In this work two indexing approaches are presented for case-based reasoning. The first is a hybrid technique which uses a combination of a matrix structure and a tree structure to solve problems. The matrix and tree structures index cases by their discre-tised feature values. The second approach is based solely on the tree structure and never uses the matrix. The two techniques are evaluated in...

A standard way of dealing with a matrix polynomial P (λ) is to convert it into an equivalent matrix pencil – a process known as linearization. For any regular matrix polynomial, a new family of linearizations generalizing the classical first and second Frobenius companion forms has recently been introduced by Antoniou and Vologiannidis, extending some linearizations previously defined by Fiedle...

We propose an efficient strategy to infer sparse Hopfield network based on magnetizations and pairwise correlations measured through Glauber samplings. This strategy incorporates the l1 regularization into the Bethe approximation by a quadratic approximation to the log-likelihood, and is able to further reduce the inference error of the Bethe approximation without the regularization. The optima...

In this paper we show that inverses of wellconditioned, finite-time Gramians and impulse response matrices of large-scale interconnected systems described by sparse state-space models, can be approximated by sparse matrices. The approximation methodology established in this paper opens the door to the development of novel methods for distributed estimation, identification and control of large-s...

We propose a novel algorithm for the recovery of non-sparse, but compressible signals from linear undersampled measurements. The algorithm proposed in this paper consists of two steps. The first step recovers the signal by the l1 minimization. Then, the second step decomposes the l1 reconstruction into major and minor components. By using the major components, measurements for the minor compone...

As the share of services in economies grow globally, the efficiency of service production becomes crucial. Despite the many studies on service efficiency, it has proven difficult to find the right measures. The main reason is wide range of services from simple to complex, and from mass to professional services. Consequently, there are no commonly accepted measurement frameworks for comparing th...

This paper presents a method to resize images by a rational factor of P/Q in the discrete cosine transform (DCT) domain where P and Q are relatively prime integers larger than one. Our method extends on the prior work of Mukherjee and Mitra which utilizes the spatial relationship of DCT coefficients between a block and its sub-blocks. To resize images by a factor of P/Q, the images are first up...

Geophysical inverse problems typically involve a tradeoff between data misfit and some prior model. Pareto curves trace the optimal trade-off between these two competing aims. These curves are used commonly in problems with two-norm priors in which they are plotted on a log-log scale and are known as L-curves. For other priors, such as the sparsity-promoting one-norm prior, Pareto curves remain...

In this paper, we study the problem of nonnegative graph embedding, originally investigated in [14] for reaping the benefits from both nonnegative data factorization and the specific purpose characterized by the intrinsic and penalty graphs [13]. Our contributions are two-fold. On the one hand, we present a multiplicative iterative procedure for nonnegative graph embedding, which significantly ...

Since their introduction, properties of Phase Type (PH) distributions have been analyzed and many interesting theoretical results found. Thanks to these results, PH distributions have been profitably used in many modeling contexts where non exponentially distributed behavior is present. Matrix Exponential (ME) distributions are distributions whose matrix representation is structurally similar t...