Search
Search results for: GRADIENT-WEIGHTED CLASS ACTIVATION MAPPING
-
Computer-Aided Diagnosis of COVID-19 from Chest X-ray Images Using Hybrid-Features and Random Forest Classifier
PublicationIn recent years, a lot of attention has been paid to using radiology imaging to automatically find COVID-19. (1) Background: There are now a number of computer-aided diagnostic schemes that help radiologists and doctors perform diagnostic COVID-19 tests quickly, accurately, and consistently. (2) Methods: Using chest X-ray images, this study proposed a cutting-edge scheme for the automatic recognition of COVID-19 and pneumonia....
-
Deep Features Class Activation Map for Thermal Face Detection and Tracking
PublicationRecently, capabilities of many computer vision tasks have significantly improved due to advances in Convolutional Neural Networks. In our research, we demonstrate that it can be also used for face detection from low resolution thermal images, acquired with a portable camera. The physical size of the camera used in our research allows for embedding it in a wearable device or indoor remote monitoring solution for elderly and disabled...
-
Weighted Ensemble with one-class Classification and Over-sampling and Instance selection (WECOI): An approach for learning from imbalanced data streams
Publication -
Generalized Gradient Equivariant Multivalued Maps, Approximation and Degree
PublicationConsider the Euclidean space Rn with the orthogonal action of a compact Lie group G. We prove that a locally Lipschitz G-invariant mapping f from Rn to R can be uniformly approximated by G-invariant smooth mappings g in such a way that the gradient of g is a graph approximation of Clarke’s generalized gradient of f . This result enables a proper development of equivariant gradient degree theory for a class of set-valued gradient...
-
A Note on Reduced Strain Gradient Elasticity
PublicationWe discuss the particular class of strain-gradient elastic material models which we called the reduced or degenerated strain-gradient elasticity. For this class the strain energy density depends on functions which have different differential properties in different spatial directions. As an example of such media we consider the continual models of pantographic beam lattices and smectic and columnar liquid crystals.
-
Tropospheric delays derived from GNSS observations during the derecho event in Poland of 11th August 2017
Open Research DataPropagation of global navigation satellite systems (GNSS) radio signals is disturbed by the current state of the Earth's atmosphere. For this reason, advances processing of GNSS signals can be used for investigation of the atmospheric condition. In case of troposphere, the GNSS signals allow for obtain information of tropospheric delay, which is mainly...
-
Shared processor scheduling
PublicationWe study the shared processor scheduling problem with a single shared processor to maximize total weighted overlap, where an overlap for a job is the amount of time it is processed on its private and shared processor in parallel. A polynomial-time optimization algorithm has been given for the problem with equal weights in the literature. This paper extends that result by showing an (log)-time optimization algorithm for a class...
-
Ellipticity in couple-stress elasticity
PublicationWe discuss ellipticity property within the linear couple-stress elasticity. In this theory, there exists a deformation energy density introduced as a function of strains and gradient of macrorotations, where the latter are expressed through displacements. So the couple-stress theory could be treated as a particular class of strain gradient elasticity. Within the micropolar elasticity, the model is called Cosserat pseudocontinuum...
-
New approach to noncausal identification of nonstationary stochastic systems subject to both smooth and abrupt parameter changes
PublicationIn this paper we consider the problem of finiteintervalparameter smoothing for a class of nonstationary linearstochastic systems subject to both smooth and abrupt parameterchanges. The proposed parallel estimation scheme combines theestimates yielded by several exponentially weighted basis functionalgorithms. The resulting smoother automatically adjustsits smoothing bandwidth to the type and rate of nonstationarityof the identified...
-
On nonlinear dilatational strain gradient elasticity
PublicationWe call nonlinear dilatational strain gradient elasticity the theory in which the specific class of dilatational second gradient continua is considered: those whose deformation energy depends, in an objective way, on the gradient of placement and on the gradient of the determinant of the gradient of placement. It is an interesting particular case of complete Toupin–Mindlin nonlinear strain gradient elasticity: indeed, in it, the...
-
On the well posedness of static boundary value problem within the linear dilatational strain gradient elasticity
PublicationIn this paper, it is proven an existence and uniqueness theorem for weak solutions of the equilibrium problem for linear isotropic dilatational strain gradient elasticity. Considered elastic bodies have as deformation energy the classical one due to Lamé but augmented with an additive term that depends on the norm of the gradient of dilatation: only one extra second gradient elastic coefficient is introduced. The studied class...
