New Family Of Methods Research Articles

Learning from crowds for automated histopathological image segmentation

Automated semantic segmentation of histopathological images is an essential task in Computational Pathology (CPATH). The main limitation of Deep Learning (DL) to address this task is the scarcity of expert annotations. Crowdsourcing (CR) has emerged as a promising solution to reduce the individual (expert) annotation cost by distributing the labeling effort among a group of (non-expert) annotators. Extracting knowledge in this scenario is challenging, as it involves noisy annotations. Jointly learning the underlying (expert) segmentation and the annotators’ expertise is currently a commonly used approach. Unfortunately, this approach is frequently carried out by learning a different neural network for each annotator, which scales poorly when the number of annotators grows. For this reason, this strategy cannot be easily applied to real-world CPATH segmentation. This paper proposes a new family of methods for CR segmentation of histopathological images. Our approach consists of two coupled networks: a segmentation network (for learning the expert segmentation) and an annotator network (for learning the annotators’ expertise). We propose to estimate the annotators’ behavior with only one network that receives the annotator ID as input, achieving scalability on the number of annotators. Our family is composed of three different models for the annotator network. Within this family, we propose a novel modeling of the annotator network in the CR segmentation literature, which considers the global features of the image. We validate our methods on a real-world dataset of Triple Negative Breast Cancer images labeled by several medical students. Our new CR modeling achieves a Dice coefficient of 0.7827, outperforming the well-known STAPLE (0.7039) and being competitive with the supervised method with expert labels (0.7723). The code is available at https://github.com/wizmik12/CRowd_Seg.

Retrieval of surface solar irradiance from satellite imagery using machine learning: pitfalls and perspectives

Abstract. Knowledge of the spatial and temporal characteristics of solar surface irradiance (SSI) is critical in many domains. While meteorological ground stations can provide accurate measurements of SSI locally, they are sparsely distributed worldwide. SSI estimations derived from satellite imagery are thus crucial to gain a finer understanding of the solar resource. Inferring SSI from satellite images is, however, not straightforward, and it has been the focus of many researchers in the past 30 to 40 years. For long, the emphasis has been on models grounded in physical laws with, in some cases, simple statistical parametrizations. Recently, new satellite SSI retrieval methods have been emerging, which directly infer the SSI from the satellite images using machine learning. Although only a few such works have been published, their practical efficiency has already been questioned. The objective of this paper is to better understand the potential and the pitfalls of this new family of methods. To do so, simple multi-layer-perceptron (MLP) models are constructed with different training datasets of satellite-based radiance measurements from Meteosat Second Generation (MSG) with collocated SSI ground measurements from Météo-France. The performance of the models is evaluated on a test dataset independent from the training set in both space and time and compared to that of a state-of-the-art physical retrieval model from the Copernicus Atmosphere Monitoring Service (CAMS). We found that the data-driven model's performance is very dependent on the training set. Provided the training set is sufficiently large and similar enough to the test set, even a simple MLP has a root mean square error (RMSE) that is 19 % lower than CAMS and outperforms the physical retrieval model at 96 % of the test stations. On the other hand, in certain configurations, the data-driven model can dramatically underperform even in stations located close to the training set: when geographical separation was enforced between the training and test set, the MLP-based model exhibited an RMSE that was 50 % to 100 % higher than that of CAMS in several locations.

Expansion Cones: A Progressive Volumetric Mapping Framework

Volumetric mapping is a ubiquitous and difficult problem in Geometry Processing and has been the subject of research in numerous and various directions. While several methods show encouraging results, the field still lacks a general approach with guarantees regarding map bijectivity. Through this work, we aim at opening the door to a new family of methods by providing a novel framework based on the concept of progressive expansion. Starting from an initial map of a tetrahedral mesh whose image may contain degeneracies but no inversions, we incrementally adjust vertex images to expand degenerate elements. By restricting movement to so-called expansion cones , it is done in such a way that the number of degenerate elements decreases in a strictly monotonic manner, without ever introducing any inversion. Adaptive local refinement of the mesh is performed to facilitate this process. We describe a prototype algorithm in the realm of this framework for the computation of maps from ball-topology tetrahedral meshes to convex or star-shaped domains. This algorithm is evaluated and compared to state-of-the-art methods, demonstrating its benefits in terms of bijectivity. We also discuss the associated cost in terms of sometimes significant mesh refinement to obtain the necessary degrees of freedom required for establishing a valid mapping. Our conclusions include that while this algorithm is only of limited immediate practical utility due to efficiency concerns, the general framework has the potential to inspire a range of novel methods improving on the efficiency aspect.

