Filtry
wszystkich: 1356
-
Katalog
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: FASTER REGION BASED CONVOLUTION NEURAL NETWORK
-
Design of a complex multiplier based on the convolution with the use of the polynomial residue number system
Publikacjazaproponowano realizację mnożnika zespolonego opartego na algorytmie dekompozycyjnym skavantzosa i stouraitisa. mnożenie zespolone jest wykonywane jako splot 8-punktowy. przedstawiono przykład obliczeniowy i architekturę mnożnika dla małych liczb.
-
A compact smart sensor based on a neural classifier for objects modeled by Beaunier's model
PublikacjaA new solution of a smart microcontroller sensor based on a simple direct sensor-microcontroller interface for technical objects modeled by two-terminal networks and by the Beaunier’s model of anticorrosion coating is proposed. The tested object is stimulated by a square pulse and its time voltage response is sampled four times by the internal ADC of microcontroller. A neural classifier based on measurement data classifies the...
-
PROGRAMMABLE YANG - BASED INTERFACE IN CONTROL OF OPTICAL TRANSPORT NETWORK
PublikacjaSince over a decade we observe intensive effort of research institutions and industrial consortia on extending flexibility and automation of the transport network control also known under the term network programmability. Key aspect of each programming interface is ability to evolve but also sensitivity to future modifications. As indicated in the past work in the specific context of optical transport networks an important criterion...
-
Neural network modelling of the influence of channelopathies on reflex visual attention
Publikacja -
Energy-Efficient Neural Network Inference with Microcavity Exciton Polaritons
Publikacja -
Neural network approach to 2D Kalman filtering in image processing
Publikacja -
Application of a fuzzy neural network for river water quality prediction
PublikacjaMonitoring i modelowanie zmian w jakości wód powierzchniowych stanowią jeden z kluczowych elementów monitoringu i zarządzania ochroną środowiska na skalę globalną. Kontrolowanie tak złożonych i nieliniowych w swojej charakterystyce obiektów, jakimi są rzeki, jest trudnym zadaniem. Zazwyczaj do tego celu wykorzystuje się modele matematyczne, jednak czasem wymagają one bardzo dużej ilości danych, lub czas oczekiwania na odpowiedź...
-
The fuzzy neural network: application for trends in river pollution prediction
PublikacjaPraca przedstawia zastosowanie rozmytych sieci neuronowych do przygotowywania prognoz zmian w stężeniu zanieczyszczeń w rzekach. Opisane są pokrótce inne narzędzia stosowane w tym celu.
-
A new analyzer based on pellistor sensor with neural network data postprocessing for measurement of hydrocarbons in lower explosive limit range
PublikacjaW pracy przedstawiono rezultaty pierwszego etapu badań nad nowym typem analizatora do oznaczania stężenia wodoru i lotnych węglowodorów w zakresie dolnej granicy wybuchowości. Analizator ten zbudowano w oparciu o pojedynczy czujnik pelistorowy z układem przetwarzania danych wykorzystującym sztuczną sieć neuronową.
-
Expedited Trust-Region-Based Design Closure of Antennas by Variable-Resolution EM Simulations
PublikacjaThe observed growth in the complexity of modern antenna topologies fostered a widespread employment of numerical optimization methods as the primary tools for final adjustment of the system parameters. This is mainly caused by insufficiency of traditional design closure approaches, largely based on parameter sweeping. Reliable evaluation of complex antenna structures requires full-wave electromagnetic (EM) analysis. Yet, EM-driven...
-
Generalized regression neural network and fitness dependent optimization: Application to energy harvesting of centralized TEG systems
PublikacjaThe thermoelectric generator (TEG) system has attracted extensive attention because of its applications in centralized solar heat utilization and recoverable heat energy. The operating efficiency of the TEG system is highly affected by operating conditions. In a series-parallel structure, due to diverse temperature differences, the TEG modules show non-linear performance. Due to the non-uniform temperature distribution (NUTD) condition,...
-
A method of the UMTS-FDD network design based on universal load characteristics
PublikacjaIn the paper an original method of the UMTS radio network design was presented. The method is based on simple way of capacity-coverage trade-off estimation for WCDMA/FDD radio interface. This trade-off is estimated by using universal load characteristics and normalized coverage characteristics. The characteristics are useful for any propagation environment as well as for any service performance requirements. The practical applications...
