980 resultados para GAUSSIAN-BASIS SET


Relevância:

30.00% 30.00%

Publicador:

Resumo:

Automatic recognition of people is an active field of research with important forensic and security applications. In these applications, it is not always possible for the subject to be in close proximity to the system. Voice represents a human behavioural trait which can be used to recognise people in such situations. Automatic Speaker Verification (ASV) is the process of verifying a persons identity through the analysis of their speech and enables recognition of a subject at a distance over a telephone channel { wired or wireless. A significant amount of research has focussed on the application of Gaussian mixture model (GMM) techniques to speaker verification systems providing state-of-the-art performance. GMM's are a type of generative classifier trained to model the probability distribution of the features used to represent a speaker. Recently introduced to the field of ASV research is the support vector machine (SVM). An SVM is a discriminative classifier requiring examples from both positive and negative classes to train a speaker model. The SVM is based on margin maximisation whereby a hyperplane attempts to separate classes in a high dimensional space. SVMs applied to the task of speaker verification have shown high potential, particularly when used to complement current GMM-based techniques in hybrid systems. This work aims to improve the performance of ASV systems using novel and innovative SVM-based techniques. Research was divided into three main themes: session variability compensation for SVMs; unsupervised model adaptation; and impostor dataset selection. The first theme investigated the differences between the GMM and SVM domains for the modelling of session variability | an aspect crucial for robust speaker verification. Techniques developed to improve the robustness of GMMbased classification were shown to bring about similar benefits to discriminative SVM classification through their integration in the hybrid GMM mean supervector SVM classifier. Further, the domains for the modelling of session variation were contrasted to find a number of common factors, however, the SVM-domain consistently provided marginally better session variation compensation. Minimal complementary information was found between the techniques due to the similarities in how they achieved their objectives. The second theme saw the proposal of a novel model for the purpose of session variation compensation in ASV systems. Continuous progressive model adaptation attempts to improve speaker models by retraining them after exploiting all encountered test utterances during normal use of the system. The introduction of the weight-based factor analysis model provided significant performance improvements of over 60% in an unsupervised scenario. SVM-based classification was then integrated into the progressive system providing further benefits in performance over the GMM counterpart. Analysis demonstrated that SVMs also hold several beneficial characteristics to the task of unsupervised model adaptation prompting further research in the area. In pursuing the final theme, an innovative background dataset selection technique was developed. This technique selects the most appropriate subset of examples from a large and diverse set of candidate impostor observations for use as the SVM background by exploiting the SVM training process. This selection was performed on a per-observation basis so as to overcome the shortcoming of the traditional heuristic-based approach to dataset selection. Results demonstrate the approach to provide performance improvements over both the use of the complete candidate dataset and the best heuristically-selected dataset whilst being only a fraction of the size. The refined dataset was also shown to generalise well to unseen corpora and be highly applicable to the selection of impostor cohorts required in alternate techniques for speaker verification.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

This thesis presents an original approach to parametric speech coding at rates below 1 kbitsjsec, primarily for speech storage applications. Essential processes considered in this research encompass efficient characterization of evolutionary configuration of vocal tract to follow phonemic features with high fidelity, representation of speech excitation using minimal parameters with minor degradation in naturalness of synthesized speech, and finally, quantization of resulting parameters at the nominated rates. For encoding speech spectral features, a new method relying on Temporal Decomposition (TD) is developed which efficiently compresses spectral information through interpolation between most steady points over time trajectories of spectral parameters using a new basis function. The compression ratio provided by the method is independent of the updating rate of the feature vectors, hence allows high resolution in tracking significant temporal variations of speech formants with no effect on the spectral data rate. Accordingly, regardless of the quantization technique employed, the method yields a high compression ratio without sacrificing speech intelligibility. Several new techniques for improving performance of the interpolation of spectral parameters through phonetically-based analysis are proposed and implemented in this research, comprising event approximated TD, near-optimal shaping event approximating functions, efficient speech parametrization for TD on the basis of an extensive investigation originally reported in this thesis, and a hierarchical error minimization algorithm for decomposition of feature parameters which significantly reduces the complexity of the interpolation process. Speech excitation in this work is characterized based on a novel Multi-Band Excitation paradigm which accurately determines the harmonic structure in the LPC (linear predictive coding) residual spectra, within individual bands, using the concept 11 of Instantaneous Frequency (IF) estimation in frequency domain. The model yields aneffective two-band approximation to excitation and computes pitch and voicing with high accuracy as well. New methods for interpolative coding of pitch and gain contours are also developed in this thesis. For pitch, relying on the correlation between phonetic evolution and pitch variations during voiced speech segments, TD is employed to interpolate the pitch contour between critical points introduced by event centroids. This compresses pitch contour in the ratio of about 1/10 with negligible error. To approximate gain contour, a set of uniformly-distributed Gaussian event-like functions is used which reduces the amount of gain information to about 1/6 with acceptable accuracy. The thesis also addresses a new quantization method applied to spectral features on the basis of statistical properties and spectral sensitivity of spectral parameters extracted from TD-based analysis. The experimental results show that good quality speech, comparable to that of conventional coders at rates over 2 kbits/sec, can be achieved at rates 650-990 bits/sec.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