SAR Target Recognition via Random Sampling Combination in Open-World Environments

Target recognition in SAR images was widely studied over the years. Most of these works were usually based on the assumption that the targets in the test set belong to a limited set of classes. In the practical scenarios, it is common to encounter various kinds of new targets. It is therefore more meaningful to study target recognition in open-world environments. In these scenes, it is needed to reject the unknown classes while maintain the classification performance on known classes. In the past years, few works were devoted to open set target recognition. Though the detection performance on unknown targets can be improved to a certain extent in the preceding works, most detection schemes are independent of a pretrained feature extractor, leading to potential open space risks. Besides, the model architectures are complicated, resulting in huge computational cost. To solve these problems, a family of new methods for open set target recognition is proposed. Targets indistinguishable from known classes are constructed by random sampling combination strategy. They are further sent into the classifier for feature learning. The original open-world environment is then transformed into a closed-world environment containing the unknown class. Moreover, the special implication of generated unknown targets is highlighted and used to realize unknown detection. Extensive experimental results on the MSTAR benchmark dataset illustrate the effectiveness of the proposed methods.

Enhancing socio-emotional communication and quality of life in young cochlear implant recipients: Perspectives from parameter-specific morphing and caricaturing.

The use of digitally modified stimuli with enhanced diagnostic information to improve verbal communication in children with sensory or central handicaps was pioneered by Tallal and colleagues in 1996, who targeted speech comprehension in language-learning impaired children. Today, researchers are aware that successful communication cannot be reduced to linguistic information—it depends strongly on the quality of communication, including non-verbal socio-emotional communication. In children with cochlear implants (CIs), quality of life (QoL) is affected, but this can be related to the ability to recognize emotions in a voice rather than speech comprehension alone. In this manuscript, we describe a family of new methods, termed parameter-specific facial and vocal morphing. We propose that these provide novel perspectives for assessing sensory determinants of human communication, but also for enhancing socio-emotional communication and QoL in the context of sensory handicaps, via training with digitally enhanced, caricatured stimuli. Based on promising initial results with various target groups including people with age-related macular degeneration, people with low abilities to recognize faces, older people, and adult CI users, we discuss chances and challenges for perceptual training interventions for young CI users based on enhanced auditory stimuli, as well as perspectives for CI sound processing technology.

High order integrators obtained by linear combinations of symmetric-conjugate compositions

A new family of methods involving complex coefficients for the numerical integration of differential equations is presented and analyzed. They are constructed as linear combinations of symmetric-conjugate compositions obtained from a basic time-symmetric integrator of order 2n (n≥1). The new integrators are of order 2(n+k), k=1,2,…, and preserve time-symmetry up to order 4n+3 when applied to differential equations with real vector fields. If in addition the system is Hamiltonian and the basic scheme is symplectic, then they also preserve symplecticity up to order 4n+3. We show that these integrators are well suited for a parallel implementation, thus improving their efficiency. Methods up to order 10 based on a 4th-order integrator are built and tested in comparison with other standard procedures to increase the order of a basic scheme.