-
Analysis of the impact of socio-economic development on road safety based on the example of Baltic Sea Region countries
PublikacjaBaltic Sea Region (BSR) is a specific region of Europe, bringing together countries with different levels of socio-economic development. The main common point is territorial access to the Baltic Sea and the importance of maritime transport in the transportation of goods. The region consists of 9 countries, including Germany, Poland, Lithuania, Latvia, Estonia, Finland, Sweden, Denmark and Russia (more specifically, Kaliningrad...
-
Energy Management for PV Powered Hybrid Storage System in Electric Vehicles Using Artificial Neural Network and Aquila Optimizer Algorithm
PublikacjaIn an electric vehicle (EV), using more than one energy source often provides a safe ride without concerns about range. EVs are powered by photovoltaic (PV), battery, and ultracapacitor (UC) systems. The overall results of this arrangement are an increase in travel distance; a reduction in battery size; improved reaction, especially under overload; and an extension of battery life. Improved results allow the energy to be used efficiently,...
-
An application of the TCRBF neural network in multi-node fault diagnosis method
PublikacjaPrzedstawiono nową metodę samo-testowania części analogowej w systemach elektronicznych sterowanych mikrokontrolerami. Układ badany pobudzany jest przebiegiem sinusoidalnym przez generator zamontowany w systemie, a jego odpowiedź jest próbkowana w wybranych węzłach przez wewnętrzny przetwornik A/C mikrokontrolera. Detekcja i lokalizacja uszkodzenia jest dokontwana przez sieć neuronową typu TCRBF. Procedurę diagnostyczną zaimplementowano...
-
Diagnostic potential for a serum miRNA neural network for detection of ovarian cancer
Publikacja -
Ultracapacitor modeling and control with discrete fractional order artificial neural network
Publikacja -
Artificial neural network controller for underwater ship hull operation robot.
PublikacjaZaproponowano model matematyczny pojazdu podwodnego, który w uproszczonej wersji spełnia warunki dynamiki odpowiadające głowicy roboczej podwodnego robota. Uwzględniono niektóre czynniki oddziałujące na ruch podwodnej głowicy roboczej, jak np. gęstość wody oraz siły odśrodkowe i wypornościowe. Przedstawiono układ sterowania, w którym zastosowano regulator oparty na bazie sieci neuronowych, za pomocą którego można sterować...
-
Neural Network Application for Recognition of Geometry Degradation of Power Cycle Components
PublikacjaPrzedyskutowano problem rozpoznawania degradacji geometrycznej. Skuteczne zastosowanie wybranego typu sieci neuronowej (SSN) jest prezentowane w referacie. SSN wykrywająca typy degradacji geometrycznej wykazała wysoką jakość. Pokazano pewną możliwość ekstrapolacji takich SSN. Pokazano możliwość wykrywania typów degradacji geometrycznej nawet w przypadku pozyskiwania niepełnych danych pomiarowych.
-
Hybrid Technique Combining the FDTD Method and Its Convolution Formulation Based on the Discrete Green's Function
PublikacjaIn this letter, a technique combining the finite-difference time-domain (FDTD) method and its formulation based on the discrete Green's function (DGF) is presented. The hybrid method is applicable to inhomogeneous dielectric structures that are mutually coupled with wire antennas. The method employs the surface equivalence theorem in the discrete domain to separate the problem into a dielectric domain simulated using the FDTD method...
-
A Novel Trust-Region-Based Algorithm with Flexible Jacobian Updates for Expedited Optimization of High-Frequency Structures
PublikacjaSimulation-driven design closure is mandatory in the design of contemporary high-frequency components. It aims at improving the selected performance figures through adjustment of the structure’s geometry (and/or material) parameters. The computational cost of this process when employing numerical optimization is often prohibitively high, which is a strong motivation for the development of more efficient methods. This is especially...
-
Surface effects of network materials based on strain gradient homogenized media
PublikacjaThe 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...
