Restoration of images and 3D data to higher resolution by deconvolution with sparsity regularization

Image convolution is conventionally approximated by the LTI discrete model. It is well recognized that the higher the sampling rate, the better is the approximation. However sometimes images or 3D data are only available at a lower sampling rate due to physical constraints of the imaging system. In this paper, we model the under-sampled observation as the result of combining convolution and subsampling. Because the wavelet coefficients of piecewise smooth images tend to be sparse and well modelled by tree-like structures, we propose the L0 reweighted-L2 minimization (L0RL2 ) algorithm to solve this problem. This promotes model-based sparsity by minimizing the reweighted L2 norm, which approximates the L0 norm, and by enforcing a tree model over the weights. We test the algorithm on 3 examples: a simple ring, the cameraman image and a 3D microscope dataset; and show that good results can be obtained. © 2010 IEEE.

H∞ sampled-data synthesis and related numerical issues

In this paper we present a new, compact derivation of state-space formulae for the so-called discretisation-based solution of the H∞ sampled-data control problem. Our approach is based on the established technique of continuous time-lifting, which is used to isometrically map the continuous-time, linear, periodically time-varying, sampled-data problem to a discretetime, linear, time-invariant problem. State-space formulae are derived for the equivalent, discrete-time problem by solving a set of two-point, boundary-value problems. The formulae accommodate a direct feed-through term from the disturbance inputs to the controlled outputs of the original plant and are simple, requiring the computation of only a single matrix exponential. It is also shown that the resultant formulae can be easily re-structured to give a numerically robust algorithm for computing the state-space matrices. © 1997 Elsevier Science Ltd. All rights reserved.

The most persistent soft-clique in a set of sampled graphs

When searching for characteristic subpatterns in potentially noisy graph data, it appears self-evident that having multiple observations would be better than having just one. However, it turns out that the inconsistencies introduced when different graph instances have different edge sets pose a serious challenge. In this work we address this challenge for the problem of finding maximum weighted cliques. We introduce the concept of most persistent soft-clique. This is subset of vertices, that 1) is almost fully or at least densely connected, 2) occurs in all or almost all graph instances, and 3) has the maximum weight. We present a measure of clique-ness, that essentially counts the number of edge missing to make a subset of vertices into a clique. With this measure, we show that the problem of finding the most persistent soft-clique problem can be cast either as: a) a max-min two person game optimization problem, or b) a min-min soft margin optimization problem. Both formulations lead to the same solution when using a partial Lagrangian method to solve the optimization problems. By experiments on synthetic data and on real social network data we show that the proposed method is able to reliably find soft cliques in graph data, even if that is distorted by random noise or unreliable observations. Copyright 2012 by the author(s)/owner(s).

Plastic limit solution for the response of plate anchors under combined translational and torsional undrained loading

Plate anchors are increasingly being used to moor large floating offshore structures in deep and ultradeep water. These facilities impart substantial vertical uplift loading to plate anchors. However, extreme operating conditions such as hurricane loading often result in partial system failures, with significant change in the orientation of the remaining intact mooring lines. The purpose of this study is to investigate the undrained pure translational (parallel to plate) and torsional bearing capacity of anchor plates idealized as square and rectangular shaped plates. Moreover, the interaction response of plate anchors under combined translational and torsional loading is studied using a modified plastic limit analysis (PLA) approach. The previous PLA formulation which did not account for shear-normal force interaction on the vertical end faces of the plate provides an exact solution to the idealized problem of an infinitely thin plate but only an approximate solution to the problem of a plate of finite thickness. This is also confirmed by the three-dimensional finite element (FE) results, since the PLA values exceed FE results as the thickness of the plate increases. By incorporating the shear-normal interaction relationship in the modified solution, the torsional bearing capacity factors, as well as the plate interaction responses are enhanced as they show satisfactory agreement with the FE results. The interaction relationship is then obtained for square and rectangular plates of different aspect ratios and thicknesses. The new interaction relationships could also be used as an associated plastic failure locus for combined shear and torsional loading to predict plastic displacements and rotations in translational and torsional loading modes as well. Copyright © 2011 by the International Society of Offshore and Polar Engineers (ISOPE).

Linear regression under fixed-rank constraints: A Riemannian approach

In this paper, we tackle the problem of learning a linear regression model whose parameter is a fixed-rank matrix. We study the Riemannian manifold geometry of the set of fixed-rank matrices and develop efficient line-search algorithms. The proposed algorithms have many applications, scale to high-dimensional problems, enjoy local convergence properties and confer a geometric basis to recent contributions on learning fixed-rank matrices. Numerical experiments on benchmarks suggest that the proposed algorithms compete with the state-of-the-art, and that manifold optimization offers a versatile framework for the design of rank-constrained machine learning algorithms. Copyright 2011 by the author(s)/owner(s).

Numerical analysis of shallow foundations under combined horizontal and torsional loading

Foundations of subsea infrastructure in deep water subjected to asymmetric environmental loads have underscored the importance of combined torsional and horizontal loading effects on the bearing capacity of rectangular shallow foundations. The purpose of this study is to investigate the undrained sliding and torsional bearing capacity of rectangular and square shallow foundations together with the interaction response under combined loading using three-dimensional finite element (3D-FE) analysis. Upper bound plastic limit analysis is employed to establish a reference value for horizontal and torsional bearing capacity, and an interaction relationship for the combined loading condition. Satisfactory agreement of plastic limit analysis (PLA) and 3D-FE results for ultimate capacity and interaction curves ensures that simple PLA solution could be used to evaluate the bearing capacity problem of foundation under combined sliding and torsion.