Filters
total: 7584
filtered: 6373
-
Catalog
- Publications 6373 available results
- Journals 249 available results
- Conferences 107 available results
- People 338 available results
- Projects 18 available results
- Laboratories 3 available results
- e-Learning Courses 306 available results
- Events 11 available results
- Open Research Data 179 available results
Chosen catalog filters
displaying 1000 best results Help
Search results for: SURROGATE MODELING , ANTENNA DESIGN , DOMAIN CONFINEMENT , NESTED KRIGING , DEEP NEURAL NETWORKS
-
Neural Networks Based on Ultrafast Time-Delayed Effects in Exciton Polaritons
Publication -
Extended Hopfield models of neural networks for combinatorial multiobjective optimization problems
Publication -
Analysis of electrical patterns activity in artificial multi-stable neural networks
Publication -
Musical phrase representation and recognition by means of neural networks and rough sets.
PublicationW artykule przedstawiono podstawowe definicje dotyczące frazy muzycznej. W eksperymentach posłużono się zapisem parametrycznym. W celu wzmocnienia procesu rozpoznawania wykorzystano kodowanie entropijne muzyki. W eksperymentach klasyfikacji oparto się o sztuczne sieci neuronowe i metodę zbiorów przybliżonych. Słowa kluczowe: fraza muzyczna, klasyfikacja, sztuczne sieci neuronowe, metoda zbiorów przybliżonych
-
Processing of musical data employing rough sets and artificial neural networks
PublicationArtykuł opisuje założenia systemu automatycznej identyfikacji muzyki i dźwięków muzycznych. Dokonano przeglądu standardu MPEG-7, ze szczególnym naciskiem na parametry opisowe dźwięku. Przedyskutowano problemy analizy danych audio, związane z zastosowaniami wykorzystującymi MPEG-7. W oparciu o eksperymenty przedstawiono efektywność deskryptorów niskiego poziomu w automatycznym rozpoznawaniu dźwięków instrumentów muzycznych. Przedyskutowano...
-
Comparison of effectiveness of musical sound separation algorithms employing neural networks.
PublicationNiniejszy referat przedstawia kilka algorytmów służących do separacji dźwięków instrumentów muzycznych. Zaproponowane podejście do dekompozycji miksów dźwiękowych opiera się na założeniu, że wysokość dźwięków w miksie jest znana, tzn. wejściem dla algorytmów jest przebieg zmian wysokości dźwięków składowych miksu. Proces estymacji fazy i amplitudy składowych harmonicznych wykorzystuje dopasowywanie zespolonych przebiegów harmonicznych...
-
Processing of musical data employing rough sets and artificial neural networks
PublicationArtykuł opisuje założenia systemu automatycznej identyfikacji muzyki i dźwięków muzycznych. Dokonano przeglądu standardu MPEG-7, ze szczególnym naciskiem na parametry opisowe dźwięku. Przedyskutowano problemy analizy danych audio, związane z zastosowaniami wykorzystującymi MPEG-7. W oparciu o eksperymenty przedstawiono efektywność deskryptorów niskiego poziomu w automatycznym rozpoznawaniu dźwięków instrumentów muzycznych. Przedyskutowano...
-
Estimation of musical sound separation algorithm effectiveness employing neural networks.
PublicationŚlepa separacja dźwięków sygnałów muzycznych zawartych w zmiksowanym materiale jest trudnym zadaniem. Jest to spowodowane tym, że dźwięki znajdujące się w relacjach harmonicznych mogą zawierać kolidujące składowe sinusoidalne (składowe harmoniczne). Ewaluacja wyników separacji jest również problematyczna, gdyż analiza błędu energetycznego często nie odzwierciedla subiektywnej jakości odseparowanych sygnałów. W tej publikacji zostały...
-
The concept of application of artificial neural networks for cultivation controlof cartilages in bioreactors.
PublicationNowym elementem niniejszej pracy jest omówienie problemów związanych z możliwością sterowania parametrami hydrodynamicznymi hodowanej w bioreaktorze chrząstki stawowej przy wykorzystaniu sztucznych sieci neuronowych. Przedstawiona została architektura strategii sterowania hodowlą tkanki z zastosowaniem tych sieci.