Using Lasso and Adaptive Lasso to Identify DIF in Multidimensional 2PL Models

Differential item functioning (DIF) analysis refers to procedures that evaluate whether an item’s characteristic differs for different groups of persons after controlling for overall differences in performance. DIF is routinely evaluated as a screening step to ensure items behave the same across groups. Currently, the majority DIF studies focus predominately on unidimensional IRT models, although multidimensional IRT (MIRT) models provide a powerful tool for enriching the information gained in modern assessment. In this study, we explore regularization methods for DIF detection in MIRT models and compare their performance to the classic likelihood ratio test. Regularization methods have recently emerged as a new family of methods for DIF detection due to their advantages: (1) they bypass the tedious iterative purification procedure that is often needed in other methods for identifying anchor items, and (2) they can handle multiple covariates simultaneously. The specific regularization methods considered in the study are: lasso with expectation-maximization (EM), lasso with expectation-maximization-maximization (EMM) algorithm, and adaptive lasso with EM. Simulation results show that lasso EMM and adaptive lasso EM hold great promise when the sample size is large, and they both outperform lasso EM. A real data example from PROMIS depression and anxiety scales is presented in the end.

Efficient Evaluation of Matrix Polynomials beyond the Paterson–Stockmeyer Method

Recently, two general methods for evaluating matrix polynomials requiring one matrix product less than the Paterson–Stockmeyer method were proposed, where the cost of evaluating a matrix polynomial is given asymptotically by the total number of matrix product evaluations. An analysis of the stability of those methods was given and the methods have been applied to Taylor-based implementations for computing the exponential, the cosine and the hyperbolic tangent matrix functions. Moreover, a particular example for the evaluation of the matrix exponential Taylor approximation of degree 15 requiring four matrix products was given, whereas the maximum polynomial degree available using Paterson–Stockmeyer method with four matrix products is 9. Based on this example, a new family of methods for evaluating matrix polynomials more efficiently than the Paterson–Stockmeyer method was proposed, having the potential to achieve a much higher efficiency, i.e., requiring less matrix products for evaluating a matrix polynomial of certain degree, or increasing the available degree for the same cost. However, the difficulty of these family of methods lies in the calculation of the coefficients involved for the evaluation of general matrix polynomials and approximations. In this paper, we provide a general matrix polynomial evaluation method for evaluating matrix polynomials requiring two matrix products less than the Paterson-Stockmeyer method for degrees higher than 30. Moreover, we provide general methods for evaluating matrix polynomial approximations of degrees 15 and 21 with four and five matrix product evaluations, respectively, whereas the maximum available degrees for the same cost with the Paterson–Stockmeyer method are 9 and 12, respectively. Finally, practical examples for evaluating Taylor approximations of the matrix cosine and the matrix logarithm accurately and efficiently with these new methods are given.

A parallel spatial and Bloch manifold regularized iterative reconstruction method for MR Fingerprinting

Magnetic Resonance Fingerprinting (MRF) reconstructs tissue maps based on a sequence of very highly undersampled images. In order to be able to perform MRF reconstruction, state-of-the-art MRF methods rely on priors such as the MR physics (Bloch equations) and might also use some additional low-rank or spatial regularization. However to our knowledge these three regularizations are not applied together in a joint reconstruction. The reason is that it is indeed challenging to incorporate effectively multiple regularizations in a single MRF optimization algorithm. As a result most of these methods are not robust to noise especially when the sequence length is short. In this paper, we propose a family of new methods where spatial and low-rank regularizations, in addition to the Bloch manifold regularization, are applied on the images. We show on digital phantom and NIST phantom scans, as well as volunteer scans that the proposed methods bring significant improvement in the quality of the estimated tissue maps.

The Role of Global Appearance of Omnidirectional Images in Relative Distance and Orientation Retrieval.

Over the last few years, mobile robotics has experienced a great development thanks to the wide variety of problems that can be solved with this technology. An autonomous mobile robot must be able to operate in a priori unknown environments, planning its trajectory and navigating to the required target points. With this aim, it is crucial solving the mapping and localization problems with accuracy and acceptable computational cost. The use of omnidirectional vision systems has emerged as a robust choice thanks to the big quantity of information they can extract from the environment. The images must be processed to obtain relevant information that permits solving robustly the mapping and localization problems. The classical frameworks to address this problem are based on the extraction, description and tracking of local features or landmarks. However, more recently, a new family of methods has emerged as a robust alternative in mobile robotics. It consists of describing each image as a whole, what leads to conceptually simpler algorithms. While methods based on local features have been extensively studied and compared in the literature, those based on global appearance still merit a deep study to uncover their performance. In this work, a comparative evaluation of six global-appearance description techniques in localization tasks is carried out, both in terms of accuracy and computational cost. Some sets of images captured in a real environment are used with this aim, including some typical phenomena such as changes in lighting conditions, visual aliasing, partial occlusions and noise.