This paper presents a novel method for remaining useful life prediction using the Elliptical Basis Function (EBF) network and a Markov chain. The EBF structure is trained by a modified Expectation-Maximization (EM) algorithm in order to take into account the missing covariate set. No explicit extrapolation is needed for internal covariates while a Markov chain is constructed to represent the evolution of external covariates in the study. The estimated external and the unknown internal covariates constitute an incomplete covariate set which are then used and analyzed by the EBF network to provide survival information of the asset. It is shown in the case study that the method slightly underestimates the remaining useful life of an asset which is a desirable result for early maintenance decision and resource planning.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we prove general risk bounds in terms of these complexities. We consider function classes that can be expressed as combinations of functions from basis classes and show how the Rademacher and Gaussian complexities of such a function class can be bounded in terms of the complexity of the basis classes. We give examples of the application of these techniques in finding data-dependent risk bounds for decision trees, neural networks and support vector machines.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

This paper presents an approach to building an observation likelihood function from a set of sparse, noisy training observations taken from known locations by a sensor with no obvious geometric model. The basic approach is to fit an interpolant to the training data, representing the expected observation, and to assume additive sensor noise. This paper takes a Bayesian view of the problem, maintaining a posterior over interpolants rather than simply the maximum-likelihood interpolant, giving a measure of uncertainty in the map at any point. This is done using a Gaussian process framework. To validate the approach experimentally, a model of an environment is built using observations from an omni-directional camera. After a model has been built from the training data, a particle filter is used to localise while traversing this environment

Relevância:

30.00% 30.00%

Publicador:

Resumo:

PySSM is a Python package that has been developed for the analysis of time series using linear Gaussian state space models (SSM). PySSM is easy to use; models can be set up quickly and efficiently and a variety of different settings are available to the user. It also takes advantage of scientific libraries Numpy and Scipy and other high level features of the Python language. PySSM is also used as a platform for interfacing between optimised and parallelised Fortran routines. These Fortran routines heavily utilise Basic Linear Algebra (BLAS) and Linear Algebra Package (LAPACK) functions for maximum performance. PySSM contains classes for filtering, classical smoothing as well as simulation smoothing.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Power system restoration after a large area outage involves many factors, and the procedure is usually very complicated. A decision-making support system could then be developed so as to find the optimal black-start strategy. In order to evaluate candidate black-start strategies, some indices, usually both qualitative and quantitative, are employed. However, it may not be possible to directly synthesize these indices, and different extents of interactions may exist among these indices. In the existing black-start decision-making methods, qualitative and quantitative indices cannot be well synthesized, and the interactions among different indices are not taken into account. The vague set, an extended version of the well-developed fuzzy set, could be employed to deal with decision-making problems with interacting attributes. Given this background, the vague set is first employed in this work to represent the indices for facilitating the comparisons among them. Then, a concept of the vague-valued fuzzy measure is presented, and on that basis a mathematical model for black-start decision-making developed. Compared with the existing methods, the proposed method could deal with the interactions among indices and more reasonably represent the fuzzy information. Finally, an actual power system is served for demonstrating the basic features of the developed model and method.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Invasive species provide excellent study systems to evaluate the ecological and evolutionary processes that contribute to the colonization of novel environments. While the ecological processes that contribute to the successful establishment of invasive plants have been studied in detail, investigation of the evolutionary processes involved in successful invasions has only recently received attention. In particular, studies investigating the genomic and gene expression differences between native and introduced populations of invasive species are just beginning and are required if we are to understand how plants become invasive. In the current issue of Molecular Ecology, Hodgins et al. () tackle this unresolved question, by examining gene expression differences between native and introduced populations of annual ragweed, Ambrosia artemisiifolia. The study identifies a number of potential candidate genes based on gene expression differences that may be responsible for the success of annual ragweed in its introduced range. Furthermore, genes involved in stress response are over-represented in the differentially expressed gene set. Future experiments could use functional studies to test whether changes in gene expression at these candidate genes do in fact underlie changes in growth characteristics and reproductive output observed in this and other invasive species.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Novelty-biased cumulative gain (α-NDCG) has become the de facto measure within the information retrieval (IR) community for evaluating retrieval systems in the context of sub-topic retrieval. Setting the incorrect value of parameter α in α-NDCG prevents the measure from behaving as desired in particular circumstances. In fact, when α is set according to common practice (i.e. α = 0.5), the measure favours systems that promote redundant relevant sub-topics rather than provide novel relevant ones. Recognising this characteristic of the measure is important because it affects the comparison and the ranking of retrieval systems. We propose an approach to overcome this problem by defining a safe threshold for the value of α on a query basis. Moreover, we study its impact on system rankings through a comprehensive simulation.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

