meaningful information that characterize the faults. The result is a set of representative information of the monitored signals in power generators. This information can be further classified by an expert system (or other classification method) in order to classify the faults and other abnormal operating conditions. The large amount of data produced by digital fault recorders during faults justify the research of methods to assist the analysts in their task of analysing the disturbances. The literature review pointed out the state of the art and possible applications for oscillography records. The review of the COMTRADE standard and wavelet transform underlines the choice of the method for solving the problem. The conducted tests lead to the determination of the best mother wavelet for the segmentation process. The application of the proposed method to five case studies with real oscillographic records confirmed the accuracy and efficiency of the proposed scheme. With this research, the post-operation analysis of occurrences is improved and as a direct result is the reduction of the time that generators are offline.

Análise das mudanças espaciais e temporais nos padrões de paisagem na região do oeste da Bahia sobre a formação do grupo urucuia (1988-2011) e suas implicações para a conservação do Cerrado

Tese (doutorado)—Universidade de Brasília, Instituto de Ciências Humanas, Departamento de Geografia, Programa de Pós Graduação em Geografia, 2015.

Active Foreground Region Extraction and Tracking for Sports Video Annotation

Automatic video segmentation plays a vital role in sports videos annotation. This paper presents a fully automatic and computationally efficient algorithm for analysis of sports videos. Various methods of automatic shot boundary detection have been proposed to perform automatic video segmentation. These investigations mainly concentrate on detecting fades and dissolves for fast processing of the entire video scene without providing any additional feedback on object relativity within the shots. The goal of the proposed method is to identify regions that perform certain activities in a scene. The model uses some low-level feature video processing algorithms to extract the shot boundaries from a video scene and to identify dominant colours within these boundaries. An object classification method is used for clustering the seed distributions of the dominant colours to homogeneous regions. Using a simple tracking method a classification of these regions to active or static is performed. The efficiency of the proposed framework is demonstrated over a standard video benchmark with numerous types of sport events and the experimental results show that our algorithm can be used with high accuracy for automatic annotation of active regions for sport videos.

Pattern recognition methods for EMG prosthetic control

In this work we focus on pattern recognition methods related to EMG upper-limb prosthetic control. After giving a detailed review of the most widely used classification methods, we propose a new classification approach. It comes as a result of comparison in the Fourier analysis between able-bodied and trans-radial amputee subjects. We thus suggest a different classification method which considers each surface electrodes contribute separately, together with five time domain features, obtaining an average classification accuracy equals to 75% on a sample of trans-radial amputees. We propose an automatic feature selection procedure as a minimization problem in order to improve the method and its robustness.