On the global convergence of a fast Halley’s family to solve nonlinear equations

The purpose of this paper is to suggest an approach for increasing the convergence speed of Halley’s method to solve a non-linear equation. This approach is based on the second order Taylor polynomial and on Halley’s formula. By applying it a certain number of times, we obtain a new family of methods. The originality of this family is manifested in the fact that all its sequences are generated from one exceptional formula that depends on a natural integer parameter p. In addition, under certain conditions, the convergence speed of its sequences increases with p. The convergence analysis shows that the order of convergence of all proposed methods is three. A study on their global convergence is carried out. To illustrate the performance of this family, several numerical comparisons are made with other third and higher order methods.

Higher order Jarratt-like iterations for solving systems of nonlinear equations

In this article, we propose a new family of methods, such as Jarratt, with the fifth and sixth order. This includes some popular methods as special cases. We propose four different selection for parameter matrix Tk. The main advantage of the proposed methods is that they work well for any value of parameter “a” in the first stage of iterations, while the existing methods work only for some a(2/3or1/2). Thus, we extend essentially the domain of applicability of the original ones. Based on the computational efficiency analysis, we also made a selection of some high-efficiency ones among the families.

A New Class of Halley’s Method with Third-Order Convergence for Solving Nonlinear Equations

In this paper, we present a new family of methods for finding simple roots of nonlinear equations. The convergence analysis shows that the order of convergence of all these methods is three. The originality of this family lies in the fact that these sequences are defined by an explicit expression which depends on a parameterpwherepis a nonnegative integer. A first study on the global convergence of these methods is performed. The power of this family is illustrated analytically by justifying that, under certain conditions, the method convergence’s speed increases with the parameterp. This family’s efficiency is tested on a number of numerical examples. It is observed that our new methods take less number of iterations than many other third-order methods. In comparison with the methods of the sixth and eighth order, the new ones behave similarly in the examples considered.

Penalty-Free Any-Order Weak Galerkin FEMs for Elliptic Problems on Quadrilateral Meshes

This paper presents a family of weak Galerkin finite element methods for elliptic boundary value problems on convex quadrilateral meshes. These new methods use degree $$k \ge 0$$ polynomials separately in element interiors and on edges for approximating the primal variable. The discrete weak gradients of these shape functions are established in the local Arbogast–Correa $$AC_k $$ spaces. These discrete weak gradients are then used to approximate the classical gradient in the variational formulation. These new methods do not use any nonphysical penalty factor but produce optimal-order approximation to the primal variable, flux, normal flux, and divergence of flux. Moreover, these new solvers are locally conservative and offer continuous normal fluxes. Numerical experiments are presented to demonstrate the accuracy of this family of new methods.

Reference-enhanced x-ray single-particle imaging

X-ray single-particle imaging involves the measurement of a large number of noisy diffraction patterns of isolated objects in random orientations. The missing information about these patterns is then computationally recovered in order to obtain the 3D structure of the particle. While the method has promised to deliver room-temperature structures at near-atomic resolution, there have been significant experimental hurdles in collecting data of sufficient quality and quantity to achieve this goal. This paper describes two ways to modify the conventional methodology that significantly ease the experimental challenges, at the cost of additional computational complexity in the reconstruction procedure. Both these methods involve the use of holographic reference objects in close proximity to the sample of interest, whose structure can be described with only a few parameters. A reconstruction algorithm for recovering the unknown degrees of freedom is also proposed and tested with toy model simulations. The techniques proposed here enable 3D imaging of biomolecules that is not possible with conventional methods and open up a new family of methods for recovering structures from datasets with a variety of hidden parameters.