-
On existence and uniqueness of weak solutions for linear pantographic beam lattices models
PublicationIn this paper, we discuss well-posedness of the boundary-value problems arising in some “gradientincomplete” strain-gradient elasticity models, which appear in the study of homogenized models for a large class ofmetamaterials whosemicrostructures can be regarded as beam lattices constrained with internal pivots. We use the attribute “gradient-incomplete” strain-gradient elasticity for a model in which the considered strain energy...
-
New Approach to Noncasual Identification of Nonstationary Stochastic FIR Systems Subject to Both Smooth and Abrupt Parameter Changes
PublicationIn this technical note, we consider the problem of finite-interval parameter smoothing for a class of nonstationary linear stochastic systems subject to both smooth and abrupt parameter changes. The proposed parallel estimation scheme combines the estimates yielded by several exponentially weighted basis function algorithms. The resulting smoother automatically adjusts its smoothing bandwidth to the type and rate of nonstationarity...
-
Explainable machine learning for diffraction patterns
PublicationSerial crystallography experiments at X-ray free-electron laser facilities produce massive amounts of data but only a fraction of these data are useful for downstream analysis. Thus, it is essential to differentiate between acceptable and unacceptable data, generally known as ‘hit’ and ‘miss’, respectively. Image classification methods from artificial intelligence, or more specifically convolutional neural networks (CNNs), classify...
-
Flexomagneticity in buckled shear deformable hard-magnetic soft structures
PublicationThis research work performs the first time exploring and addressing the flexomagnetic property in a shear deformable piezomagnetic structure. The strain gradient reveals flexomagneticity in a magnetization phenomenon of structures regardless of their atomic lattice is symmetrical or asymmetrical. It is assumed that a synchronous converse magnetization couples both piezomagnetic and flexomagnetic features into the material structure....
-
Chromatic cost coloring of weighted bipartite graphs
PublicationGiven a graph G and a sequence of color costs C, the Cost Coloring optimization problem consists in finding a coloring of G with the smallest total cost with respect to C. We present an analysis of this problem with respect to weighted bipartite graphs. We specify for which finite sequences of color costs the problem is NP-hard and we present an exact polynomial algorithm for the other finite sequences. These results are then extended...
-
On Nonlinear Bending Study of a Piezo-Flexomagnetic Nanobeam Based on an Analytical-Numerical Solution
PublicationAmong various magneto-elastic phenomena, flexomagnetic (FM) coupling can be defined as a dependence between strain gradient and magnetic polarization and, contrariwise, elastic strain and magnetic field gradient. This feature is a higher-order one than piezomagnetic, which is the magnetic response to strain. At the nanoscale, where large strain gradients are expected, the FM effect is significant and could be even dominant. In...
-
Smart Approach for Glioma Segmentation in Magnetic Resonance Imaging using Modified Convolutional Network Architecture (U-NET)
PublicationSegmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on...
-
On optimal tracking of rapidly varying telecommunication channels
PublicationWhen parameters of mobile telecommunication channels change rapidly, classical adaptive filters, such as exponentially weighted least squares algorithms or gradient algorithms, fail to estimate them with sufficient accuracy. In cases like this, one can use identification methods based on explicit models of parameter changes such as the method of basis functions (BF). When prior knowledge about parameter changes is available the...
-
A variational approach of homogenization of piezoelectric composites towards piezoelectric and flexoelectric effective media
PublicationThe effective piezoelectric properties of heterogeneous materials are evaluated in the context of periodic homogenization, whereby a variational formulation is developed, articulated with the extended Hill macrohomogeneity condition. The entire set of homogenized piezoelectric moduli is obtained as the volumetric averages of the microscopic properties of the individual constituents weighted by the displacement and polarization...
-
Expedited antenna optimization with numerical derivatives and gradient change tracking
PublicationDesign automation has been playing an increasing role in the development of novel antenna structures for various applications. One of its aspects is electromagnetic (EM)-driven design closure, typically applied upon establishing the antenna topology, and aiming at adjustment of geometry parameters to boost the performance figures as much as possible. Parametric optimization is often realized using local methods given usually reasonable...