-
Using Deep Neural Network Methods for Forecasting Energy Productivity Based on Comparison of Simulation and DNN Results for Central Poland—Swietokrzyskie Voivodeship
Publikacja -
Using Deep Neural Network Methods for Forecasting Energy Productivity Based on Comparison of Simulation and DNN Results for Central Poland – Swietokrzyskie Voivodeship
Publikacja -
Leveraging Training Strategies of Artificial Neural Network for Classification of Multiday Electromyography Signals
Publikacja -
Application of fuzzy neural network for supporting measurements and control in a wastewater treatment plant
PublikacjaOczyszczanie ścieków jest jednym z ważniejszych aspektów ochrony środowiska. Nowoczesne systemy kontroli w oczyszczalniach ścieków pozwalają na poprawę jakości procesu oczyszczania redukując jednocześnie koszty. Systemy kontroli i optymalizacji jakie odkilku lat opracowuje się dla oczyszczalni ścieków, bazują zazwyczaj na skomplikowanych modelach matematycznych. Kluczowym problemem w zastosowaniu tych systemów jest duża liczba...
-
Mathematical modeling and prediction of pit to crack transition under cyclic thermal load using artificial neural network
PublikacjaThe formation of pitting is a major problem in most metals, which is caused by extremely localized corrosion that creates small holes in metal and subsequently, it changes into cracks under mechanical load, thermo-mechanical stress, and corrosion process factors. This research aims to study pit to crack transition phenomenon of steel boiler heat tubes under cyclic thermal load, and mathematical modeling...
-
Intracranial hemorrhage detection in 3D computed tomography images using a bi-directional long short-term memory network-based modified genetic algorithm
PublikacjaIntroduction: Intracranial hemorrhage detection in 3D Computed Tomography (CT) brain images has gained more attention in the research community. The major issue to deal with the 3D CT brain images is scarce and hard to obtain the labelled data with better recognition results. Methods: To overcome the aforementioned problem, a new model has been implemented in this research manuscript. After acquiring the images from the Radiological...
-
Heavy Duty Vehicle Fuel Consumption Modelling Based on Exploitation Data by Using Artificial Neural Networks
PublikacjaOne of the ways to improve the fuel economy of heavy duty trucks is to operate the combustion engine in its most efficient operating points. To do that, a mathematical model of the engine is required, which shows the relations between engine speed, torque and fuel consumption in transient states. In this paper, easy accessible exploitation data collected via CAN bus of the heavy duty truck were used to obtain a model of a diesel...
-
Classification of objects in the LIDAR point clouds using Deep Neural Networks based on the PointNet model
PublikacjaThis work attempts to meet the challenges associated with the classification of LIDAR point clouds by means of deep learning. In addition to achieving high accuracy, the designed system should allow the classification of point clouds covering an area of several dozen square kilometers within a reasonable time interval. Therefore, it must be characterized by fast processing and efficient use of memory. Thus, the most popular approaches...
-
Towards Designing an Innovative Industrial Fan: Developing Regression and Neural Models Based on Remote Mass Measurements
PublikacjaThis article presents the process of the construction and testing a remote, fully autonomous system for measuring the operational parameters of fans. The measurement results obtained made it possible to create and verify mathematical models using linear regression and neural networks. The process was implemented as part of the first stage of an innovative project. The article presents detailed steps of constructing a system to...
-
The influence of image masks definition onsegmentation results of histopathological imagesusing convolutional neural network
PublikacjaAbstract—In the era of collecting large amounts of tissue materials, assisting the work of histopathologists with various electronic and information IT tools is an undeniable fact. The traditional interaction between a human pathologist and the glass slide is changing to interaction between an AI pathologist with a whole slide images. One of the important tasks is the segmentation of objects (e.g. cells) in such images. In this...
-
Taking decisions in the diagnostic intelligent systems on the basis information from an artificial neural network
Publikacja -
An application of neural network for Structural Health Monitoring of an adaptive wing with an array of FBG sensors
PublikacjaW pracy przedstwiono możliwości zastoswania sieci czujników FBG i sztucznych sieci neuronowych do detekcji uszkodzeń w poszyciu adaptacyjnego skrzydła.
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublikacjaThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
Comparison of tuning procedures based on evolutionary algorithm for multi-region fuzzy-logic PID controller for non-linear plant
PublikacjaThe paper presents a comparison of tuning procedures for a multi-region fuzzy-logic controller used for nonlinear process control. This controller is composed of local PID controllers and fuzzy-logic mechanism that aggregates local control signals. Three off-line tuning procedures are presented. The first one focuses on separate tuning of local PID controllers gains in the case when the parameters of membership functions of fuzzy-logic...