-
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
Publication -
Automatic singing voice recognition employing neural networks and rough sets
PublicationCelem prac opisanych w referacie jest automatyczne rozpoznawanie głosów śpiewaczych. Do tego celu utworzona została baza nagrań próbek śpiewu profesjonalnego i amatorskiego. Próbki poddane zostały parametryzacji parametrami zaproponowanymi przez autorów ściśle do tego celu. Sposób wyznaczenia parametrów i ich interpretacja fizyczna przedstawione są w referacie. Parametry wprowadzane są do systemów decyzyjnych, klasyfikatorów opartych...
-
Fast Multi-Objective Antenna Optimization Using Sequential Patching and Variable-Fidelity EM Models
PublicationIn this work, a technique for fast multi-objective design optimization of antenna structures is presented. In our approach, the initial approximation of the Pareto set representing the best possible trade-offs between conflicting design objectives is obtained by means of sequential patching of the design space. The latter is a stencil-based search that aims at creating a path that connects the extreme Pareto-optimal designs (obtained...
-
Variable-Fidelity Simulation Models and Sparse Gradient Updates for Cost-Efficient Optimization of Compact Antenna Input Characteristics
PublicationDesign of antennas for the Internet of Things (IoT) applications requires taking into account several performance figures, both electrical (e.g., impedance matching) and field (gain, radiation pattern), but also physical constraints, primarily concerning size limitation. Fulfillment of stringent specifications necessitates the development of topologically complex structures described by a large number of geometry parameters that...
-
BIG DATA SIGNIFICANCE IN REMOTE MEDICAL DIAGNOSTICS BASED ON DEEP LEARNING TECHNIQUES
PublicationIn this paper we discuss the evaluation of neural networks in accordance with medical image classification and analysis. We also summarize the existing databases with images which could be used for training deep models that can be later utilized in remote home-based health care systems. In particular, we propose methods for remote video-based estimation of patient vital signs and other health-related parameters. Additionally, potential...
-
Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
PublicationThe vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron,...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublicationThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
Measures of region failure survivability for wireless mesh networks
PublicationWireless mesh networks (WMNs) are considered as a promising alternative to wired local, or metropolitan area networks. However, owing to their exposure to various disruptive events, including natural disasters, or human threats, many WMN network elements located close to the failure epicentre are frequently in danger of a simultaneous failure, referred to as a region failure. Therefore, network survivability, being the ability...
-
Design and optimization of a novel compact broadband linearly/circularly polarized wide-slot antenna for WLAN and Wi-MAX applications
PublicationA novel topologically modified structure of a compact low profile wide-slot antenna for broadband applications is presented. The antenna comprises a modified E-shaped slot with unequal arm lengths in the ground plane, and a parasitic quasi-rectangular loop placed coplanar with the feedline. For exciting orthogonal modes with equal amplitude, a single-point feeding technique with an asymmetrical geometry of the coplanar waveguide...
-
Accurate Modeling of Frequency Selective Surfaces Using Fully-Connected Regression Model with Automated Architecture Determination and Parameter Selection Based on Bayesian Optimization
PublicationSurrogate modeling has become an important tool in the design of high-frequency structures. Although full-wave electromagnetic (EM) simulation tools provide an accurate account for the circuit characteristics and performance, they entail considerable computational expenditures. Replacing EM analysis by fast surrogates provides a way to accelerate the design procedures. Unfortunately, modeling of microwave passives is a challenging...
-
Time Domain Modeling of Propeller Forces due to Ventilation in Static and Dynamic Conditions
Publication -
Design and modeling of the piezoelectric motor based on three resonance actuators
PublicationThis paper describes a piezoelectric motor which combines advantages from two existing piezoelectric motors topologies. The research work presents the design, simulations and measurements of the piezoelectric motor with three rotation-mode actuators. The aim of the project was to obtain the high speed piezoelectric motor. Other advantages of this conception are blocking torque, short response times, the ability to work in a hostile...
