A fast quasi-Newton method for semi-supervised SVM

Due to its wide applicability, semi-supervised learning is an attractive method for using unlabeled data in classification. In this work, we present a semi-supervised support vector classifier that is designed using quasi-Newton method for nonsmooth convex functions. The proposed algorithm is suitable in dealing with very large number of examples and features. Numerical experiments on various benchmark datasets showed that the proposed algorithm is fast and gives improved generalization performance over the existing methods. Further, a non-linear semi-supervised SVM has been proposed based on a multiple label switching scheme. This non-linear semi-supervised SVM is found to converge faster and it is found to improve generalization performance on several benchmark datasets. (C) 2010 Elsevier Ltd. All rights reserved.

A Quasi-Newton Adaptive Algorithm for Generalized Symmetric Eigenvalue Problem

In this paper, we first recast the generalized symmetric eigenvalue problem, where the underlying matrix pencil consists of symmetric positive definite matrices, into an unconstrained minimization problem by constructing an appropriate cost function, We then extend it to the case of multiple eigenvectors using an inflation technique, Based on this asymptotic formulation, we derive a quasi-Newton-based adaptive algorithm for estimating the required generalized eigenvectors in the data case. The resulting algorithm is modular and parallel, and it is globally convergent with probability one, We also analyze the effect of inexact inflation on the convergence of this algorithm and that of inexact knowledge of one of the matrices (in the pencil) on the resulting eigenstructure. Simulation results demonstrate that the performance of this algorithm is almost identical to that of the rank-one updating algorithm of Karasalo. Further, the performance of the proposed algorithm has been found to remain stable even over 1 million updates without suffering from any error accumulation problems.

Smoothed functional and Quasi-Newton algorithms for routing in multi-stage queueing network with constraints

We consider the problem of optimal routing in a multi-stage network of queues with constraints on queue lengths. We develop three algorithms for probabilistic routing for this problem using only the total end-to-end delays. These algorithms use the smoothed functional (SF) approach to optimize the routing probabilities. In our model all the queues are assumed to have constraints on the average queue length. We also propose a novel quasi-Newton based SF algorithm. Policies like Join Shortest Queue or Least Work Left work only for unconstrained routing. Besides assuming knowledge of the queue length at all the queues. If the only information available is the expected end-to-end delay as with our case such policies cannot be used. We also give simulation results showing the performance of the SF algorithms for this problem.

Efficient implementations of a pseudodynamical stochastic filtering strategy for static elastography

A computationally efficient pseudodynamical filtering setup is established for elasticity imaging (i.e., reconstruction of shear modulus distribution) in soft-tissue organs given statically recorded and partially measured displacement data. Unlike a regularized quasi-Newton method (QNM) that needs inversion of ill-conditioned matrices, the authors explore pseudodynamic extended and ensemble Kalman filters (PD-EKF and PD-EnKF) that use a parsimonious representation of states and bypass explicit regularization by recursion over pseudotime. Numerical experiments with QNM and the two filters suggest that the PD-EnKF is the most robust performer as it exhibits no sensitivity to process noise covariance and yields good reconstruction even with small ensemble sizes.

Pseudo-time marching schemes for inverse problems in structural health assessment and medical imaging

We propose a self-regularized pseudo-time marching strategy for ill-posed, nonlinear inverse problems involving recovery of system parameters given partial and noisy measurements of system response. While various regularized Newton methods are popularly employed to solve these problems, resulting solutions are known to sensitively depend upon the noise intensity in the data and on regularization parameters, an optimal choice for which remains a tricky issue. Through limited numerical experiments on a couple of parameter re-construction problems, one involving the identification of a truss bridge and the other related to imaging soft-tissue organs for early detection of cancer, we demonstrate the superior features of the pseudo-time marching schemes.

AIWIN - A fast and jigless inspection technique for machined parts

Precision inspection of manufactured components having multiple complex surfaces and variable tolerance definition is an involved, complex and time-consuming function. In routine practice, a jig is used to present the part in a known reference frame to carry out the inspection process. Jigs involve both time and cost in their development, manufacture and use. This paper describes 'as is where is inspection' (AIWIN), a new automated inspection technique that accelerates the inspection process by carrying out a fast registration procedure and establishing a quick correspondence between the part to inspect and its CAD geometry. The main challenge in doing away with a jig is that the inspection reference frame could be far removed from the CAD frame. Traditional techniques based on iterative closest point (ICP) or Newton methods require either a large number of iterations for convergence or fail in such a situation. A two-step coarse registration process is proposed to provide a good initial guess for a modified ICP algorithm developed earlier (Ravishankar et al., Int J Adv Manuf Technol 46(1-4):227-236, 2010). The first step uses a calibrated sphere for local hard registration and fixing the translation error. This transformation locates the centre for the sphere in the CAD frame. In the second step, the inverse transformation (involving pure rotation about multiple axes) required to align the inspection points measured on the manufactured part with the CAD point dataset of the model is determined and enforced. This completes the coarse registration enabling fast convergence of the modified ICP algorithm. The new technique has been implemented on complex freeform machined components and the inspection results clearly show that the process is precise and reliable with rapid convergence. © 2011 Springer-Verlag London Limited.