-
Deformation of an elastic second gradient spherical body under equatorial line density of dead forces
PublicationWe consider deformations of an elastic body having initially a spherical shape. Assumed deformation energy depends on the first and second gradient of displacements. We apply an equatorial line density of dead loads, that are forces per unit line length directed in radial direction and applied along the equator of the sphere. We restrict ourselves our analysis to the case of linearized second strain gradient isotropic elasticity...
-
On noncausal weighted least squares identification of nonstationary stochastic systems
PublicationIn this paper, we consider the problem of noncausal identification of nonstationary, linear stochastic systems, i.e., identification based on prerecorded input/output data. We show how several competing weighted (windowed) least squares parameter smoothers, differing in memory settings, can be combined together to yield a better and more reliable smoothing algorithm. The resulting parallel estimation scheme automatically adjusts...
-
On weak solutions of the boundary value problem within linear dilatational strain gradient elasticity for polyhedral Lipschitz domains
PublicationWe provide the proof of an existence and uniqueness theorem for weak solutions of the equilibrium problem in linear dilatational strain gradient elasticity for bodies occupying, in the reference configuration, Lipschitz domains with edges. The considered elastic model belongs to the class of so-called incomplete strain gradient continua whose potential energy density depends quadratically on linear strains and on the gradient of...
-
A study of the kinetics of bismuth telluride synthesis by an oxide reduction method
PublicationThe kinetics of a reduction of bismuth and tellurium oxides in a hydrogen atmosphere, leading to the formation of thermoelectric bismuth telluride is investigated. The evaluation of the reaction kinetics was based on a thermogravimetric analysis performed in non-isothermal conditions. A non-parametric analysis method and the Friedman method were used for the evaluation of the data. Additionally, for a better understanding of the...
-
M-integral for finite anti-plane shear of a nonlinear elastic matrix with rigid inclusions
PublicationThe path-independent M-integral plays an important role in analysis of solids with inhomogeneities. However, the available applications are almost limited to linear-elastic or physically non-linear power law type materials under the assumption of infinitesimal strains. In this paper we formulate the M-integral for a class of hyperelastic solids undergoing finite anti-plane shear deformation. As an application we consider the problem...
-
Homotopy invariance of the Conley index and local Morse homology in Hilbert spaces
PublicationIn this paper we introduce a new compactness condition — Property-(C) — for flows in (not necessary locally compact) metric spaces. For such flows a Conley type theory can be developed. For example (regular) index pairs always exist for Property-(C) flows and a Conley index can be defined. An important class of flows satisfying the this compactness condition are LS-flows. We apply E-cohomology to index pairs of LS-flows and obtain...
-
On forced vibrations of piezo-flexomagnetic nano-actuator beams
PublicationThe effect of excitation frequency on the piezomagnetic Euler-Bernoulli nanobeam taking the flexomagnetic material phenomenon into consideration is investigated in this chapter. The magnetization with strain gradients creates flexomagneticity. We couple simultaneously the piezomagnetic and flexomagnetic properties in an inverse magnetization. Resemble the flexoelectricity, the flexomagneticity is also size-dependent. So, it has...
-
Conversion of waste biomass into activated carbon and evaluation of environmental consequences using life cycle assessment
PublicationIn this article, activated carbon was produced from Lantana camara and olive trees by H3PO4 chemical activation. The prepared activated carbons were analyzed by characterizations such as scanning electron microscopy, energy-dispersive X-ray spectroscopy, Brunauer–Emmett–Teller, X-ray diffraction, thermogravimetric analysis, and Fourier transform infrared spectroscopy. H3PO4 is used as an activator agent to create an abundant pore...
-
Study of Multi-Class Classification Algorithms’ Performance on Highly Imbalanced Network Intrusion Datasets
PublicationThis paper is devoted to the problem of class imbalance in machine learning, focusing on the intrusion detection of rare classes in computer networks. The problem of class imbalance occurs when one class heavily outnumbers examples from the other classes. In this paper, we are particularly interested in classifiers, as pattern recognition and anomaly detection could be solved as a classification problem. As still a major part of...
