Search results for "Linear Algebra."
showing 10 items of 552 documents
2D motif basis applied to the classification of digital images
2016
The classification of raw data often involves the problem of selecting the appropriate set of features to represent the input data. Different types of features can be extracted from the input dataset, but only some of them are actually relevant for the classification process. Since relevant features are often unknown in real-world problems, many candidate features are usually introduced. This degrades both the speed and the predictive accuracy of the classifier due to the presence of redundancy in the set of candidate features. Recently, a special class of bidimensional motifs, i.e. 2D motif basis has been introduced in the literature. 2D motif basis showed to be powerful in capturing the r…
Characteristics of neuronal systems in the visual cortex
1987
The coupling complexity of cortical areas makes it very difficult to analyse them experimentally. Studies of model systems provide the possibility of adapting the analysis to the available data base and elaborating the fundamental properties that depend on the structure of the system. We propose a model system of variable complexity that is spatially two-dimensional and time-dependent, uses feedback for iteration and smoothing, includes the mapping of the cortical networks and can be nonlinear as the case requires. Combining such elementary systems on the basis of neuroanatomical findings enables us to simulate cortical mappings and to interpret neurophysiological data. The decisive factor …
Implicit-explicit and explicit projection schemes for the unsteady incompressible Navier–Stokes equations using a high-order dG method
2017
Abstract A modified version of the projection scheme [19] is proposed, which does not show a lower limit for the time step in contrast to the limits of stability observed numerically for some projection type schemes. An advantage of the proposed scheme is that the right-hand side of the Poisson equation for the pressure is independent of the time step. An explicit version of the current scheme is also provided besides the implicit-explicit one. For the implicit-explicit version, we retain divergence of the viscous terms on the right-hand side of the Poisson equation in order to achieve a higher accuracy for low Reynolds number flows. In this way, we also ensure that the Poisson equation wit…
Basis for a general theory of organizations
2011
Purpose – The purpose of this paper is to identify the conceptual basis shared by different theories, regardless of the unit of analysis they specifically adopt. The different ontological choice (or different segment of reality studied by each theory) does not hinder conceptual common ground for a good number of organisational theories.Design/methodology/approach – The paper highlights the importance of hierarchical, social and institutional relations and of the technological, cognitive, social and institutional contents. It looks at the common conceptual contents of the two main theories examined, and those of a wide set of other theories addressed here. Both of the theories examined are i…
The Study of Dynamic Objects Identification Algorithms Based on Anisotropic Properties of Generalized Amplitude-Phase Images
2018
The article presents some results of dynamical objects identification technology based on coincidence matrixes of templates and tested objects’ amplitude-phase images (APIm) calculated with discrete Hilbert transforms (DHT). DHT algorithms are modeled on basis of isotropic (HTI), anisotropic (HTA), generalized transforms – AP-analysis (APA) and the difference (residual) relative shifted phase (DRSP-) images to calculate the APIm. The identified objects are recognized as members of classes modeled with 3D templates – images of different types airplanes rotated in space. The dynamic anisotropic properties of APIm causes the increasing of sensitivity to circular angle rotation and make possibl…
Identifying the characteristics of China’s maritime trading partners on the basis of bilateral shipping connectivity: a cluster analysis
2021
China is ranked as the number one maritime connected country in the world. This study attempts to analyse the characteristics of its 155 maritime trading partners. Five components of maritime conne...
Semisupervised nonlinear feature extraction for image classification
2012
Feature extraction is of paramount importance for an accurate classification of remote sensing images. Techniques based on data transformations are widely used in this context. However, linear feature extraction algorithms, such as the principal component analysis and partial least squares, can address this problem in a suboptimal way because the data relations are often nonlinear. Kernel methods may alleviate this problem only when the structure of the data manifold is properly captured. However, this is difficult to achieve when small-size training sets are available. In these cases, exploiting the information contained in unlabeled samples together with the available training data can si…
Kernel-Based Inference of Functions Over Graphs
2018
Abstract The study of networks has witnessed an explosive growth over the past decades with several ground-breaking methods introduced. A particularly interesting—and prevalent in several fields of study—problem is that of inferring a function defined over the nodes of a network. This work presents a versatile kernel-based framework for tackling this inference problem that naturally subsumes and generalizes the reconstruction approaches put forth recently for the signal processing by the community studying graphs. Both the static and the dynamic settings are considered along with effective modeling approaches for addressing real-world problems. The analytical discussion herein is complement…
Model selection based product kernel learning for regression on graphs
2013
The choice of a suitable graph kernel is intrinsically hard and often cannot be made in an informed manner for a given dataset. Methods for multiple kernel learning offer a possible remedy, as they combine and weight kernels on the basis of a labeled training set of molecules to define a new kernel. Whereas most methods for multiple kernel learning focus on learning convex linear combinations of kernels, we propose to combine kernels in products, which theoretically enables higher expressiveness. In experiments on ten publicly available chemical QSAR datasets we show that product kernel learning is on no dataset significantly worse than any of the competing kernel methods and on average the…
Comparison of Different Methods for the Calculation of Indices of Paternity
1992
The qualitative decision about paternity in trio cases on the basis of DNA multilocus profiles is no problem. If there are more than 1 or 2 exclusion patterns (band present in child, which is neither present in mother or alleged father), the putative father has to be excluded. The problems arise, if, in the case of a non exclusion, one wants to quantify the evidence for paternity. Different statistics have been proposed for this purpose. This paper discusses three of these statistics and demonstrates their application to real data.