This chapter describes decentralized data fusion algorithms for a team of multiple autonomous platforms. Decentralized data fusion (DDF) provides a useful basis with which to build upon for cooperative information gathering tasks for robotic teams operating in outdoor environments. Through the DDF algorithms, each platform can maintain a consistent global solution from which decisions may then be made. Comparisons will be made between the implementation of DDF using two probabilistic representations. The first, Gaussian estimates and the second Gaussian mixtures are compared using a common data set. The overall system design is detailed, providing insight into the overall complexity of implementing a robust DDF system for use in information gathering tasks in outdoor UAV applications.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Initial attempts to obtain lattice based signatures were closely related to reducing a vector modulo the fundamental parallelepiped of a secret basis (like GGH [9], or NTRUSign [12]). This approach leaked some information on the secret, namely the shape of the parallelepiped, which has been exploited on practical attacks [24]. NTRUSign was an extremely efficient scheme, and thus there has been a noticeable interest on developing countermeasures to the attacks, but with little success [6]. In [8] Gentry, Peikert and Vaikuntanathan proposed a randomized version of Babai’s nearest plane algorithm such that the distribution of a reduced vector modulo a secret parallelepiped only depended on the size of the base used. Using this algorithm and generating large, close to uniform, public keys they managed to get provably secure GGH-like lattice-based signatures. Recently, Stehlé and Steinfeld obtained a provably secure scheme very close to NTRUSign [26] (from a theoretical point of view). In this paper we present an alternative approach to seal the leak of NTRUSign. Instead of modifying the lattices and algorithms used, we do a classic leaky NTRUSign signature and hide it with gaussian noise using techniques present in Lyubashevky’s signatures. Our main contributions are thus a set of strong NTRUSign parameters, obtained by taking into account latest known attacks against the scheme, a statistical way to hide the leaky NTRU signature so that this particular instantiation of CVP-based signature scheme becomes zero-knowledge and secure against forgeries, based on the worst-case hardness of the O~(N1.5)-Shortest Independent Vector Problem over NTRU lattices. Finally, we give a set of concrete parameters to gauge the efficiency of the obtained signature scheme.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

