The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Industrial applications often require processing data with large dynamic ranges at low sample rates. As algorithms become more complex, handling the data range of variables required for fixed-point implementations becomes time consuming, and can also lead to inefficient designs. Floating-point solutions leverage these limitations trading automatic data range handling for a usually higher implementation...
In Recommender system we have similarity search as a key part for making efficient recommendations. Similarity search have always been a tough task in a high dimensional space. Locality Sensitive Hashing which is most suitable for extracting data in a high dimensional data (Multimedia data). The Idea of locality sensitive hashing is that it decreases the high dimensional data to low dimensions using...
This paper considers the problem of modeling complex motions of pedestrians in a crowded environment. A number of methods have been proposed to predict the motion of a pedestrian or an object. However, it is still difficult to make a good prediction due to challenges, such as the complexity of pedestrian motions and outliers in a training set. This paper addresses these issues by proposing a robust...
In this paper, we present a hyper graph kernel computed using substructure isomorphism tests. Measuring the isomorphisms between hyper graphs straightforwardly tends to be elusive since a hyper graph may exhibit varying relational orders. We thus transform a hyper graph into a directed line graph. This not only accurately reflects the multiple relationships exhibited by the hyper graph but is also...
In clinical neuroimaging applications where subjects belong to one of multiple classes of disease states and multiple imaging sources are available, the aim is to achieve accurate classification while assessing the importance of the sources in the classification task. This work proposes the use of fully Bayesian multiple-class multiple-kernel learning based on Gaussian Processes, as it offers flexible...
Kernel methods have revolutionized the fields of pattern recognition and machine learning. Their success, however, critically depends on the choice of kernel parameters. Using Gaussian process (GP) classification as a working example, this paper focuses on Bayesian inference of covariance (kernel) parameters using Markov chain Monte Carlo (MCMC) methods. The motivation is that, compared to standard...
Graph regularized techniques have been extensively exploited in unsupervised learning. However, there exist no principled ways to select reasonable graphs and their associated hyper parameters, particularly in multiple heterogeneous data sources. Often, the graph selection process requires rather time-consuming cross-validation and discrete grid search that are not scalable to a large number of candidate...
Complex (imaginary) signals arise commonly in the field of communications in the form of time series in the complex space. In this work we propose a symbolic approach for such signals based on string kernels derived from a complex SAX representation and apply it to a challenging counting problem. Our approach, that we call cStrings, is within a Gaussian process regression framework and outperforms...
The past twenty years has seen the explosion of the "shape zoo": myriad shape representations, each with pros and cons. Of the varied denizens, distance transforms and density function shape representations have proven to be the most utile. Distance transforms inherit the numerous geometric advantages of implicit curve representations while density functions are unmatched in their approach...
Recursive identification for semiparametric multi-channel Wiener systems is considered in the paper. Based on stochastic approximation, the recursive estimates are given for coefficients of each linear subsystem and the weighed coefficient with the help of the average derivative approach, then recursive nonparametric estimate is derived for the system nonlinearity by using kernel method. All estimates...
We review recently proposed nonlinear mitigation methods based on a frequency-domain Volterra series expansion for high-speed and long-haul optical transmission systems. Using a symmetric kernel reconstruction we derive a set of parallel frequency-domain filters that constructively add up to rebuild the matrix-based Volterra series nonlinear equalizer (VSNE). It is demonstrated through simulation...
Traditional approaches to create sensor-level maps from magnetoencephalographic (MEG) data rely on mass-univariate methods. In order to overcome some limitations of univariate approaches, multivariate approaches have been widely investigated, mostly based on the paradigm of classification. Recently a multivariate two-sample test called kernel two-sample test (KTST) has been proposed as an alternative...
Semi-supervised learning algorithms make use of labeled and unlabeled samples. A large number of experiments show that the use of unlabeled samples may improve approximation power. However, there is seldom quantitative analysis of approximation power when the number of samples increases. In this paper a semi-supervised learning algorithm is constructed based on diffusion matrices. We establish the...
The accuracy and the computational complexity of a Gaussian mixture model depends upon the number of components. In a stochastic dynamical system, the number of these components must change over time to account for the change in the uncertainty over time. A new splitting technique is provided based on the minimization of Fokker Planck Kolmogorov Equation. The effect of the splitting on the other components...
In this work a PDE backstepping-based control law for one-dimensional unstable heat equation with time-varying spatial domain is developed. The underlying parabolic partial differential equation (PDE) with time-varying domain is the model emerging from process control applications such as crystal growth. In backstepping control law synthesis, a characteristic feature is that the PDE describing the...
The numerical solution, either of a weakly singular Fred Holm integral equation of the second kind or of the spectral problem associated, using projection methods such as classical Galerkin, Kantorovich or Sloan (iterated Galerkin) requires the evaluation of a discretization matrix which represents the integral operator restricted to a finite dimensional space. The accuracy of the approximate solution...
In this paper, the stabilization of a cascaded heat-ODE system with time-dependent coefficient is discussed by choosing suitable backstepping transformation transferring the original heat-ODE system into an exponentially stable object system. We prove the existence of time-dependent kernels in forward and invertible transformation via successive approximation method, which is the novelty of the paper,...
Endowing mobile manipulation robots with skills to use objects and tools often involves the programming or training on specific object instances. To apply this knowledge to novel instances from the same class of objects, a robot requires generalization capabilities for control as well as perception. In this paper, we propose an efficient approach to deformable registration of RGB-D images that enables...
High dynamic range image processing have recently become an important topic in consumer electronics market. While multi-scale retinex with color restoration (MSRCR) have been well developed, disadvantages of low performance is not favorable to a mobile computer-vision system. To remedy the above problem, this paper proposes an accelerated MSRCR with effective use of ARM Cortex-A9 architecture and...
The fast multipole method (FMM) is often used to accelerate the calculation of particle interactions in particle-based methods to simulate incompressible flows. To evaluate the most time-consuming kernels -- the Biot-Savart equation and stretching term of the vorticity equation, we mathematically reformulated it so that only two Laplace scalar potentials are used instead of six. This automatically...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.