-
The cohomological span of LS-Conley index
PublicationIn this paper we introduce a new homotopy invariant – the cohomological span of LS-Conley index. We prove the theorems on the existence of critical points for a class of strongly indefinite functionals with the gradient of the form Lx+K(x), where L is bounded linear and K is completely continuous. We give examples of Hamiltonian systems for which our methods give better results than the Morse inequalities. We also give a formula...
-
Low-fidelity model considerations for simulation-based optimisation of miniaturised wideband antennas
PublicationHere, variable-fidelity electromagnetic (EM)-based design optimisation of miniaturised antennas is discussed. The authors focus on an appropriate selection of discretisation density of the low-fidelity EM model, which results in good performance of the optimisation algorithm in terms of its computational complexity and reliability. Trust-region gradient search with low-fidelity model corrected by means of non-linear frequency scaling...
-
On low-fidelity models for variable-fidelity simulation-driven design optimization of compact wideband antennas
PublicationThe paper addresses simulation-driven design optimization of compact antennas involving variable-fidelity electromagnetic (EM) simulation models. Comprehensive investigations are carried out concerning selection of the coarse model discretization density. The effects of the low-fidelity model setup on the reliability and computational complexity of the optimization process are determined using a benchmark set of three ultra-wideband...
-
On the Existence of Homoclinic Type Solutions of a Class of Inhomogenous Second Order Hamiltonian Systems
PublicationWe show the existence of homoclinic type solutions of a class of inhomogenous second order Hamiltonian systems, where a C1-smooth potential satisfies a relaxed superquadratic growth condition, its gradient is bounded in the time variable, and a forcing term is sufficiently small in the space of square integrable functions. The idea of our proof is to approximate the original system by time-periodic ones, with larger and larger...
-
A MODEL FOR FORECASTING PM10 LEVELS WITH THE USE OF ARTIFICIAL NEURAL NETWORKS
PublicationThis work presents a method of forecasting the level of PM10 with the use of artificial neural networks. Current level of particulate matter and meteorological data was taken into account in the construction of the model (checked the correlation of each variable and the future level of PM10), and unidirectional networks were used to implement it due to their ease of learning. Then, the configuration of the network (built on the...
-
Catalytic impact of alloyed Al on the corrosion behavior of Co50Ni23Ga26Al1.0 magnetic shape memory alloy and catalysis applications for efficient electrochemical H2 generation
PublicationThe electrochemical and corrosion behaviour of Co50Ni23Ga27-xAlx (x = 0 and 1.0 wt%) magnetic shape memory alloys (MSMAs) was studied in 0.5 M NaCl solutions using various electrochemical techniques. Results showed remarkable activation of the tested MSMA toward pitting corrosion upon alloying it with Al. XPS examination confirmed the activation influence of alloyed Al. It proved that the presence of Al in the alloy's matrix weakens...
-
On the Equations of the Surface Elasticity Model Based on the Theory of Polymeric Brushes
PublicationMotivating by theory of polymers, in particular, by the models of polymeric brushes we present here the homogenized (continual) two-dimensional (2D) model of surface elasticity. A polymeric brush consists of an system of almost aligned rigid polymeric chains. The interaction between chain links are described through Stockmayer potential, which take into account also dipole-dipole interactions. The presented 2D model can be treated...
-
Hourly GNSS-derived integrated moisture in the global tropics for the years 2001-2018
Open Research DataGlobal tropics are essential in formulating weather patterns and climate across various latitudes through atmospheric teleconnections. Since water vapour is an essential parameter in atmospheric convection and, thus, latent heat release, its tropical variability on different time scales is crucial in understanding weather and climate changes. The provided...
-
Self-Organising map neural network in the analysis of electromyography data of muscles acting at temporomandibular joint.
PublicationThe temporomandibular joint (TMJ) is the joint that via muscle action and jaw motion allows for necessary physiological performances such as mastication. Whereas mandible translates and rotates [1]. Estimation of activity of muscles acting at the TMJ provides a knowledge of activation pattern solely of a specific patient that an electromyography (EMG) examination was carried out [2]. In this work, a Self-Organising Maps (SOMs)...
-
COVID-19 severity forecast based on machine learning and complete blood count data
PublicationProper triage of COVID-19 patients is a key factor in eective case management, especially with limited and insucient resources. In this paper, we propose a machine-aided diagnostic system to predict how badly a patient with COVID-19 will develop disease. The prognosis of this type is based on the parameters of commonly used complete blood count tests, which makes it possible to obtain data from a wide range of patients.We chose...