-
Robust design in delta domain for SISO plants: PI and PID controllers
PublicationW pracy przedstawiono zunifikowaną metodę numerycznie odpornej syntezy sterowników (regulatorów) działających w dyskretnym czasie w układach sterowania skalarnymi obiektami czasu ciągłego. Wykorzystano dyskretnoczasowe modele takich obiektów, oparte na tak zwanym operatorze delta, charakteryzującym się korzystnymi odpornościowymi cechami w przypadku stosowania dostatecznie małych wartości okresu próbkowania przetwarzanych sygnałów....
-
OmicSelector: automatic feature selection and deep learning modeling for omic experiments
Publication -
Variable Data Structures and Customized Deep Learning Surrogates for Computationally Efficient and Reliable Characterization of Buried Objects
PublicationIn this study, in order to characterize the buried object via deep-learning-based surrogate modeling approach, 3-D full-wave electromagnetic simulations of a GPR model has been used. The task is to predict simultaneously and independent of each characteristic parameters of a buried object of several radii at different positions (depth and lateral position) in various dispersive subsurface media. This study has analyzed variable...
-
Ultracapacitor modeling and control with discrete fractional order artificial neural network
Publication -
Accidental wow evaluation based on sinusoidal modeling and neural nets prediction
PublicationReferat przedstawia opis algorytmu do określenia charakterystyki zniekształcenia kołysania dźwięku. Prezentowane podejście wykorzystuje sinusoidalną analizę dźwięku bazującą zarówno na amplitudowym jak i fazowym widmie sygnału fonicznego. Trajektorie poszczególnych składowych tonalnych, obrazujące zniekształcenie kołysania, określane są na podstawie analizy ich chwilowych amplitud, częstotliwości i faz. Dodatkowo referat przedstawia...
-
Modelling of residential sales price with kriging using different distance metrics in different correlation functions
PublicationThe modelling and estimation of sales prices based on economical conditions are important for housing sector especially in developing countries. Analysts are focused on the subject to analyze price movements and estimate the future trend of the sales prices for housing sector. In this study, we tried to generate a robust and efficient model related to the subject. Firstly, we investigated economic variables affecting housing sales...
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
Numerical modeling of force and contact networks in fragmented sea ice
Publication -
Modeling of Wireless Traffic Load in Next Generation Wireless Networks
Publication -
Rapid multi-objective design optimisation of compact microwave couplers by means of physics-based surrogates
PublicationThe authors introduce a methodology for fast multi-objective design optimisation of miniaturised microwave couplers. The approach exploits the surrogate-based optimisation paradigm with an underlying low-fidelity model constructed from an equivalent circuit of the structure under consideration, corrected through implicit and frequency space mapping. A fast prediction tool obtained this way is subsequently optimised by a multi-objective...
-
On Fast Multi-objective Optimization of Antenna Structures Using Pareto Front Triangulation and Inverse Surrogates
PublicationDesign of contemporary antenna systems is a challenging endeavor, where conceptual developments and initial parametric studies, interleaved with topology evolution, are followed by a meticulous adjustment of the structure dimensions. The latter is necessary to boost the antenna performance as much as possible, and often requires handling several and often conflicting objectives, pertinent to both electrical and field properties...
-
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...
-
Brain-Inspired Deep Networks for Facial Expression Recognition. Frontiers in Biomedical Technologies
Publication -
Compact antenna array comprising fractal-shaped microstripradiators
PublicationA design method of antenna array consisting of eight microstrip patches modified with Sierpinski fractal curves has been presented andexperimentally validated in this paper. Method proposed has enabled the achievement of considerable miniaturization of array length (26%),together with multi-band behavior of the antenna, which proves the attractiveness of presented design methodology and its ability to be implemented in more complex...
-
Design and Analysis of Artificial Neural Network (ANN) Models for Achieving Self-Sustainability in Sanitation
PublicationThe present study investigates the potential of using fecal ash as an adsorbent and demonstrates a self-sustaining, optimized approach for urea recovery from wastewater streams. Fecal ash was prepared by heating synthetic feces to 500 °C and then processing it as an adsorbent for urea adsorption from synthetic urine. Since this adsorption approach based on fecal ash is a promising alternative for wastewater treatment, it increases...