The recently discovered twist phase is studied in the context of the full ten-parameter family of partially coherent general anisotropic Gaussian Schell-model beams. It is shown that the nonnegativity requirement on the cross-spectral density of the beam demands that the strength of the twist phase be bounded from above by the inverse of the transverse coherence area of the beam. The twist phase as a two-point function is shown to have the structure of the generalized Huygens kernel or Green's function of a first-order system. The ray-transfer matrix of this system is exhibited. Wolf-type coherent-mode decomposition of the twist phase is carried out. Imposition of the twist phase on an otherwise untwisted beam is shown to result in a linear transformation in the ray phase space of the Wigner distribution. Though this transformation preserves the four-dimensional phase-space volume, it is not symplectic and hence it can, when impressed on a Wigner distribution, push it out of the convex set of all bona fide Wigner distributions unless the original Wigner distribution was sufficiently deep into the interior of the set.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Matrix metalloproteinase (MMP) -8, collagenase-2, is a key mediator of irreversible tissue destruction in chronic periodontitis and detectable in gingival crevicular fluid (GCF). MMP-8 mostly originates from neutrophil leukocytes, the first line of defence cells which exist abundantly in GCF, especially in inflammation. MMP-8 is capable of degrading almost all extra-cellular matrix and basement membrane components and is especially efficient against type I collagen. Thus the expression of MMP-8 in GCF could be valuable in monitoring the activity of periodontitis and possibly offers a diagnostic means to predict progression of periodontitis. In this study the value of MMP-8 detection from GCF in monitoring of periodontal health and disease was evaluated with special reference to its ability to differentiate periodontal health and different disease states of the periodontium and to recognise the progression of periodontitis, i.e. active sites. For chair-side detection of MMP-8 from the GCF or peri-implant sulcus fluid (PISF) samples, a dip-stick test based on immunochromatography involving two monoclonal antibodies was developed. The immunoassay for the detection of MMP-8 from GCF was found to be more suitable for monitoring of periodontitis than detection of GCF elastase concentration or activity. Periodontally healthy subjects and individuals suffering of gingivitis or of periodontitis could be differentiated by means of GCF MMP-8 levels and dipstick testing when the positive threshold value of the MMP-8 chair-side test was set at 1000 µg/l. MMP-8 dipstick test results from periodontally healthy and from subjects with gingivitis were mainly negative while periodontitis patients sites with deep pockets ( 5 mm) and which were bleeding on probing were most often test positive. Periodontitis patients GCF MMP-8 levels decreased with hygiene phase periodontal treatment (scaling and root planing, SRP) and even reduced during the three month maintenance phase. A decrease in GCF MMP-8 levels could be monitored with the MMP-8 test. Agreement between the test stick and the quantitative assay was very good (κ = 0.81) and the test provided a baseline sensitivity of 0.83 and specificity of 0.96. During the 12-month longitudinal maintenance phase, periodontitis patients progressing sites (sites with an increase in attachment loss ≥ 2 mm during the maintenance phase) had elevated GCF MMP-8 levels compared with stable sites. General mean MMP-8 concentrations in smokers (S) sites were lower than in non-smokers (NS) sites but in progressing S and NS sites concentrations were at an equal level. Sites with exceptionally and repeatedly elevated MMP-8 concentrations during the maintenance phase were clustered in smoking patients with poor response to SRP (refractory patients). These sites especially were identified by the MMP-8 test. Subgingival plaque samples from periodontitis patients deep periodontal pockets were examined by polymerase chain reaction (PCR) to find out if periodontal lesions may serve as a niche for Chlamydia pneumoniae. Findings were compared with the clinical periodontal parameters and GCF MMP-8 levels to determine the correlation with periodontal status. Traces of C. pneumoniae were identified from one periodontitis patient s pooled subgingival plaque sample by means of PCR. After periodontal treatment (SRP) the sample was negative for C. pneumoniae. Clinical parameters or biomarkers (MMP-8) of the patient with the positive C. pneumoniae finding did not differ from other study patients. In this study it was concluded that MMP-8 concentrations in GCF of sites from periodontally healthy individuals, subjects with gingivitis or with periodontitis are at different levels. The cut-off value of the developed MMP-8 test is at an optimal level to differentiate between these conditions and can possibly be utilised in identification of individuals at the risk of the transition of gingivitis to periodontitis. In periodontitis patients, repeatedly elevated GCF MMP-8 concentrations may indicate sites at risk of progression of periodontitis as well as patients with poor response to conventional periodontal treatment (SRP). This can be monitored by MMP-8 testing. Despite the lower mean GCF MMP-8 concentrations in smokers, a fraction of smokers sites expressed very high MMP-8 concentrations together with enhanced periodontal activity and could be identified with MMP-8 specific chair-side test. Deep periodontal lesions may be niches for non-periodontopathogenic micro-organisms with systemic effects like C. pneumoniae and possibly play a role in the transmission from one subject to another.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

A parametrization of the elements of the three-dimensional Lorentz group O(2, 1), suited to the use of a noncompact O(1, 1) basis in its unitary representations, is derived and used to set up the representation matrices for the entire group. The Plancherel formula for O(2, 1) is then expressed in this basis.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

A non-dimensional parameter descriptive of the plowing nature of surfaces is proposed for the case of sliding between a soft and a relatively hard metallic pair. From a set of potential parameters which can be descriptive of the phenomenon, dimensionless groups are formulated and the influence of each one of them is analyzed. A non-dimensional parameter involving the root-mean square deviation (R-q) and the centroidal frequency (F-mean) deducted from the power-spectrum is found to have a high degree of correlation (as high as 0.93) with the coefficient of friction obtained in sliding experiments under lubricated condition.