Prediction of Ground Water Levels in the Uplands of a Tropical Coastal Riparian Wetland using Artificial Neural Networks

Artificial Neural Networks (ANNs) have been found to be a robust tool to model many non-linear hydrological processes. The present study aims at evaluating the performance of ANN in simulating and predicting ground water levels in the uplands of a tropical coastal riparian wetland. The study involves comparison of two network architectures, Feed Forward Neural Network (FFNN) and Recurrent Neural Network (RNN) trained under five algorithms namely Levenberg Marquardt algorithm, Resilient Back propagation algorithm, BFGS Quasi Newton algorithm, Scaled Conjugate Gradient algorithm, and Fletcher Reeves Conjugate Gradient algorithm by simulating the water levels in a well in the study area. The study is analyzed in two cases-one with four inputs to the networks and two with eight inputs to the networks. The two networks-five algorithms in both the cases are compared to determine the best performing combination that could simulate and predict the process satisfactorily. Ad Hoc (Trial and Error) method is followed in optimizing network structure in all cases. On the whole, it is noticed from the results that the Artificial Neural Networks have simulated and predicted the water levels in the well with fair accuracy. This is evident from low values of Normalized Root Mean Square Error and Relative Root Mean Square Error and high values of Nash-Sutcliffe Efficiency Index and Correlation Coefficient (which are taken as the performance measures to calibrate the networks) calculated after the analysis. On comparison of ground water levels predicted with those at the observation well, FFNN trained with Fletcher Reeves Conjugate Gradient algorithm taken four inputs has outperformed all other combinations.

Variance-Reduced Particle Filters for Structural System Identification Problems

A few variance reduction schemes are proposed within the broad framework of a particle filter as applied to the problem of structural system identification. Whereas the first scheme uses a directional descent step, possibly of the Newton or quasi-Newton type, within the prediction stage of the filter, the second relies on replacing the more conventional Monte Carlo simulation involving pseudorandom sequence with one using quasi-random sequences along with a Brownian bridge discretization while representing the process noise terms. As evidenced through the derivations and subsequent numerical work on the identification of a shear frame, the combined effect of the proposed approaches in yielding variance-reduced estimates of the model parameters appears to be quite noticeable. DOI: 10.1061/(ASCE)EM.1943-7889.0000480. (C) 2013 American Society of Civil Engineers.

Modified Newton, rank-1 Broyden update and rank-2 BFGS update methods in helicopter trim: A comparative study

Nonlinear equations in mathematical physics and engineering are solved by linearizing the equations and forming various iterative procedures, then executing the numerical simulation. For strongly nonlinear problems, the solution obtained in the iterative process can diverge due to numerical instability. As a result, the application of numerical simulation for strongly nonlinear problems is limited. Helicopter aeroelasticity involves the solution of systems of nonlinear equations in a computationally expensive environment. Reliable solution methods which do not need Jacobian calculation at each iteration are needed for this problem. In this paper, a comparative study is done by incorporating different methods for solving the nonlinear equations in helicopter trim. Three different methods based on calculating the Jacobian at the initial guess are investigated. (C) 2011 Elsevier Masson SAS. All rights reserved.

Approximation of the perturbation equations of a quasi-linear hyperbolic system in the neighborhood of a bicharacteristic

In 1956 Whitham gave a nonlinear theory for computing the intensity of an acoustic pulse of an arbitrary shape. The theory has been used very successfully in computing the intensity of the sonic bang produced by a supersonic plane. [4.] derived an approximate quasi-linear equation for the propagation of a short wave in a compressible medium. These two methods are essentially nonlinear approximations of the perturbation equations of the system of gas-dynamic equations in the neighborhood of a bicharacteristic curve (or rays) for weak unsteady disturbances superimposed on a given steady solution. In this paper we have derived an approximate quasi-linear equation which is an approximation of perturbation equations in the neighborhood of a bicharacteristic curve for a weak pulse governed by a general system of first order quasi-linear partial differential equations in m + 1 independent variables (t, x1,…, xm) and derived Gubkin's result as a particular case when the system of equations consists of the equations of an unsteady motion of a compressible gas. We have also discussed the form of the approximate equation describing the waves propagating upsteam in an arbitrary multidimensional transonic flow.