-
COVID-19 severity forecast based on machine learning and complete blood count data
PublicationProper triage of COVID-19 patients is a key factor in eective case management, especially with limited and insucient resources. In this paper, we propose a machine-aided diagnostic system to predict how badly a patient with COVID-19 will develop disease. The prognosis of this type is based on the parameters of commonly used complete blood count tests, which makes it possible to obtain data from a wide range of patients.We chose...
-
MSIS sonar image segmentation method based on underwater viewshed analysis and high-density seabed model
PublicationHigh resolution images of Mechanically Scanned Imaging Sonars can bring detailed representation of underwater area if favorable conditions for acoustic signal to propagate are provided. However to properly asses underwater situation based solely on such data can be challenging for less than proficient interpreter. In this paper we propose a method to enhance interpretative potential of MSIS image by dividing it in to subareas depending...
-
Intelligent Decision Forest Models for Customer Churn Prediction
PublicationCustomer churn is a critical issue impacting enterprises and organizations, particularly in the emerging and highly competitive telecommunications industry. It is important to researchers and industry analysts interested in projecting customer behavior to separate churn from non‐churn consumers. The fundamental incentive is a firm’s intent desire to keep current consumers, along with the exorbitant expense of gaining new ones....
-
The concept of experience marketing - examples of practical application, (W), sem. 02, zimowy 22/23
e-Learning CoursesCelem przedmiotu jest zaznajomienie studentów z koncepcją marketingu doświadczeń, będącego coraz częściej obligatoryjną podstawą innowacyjnych strategii marketingowych przedsiębiorstw oraz ukazanie praktycznego zastosowania niniejszej idei (zarządzanie doświadczeniami, strategiczne moduły doświadczeń, mapowanie podróży klienta i pracownika firmy). The aim of the course is to familiarize students with the concept of experience...
-
Thermal buckling of functionally graded piezomagnetic micro- and nanobeams presenting the flexomagnetic effect
PublicationGalerkin weighted residual method (GWRM) is applied and implemented to address the axial stability and bifurcation point of a functionally graded piezomagnetic structure containing flexomagneticity in a thermal environment. The continuum specimen involves an exponential mass distributed in a heterogeneous media with a constant square cross section. The physical neutral plane is investigated to postulate functionally graded material...
-
The Use of an Ontotrigger for Designing the Ontology of a Model Maturity Capsule
PublicationThe aim of this work is to give the definition and present the possibility of applying (introduced and defined here) ontotriggers to design the ontology of a maturity capsule used in the assessment of IT projects. The complexity of designing ontology processes raises the question of whether there is a need for designing ontologies in a situation where it is possible to map them. The work is divided into four main parts. The first...
-
Reduced-Cost Microwave Design Closure by Multi-Resolution EM Simulations and Knowledge-Based Model Management
PublicationParameter adjustment through numerical optimization has become a commonplace of contemporary microwave engineering. Although circuit theory methods are ubiquitous in the development of microwave components, the initial designs obtained with such tools have to be further tuned to improve the system performance. This is particularly pertinent to miniaturized structures, where the cross-coupling effects cannot be adequately accounted...
-
Levels of 13 multi-class pesticide residues in Polish honeys determined by LC-ESI-MS/MS
PublicationLevels of 13 pesticides in 40 honey samples form Poland are reported. A rapid and sensitive method was developed for the LC-ESI-MS/MS determination of multi-class pesticide residues in honey samples. Liquid-liquid extraction (LLE) on a diatomaceous earth support (requiring the use of small amounts of organic solvent), followed by chromatographic separation on a C18 column and gradient elution were employed. The method quantifies...
-
Surface effects of network materials based on strain gradient homogenized media
PublicationThe asymptotic homogenization of periodic network materials modeled as beam networks is pursued in this contribution, accounting for surface effects arising from the presence of a thin coating on the surface of the structural beam elements of the network. Cauchy and second gradient effective continua are considered and enhanced by the consideration of surface effects. The asymptotic homogenization technique is here extended to...
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublicationThe diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) - the most popular kind of deep learning algorithms...