Generalized affine scaling algorithms for linear programming problems

Interior Point Methods are widely used to solve Linear Programming problems. In this work, we present two primal Affine Scaling algorithms to achieve faster convergence in solving Linear Programming problems. In the first algorithm, we integrate Nesterov’s restarting strategy in the primal Affine Scaling method with an extra parameter, which in turn generalizes the original primal Affine Scaling method. We provide the proof of convergence for the proposed generalized algorithm considering long step size. We also provide the proof of convergence for the primal and dual sequence without the degeneracy assumption. This convergence result generalizes the original convergence result for the Affine Scaling methods and it gives us hints about the existence of a new family of methods. Then, we introduce a second algorithm to accelerate the convergence rate of the generalized algorithm by integrating a non-linear series transformation technique. Our numerical results show that the proposed algorithms outperform the original primal Affine Scaling method.

Biorthogonal Rosenbrock-Krylov time discretization methods

Many scientific applications require the solution of large initial-value problems, such as those produced by the method of lines after semi-discretization in space of partial differential equations. The computational cost of implicit time discretizations is dominated by the solution of nonlinear systems of equations at each time step. In order to decrease this cost, the recently developed Rosenbrock-Krylov (ROK) time integration methods extend the classical linearly-implicit Rosenbrock(-W) methods, and make use of a Krylov subspace approximation to the Jacobian computed via an Arnoldi process. Since the ROK order conditions rely on the construction of a single Krylov space, no restarting of the Arnoldi process is allowed, and the iterations quickly become expensive with increasing subspace dimensions. This work extends the ROK framework to make use of the Lanczos biorthogonalization procedure for constructing Jacobian approximations. The resulting new family of methods is named biorthogonal ROK (BOROK). The Lanczos procedure's short two-term recurrence allows BOROK methods to utilize larger subspaces for the Jacobian approximation, resulting in increased numerical stability of the time integration at a reduced computational cost. Adaptive subspace size selection and basis extension procedures are also developed for the new schemes. Numerical experiments show that for stiff problems, where a large subspace used to approximate the Jacobian is required for stability, the BOROK methods outperform the original ROK methods.

Wind Energy Forecasting with Neural Networks: A Literature Review

Renewable energy is intermittent by nature and to integrate this energy into the Grid while assuring safety and stability the accurate forecasting of there newable energy generation is critical. Wind Energy prediction is based on the ability to forecast wind. There are many methods for wind forecasting based on the statistical properties of the wind time series and in the integration of meteorological information, these methods are being used commercially around the world. But one family of new methods for wind power fore castingis surging based on Machine Learning Deep Learning techniques. This paper analyses the characteristics of the Wind Speed time series data and performs a literature review of recently published works of wind power forecasting using Machine Learning approaches (neural and deep learning networks), which have been published in the last few years.

A new family of methods for single and multiple roots

We present a new family of iterative methods for multiple and single roots of nonlinear equations. This family contains as a special case the authors’ family for finding simple roots from Herceg and Herceg (2015). Some well-known classical methods for simple roots, for example Newton, Potra–Pták, Newton–Steffensen, King and Ostrowski’s methods, belong to this family, which implies that our new family contains modifications of these methods suitable for finding multiple roots. Convergence analysis shows that our family contains methods of convergence order from 2 to 4. The new methods require two function evaluations and one evaluation of the first derivative per iteration, so all our fourth order methods are optimal in terms of the Kung and Traub conjecture. Several examples are presented and compared. Through various test equations, relevant numerical experiments strongly support the claimed theory in this paper. Extraneous fixed points of the iterative maps associated with the proposed methods are also investigated. Their dynamics is explored along with illustrated basins of attraction for various polynomials.

SPMR: A Family of Saddle-Point Minimum Residual Solvers

We introduce a new family of saddle-point minimum residual methods for iteratively solving saddle-point systems using a minimum or quasi-minimum residual approach. No symmetry assumptions are made. The basic mechanism underlying the method is a novel simultaneous bidiagonalization procedure that yields a simplified saddle-point matrix on a projected Krylov-like subspace and allows for a monotonic short-recurrence iterative scheme. We develop a few variants, demonstrate the advantages of our approach, derive optimality conditions, and discuss connections to existing methods. Numerical experiments illustrate the merits of this new family of methods.