Parallel computing concepts and methods for floquet analysis of helicopter trim and stability

Floquet analysis is widely used for small-order systems (say, order M < 100) to find trim results of control inputs and periodic responses, and stability results of damping levels and frequencies, Presently, however, it is practical neither for design applications nor for comprehensive analysis models that lead to large systems (M > 100); the run time on a sequential computer is simply prohibitive, Accordingly, a massively parallel Floquet analysis is developed with emphasis on large systems, and it is implemented on two SIMD or single-instruction, multiple-data computers with 4096 and 8192 processors, The focus of this development is a parallel shooting method with damped Newton iteration to generate trim results; the Floquet transition matrix (FTM) comes out as a byproduct, The eigenvalues and eigenvectors of the FTM are computed by a parallel QR method, and thereby stability results are generated, For illustration, flap and flap-lag stability of isolated rotors are treated by the parallel analysis and by a corresponding sequential analysis with the conventional shooting and QR methods; linear quasisteady airfoil aerodynamics and a finite-state three-dimensional wake model are used, Computational reliability is quantified by the condition numbers of the Jacobian matrices in Newton iteration, the condition numbers of the eigenvalues and the residual errors of the eigenpairs, and reliability figures are comparable in both the parallel and sequential analyses, Compared to the sequential analysis, the parallel analysis reduces the run time of large systems dramatically, and the reduction increases with increasing system order; this finding offers considerable promise for design and comprehensive-analysis applications.

{C}^0$ penalty methods for the fully nonlinear Monge-Ampère equation

In this paper, we develop and analyze C(0) penalty methods for the fully nonlinear Monge-Ampere equation det(D(2)u) = f in two dimensions. The key idea in designing our methods is to build discretizations such that the resulting discrete linearizations are symmetric, stable, and consistent with the continuous linearization. We are then able to show the well-posedness of the penalty method as well as quasi-optimal error estimates using the Banach fixed-point theorem as our main tool. Numerical experiments are presented which support the theoretical results.

Quasi-based hierarchical clustering for land cover mapping using satellite images

This paper presents an improved hierarchical clustering algorithm for land cover mapping problem using quasi-random distribution. Initially, Niche Particle Swarm Optimization (NPSO) with pseudo/quasi-random distribution is used for splitting the data into number of cluster centers by satisfying Bayesian Information Criteria (BIC). Themain objective is to search and locate the best possible number of cluster and its centers. NPSO which highly depends on the initial distribution of particles in search space is not been exploited to its full potential. In this study, we have compared more uniformly distributed quasi-random with pseudo-random distribution with NPSO for splitting data set. Here to generate quasi-random distribution, Faure method has been used. Performance of previously proposed methods namely K-means, Mean Shift Clustering (MSC) and NPSO with pseudo-random is compared with the proposed approach - NPSO with quasi distribution(Faure). These algorithms are used on synthetic data set and multi-spectral satellite image (Landsat 7 thematic mapper). From the result obtained we conclude that use of quasi-random sequence with NPSO for hierarchical clustering algorithm results in a more accurate data classification.

Quasi-static and dynamic strain sensing using carbon nanotube/epoxy nanocomposite thin films

Thin films are developed by dispersing carbon black nanoparticles and carbon nanotubes (CNTs) in an epoxy polymer. The films show a large variation in electrical resistance when subjected to quasi-static and dynamic mechanical loading. This phenomenon is attributed to the change in the band-gap of the CNTs due to the applied strain, and also to the change in the volume fraction of the constituent phases in the percolation network. Under quasi-static loading, the films show a nonlinear response. This nonlinearity in the response of the films is primarily attributed to the pre-yield softening of the epoxy polymer. The electrical resistance of the films is found to be strongly dependent on the magnitude and frequency of the applied dynamic strain, induced by a piezoelectric substrate. Interestingly, the resistance variation is found to be a linear function of frequency and dynamic strain. Samples with a small concentration of just 0.57% of CNT show a sensitivity as high as 2.5% MPa-1 for static mechanical loading. A mathematical model based on Bruggeman's effective medium theory is developed to better understand the experimental results. Dynamic mechanical loading experiments reveal a sensitivity as high as 0.007% Hz(-1) at a constant small-amplitude vibration and up to 0.13%/mu-strain at 0-500 Hz vibration. Potential applications of such thin films include highly sensitive strain sensors, accelerometers, artificial neural networks, artificial skin and polymer electronics.

Higher-Order Nonlinearity In Accretion Disks: Quasi-Periodic Oscillations Of Black Hole And Neutron Star Sources And Their Spin

We propose a unified model to explain Quasi-Periodic Oscillation (QPO), particularly of high frequency, observed from black hole and neutron star systems globally. We consider accreting systems to be damped harmonic oscillators exhibiting epicyclic oscillations with higher-order nonlinear resonance to explain QPO. The resonance is expected to be driven by the disturbance from the compact object at its spin frequency. The model explains various properties parallelly for both types of the compact object. It describes QPOs successfully for ten different compact sources. Based on this, we predict the spin frequency of the neutron star Sco X-1 and specific angular momentum of black holes GRO J1655–40, XTE J1550–564, H1743–322, and GRS 1915+105.