-
EXPERIMENTAL AND THEORETICAL FLOW OF THE FORCES IN DEEP BEAMS WITH CANTILEVAR
PublicationThis article presents the results of experimental research carried out on deep beams with cantilever which was loaded throughout the depth. The main deep beam was directly simply supported on the one side. On the other side the deep beam was suspended in another deep member situated at right angles. All deep beams created a spatial arrangement. The paper is focused on the analysis of the cracks morphology and flow of the internal...
-
Adsorption chiller in a combined heating and cooling system: simulation and optimization by neural networks
Publication -
Self-organizing Artificial Neural Networks into Hydrographic Big Data Reduction Process
Publication -
Artificial Neural Networks in Classification of Steel Grades Based on Non-Destructive Tests
Publication -
Designing the Composition of Cement Stabilized Rammed Earth Using Artificial Neural Networks
Publication -
The Influence of Input Data Standardization Method on Prediction Accuracy of Artificial Neural Networks
Publication -
Aerodynamic excitations generated in turbine shroud clearance determined bymeans of neural networks
PublicationSiły aerodynamiczne generowane w uszczelnieniach turbinowych z reguły opisywane są modelem liniowym. Przy dużych drganiach wirnika sposób ten daje niezbyt dokładne wyniki. Zaproponowano wykorzystanie sieci neuronowych do określania sił ciśnieniowych powstających w uszczelnieniu. Wyniki porównano z badaniami eksperymentalnymi.
-
Design of Optical Wireless Networks with Fair Traffic Flows
Publication -
Design of Weather Disruption-Tolerant Wireless Mesh Networks
PublicationZ uwagi na wysoki koszt realizacji sieci teleinformatycznych wykorzystujących przewodową transmisję światłowodową, bezprzewodowe sieci kratowe (WMN) oferujące transmisję rzędu 1-10 Gb/s (przy wykorzystaniu pasma millimeter-wave - 71-86 GHz), wydają się być obiecującą alternatywą dla przewodowych sieci MAN. Jednakże z uwagi na właściwości transmisji bezprzewodowej w oparciu o łącza wysokiej częstotliwości, łącza te są bardzo wrażliwe...
-
Compact Dual-Polarized Corrugated Horn Antenna for Satellite Communications
PublicationIn this paper, a structure and design procedure of a novel compact dual-polarized corrugated horn antenna with high gain and a stable phase center for satellite communication is presented. The antenna incorporates an Ortho-Mode Transducer (OMT), a mode converter, and a corrugated structure. The compact OMT section is designed to be fed by standard WR-75 waveguides. The proposed compact design utilizes only ten corrugated slots...
-
Two- and three-dimensional elastic networks with rigid junctions: modeling within the theory of micropolar shells and solids
PublicationFor two- and three-dimensional elastic structures made of families of flexible elastic fibers undergoing finite deformations, we propose homogenized models within the micropolar elasticity. Here we restrict ourselves to networks with rigid connections between fibers. In other words, we assume that the fibers keep their orthogonality during deformation. Starting from a fiber as the basic structured element modeled by the Cosserat...
-
Extraction of antenna pattern from near field antenna measurements distorted by undesired emission
PublicationIn this paper authors present experimental correction of antenna pattern obtained from near field measurements when they are distorted by determined electromagnetic emission. Such situation may be met e.g. when feeding or supply subsystem interacts with antenna radiation pattern due to self-emission. Presented results of experiments show effectiveness of extraction of antenna pattern utilizing near field antenna measurements.
-
Statistical analysis and robust design of circularly polarized antennas using sequential approximate optimization
PublicationIn the paper, reliable yield estimation and tolerance-aware design optimization of circular polarization (CP) antennas is discussed. We exploit auxiliary kriging interpolation models established in the vicinity of the nominal design in order to speed up the process of statistical analysis of the antenna structure at hand. Sequential approximate optimization is then applied to carry out robust design of the antenna, here, oriented...
-
THE ROLE OF INFERENCE IN MOBILE MEDICAL APPLICATION DESIGN
PublicationIn the early 21st century, artificial intelligence began to be used to process medical information. However, before this happened, predictive models used in healthcare could only consider a limited number of variables, and only in properly structured and organised medical data. Today, advanced tools based on machine learning techniques - which, using artificial neural networks, can explore extremely complex relationships - and...