-
Modified Inductive Multi-Coil Wireless Power Transfer Approach Based On Z-Source Network
PublikacjaThis article presents a non-conventional approach to a multi-coil wireless power transfer system based on a Z-source network. The novelty of the approach lies in the use of a Z-source as a voltage source for energy transmission through the wireless power transfer coils. The main advantage is in a reduced number of semiconductors. This paper provides the design approach, simulation and experimental study. Feasibility and possible...
-
Wind-wave variability in a shallow tidal sea—Spectral modelling combined with neural network methods
Publikacja -
Neural network simulator's application to reference performance determination of turbine blading in the heat-flow diagnostics.
PublikacjaIn the paper, the possibility of application of artificial neural networks to perform the fluid flow calculations through both damaged and undamaged turbine blading was investigated. Preliminary results are presented and show the potentiality of further development of the method for the purpose of heat-flow diagnostics.
-
Performance and Energy Aware Training of a Deep Neural Network in a Multi-GPU Environment with Power Capping
PublikacjaIn this paper we demonstrate that it is possible to obtain considerable improvement of performance and energy aware metrics for training of deep neural networks using a modern parallel multi-GPU system, by enforcing selected, non-default power caps on the GPUs. We measure the power and energy consumption of the whole node using a professional, certified hardware power meter. For a high performance workstation with 8 GPUs, we were...
-
Selective adsorption of BTEX on calixarene-based molecular coordination network determined by 13C NMR spectroscopy
PublikacjaBenzene, toluene, ethylbenzene, and xylenes (BTEX), a class of volatile organic compounds, are harmful pollutants but also very important precursors in organic industrial chemistry. Among different approaches used for the BTEX treatment, the adsorption technology has been recognized as an efficient approach because it allows to recover and reuse both adsorbent and adsorbate. However, the selective adsorption of the components is...
-
QUASI-DISTRIBUTED NETWORK OF LOW-COHERENCE FIBER-OPTIC FABRY-PÉROT SENSORS WITH CAVITY LENGTH-BASED ADDRESSING
PublikacjaDistributed measurement often relies on sensor networks. In this paper, we present the construction of low coherent fiber-optic Fabry-Pérot sensors connected into a quasi-distributed network. We discuss the mechanism of spectrum modulation in this type of sensor and the constraints of assembly of such sensors in the network. Particular attention was paid to separate the signals from individual sensors, which can be achieved by...
-
Control of the induction motor in the field weakening region based on the multiscalar model.
PublikacjaNajwiększą korzyścią płynąca z zastosowania w układzie regulacji modelu multiskalarnego jest pełne odsprzężenie toru sterowania prędkością i toru sterowania strumieniem. Wykorzystanie zależności występujących w modelu multiskalarnym pozwala na określenie maksymalnego momentu wyjściowego w układzie napędowym dla zakresu osłabiania pola. Zaproponowany został bezczujnikowy układ regulacji w oparciu o obserwator prędkości.
-
Selecting wells for an optimal design of groundwater monitoring network based on monitoring priority map: A Kish Island case study
PublikacjaThis paper presents a novel approach, i.e. a combination of gamma test and monitoring priority map, for optimal design of groundwater monitoring network (GMN) by considering the cumulative effects of industries, human activities, and natural factors on the groundwater quality. The proposed method was successfully applied to design an optimal network for groundwater salinity monitoring on Kish Island, Persian Gulf. The priority...
-
Novel Adaptive Method for Data Streams Allocation Based on the Estimate of Radio Channel Parameters in Heterogeneous WBAN Network
PublikacjaThe new adaptive method for data streams allocation in heterogeneous Wireless Body Area Networks and meas-urement equipment is presented. The results obtained using the developed method compared with the selected algorithms likely to be used in those networks. The pro-posed adaptive data streams allocation method based on radio channel parameters makes it even twice as efficient to use in terms of resources usage in a WBAN heterogeneous...
-
Designing of an effective structure of system for the maintenance of a technical object with the using information from an artificial neural network
Publikacja -
<title>Recurrent neural network application to image filtering: 2-D Kalman filtering approach</title>
Publikacja -
Neural networks based NARX models in nonlinear adaptive control
Publikacja -
The Optical Transport Network Control Based on SDN Architecture
PublikacjaThe aim of this publication is to present research results on the usability of the Software-Defined Networking concept to control transport networks. For this purpose, an easy-to-use connection scheduler was developed capable of controlling connections in optical transport networks. The authors would like to present this solution and details of constructed SDN architecture implemented for modern optical transport solutions based...
-
Burst loss probability for the combination of extended offset time based service differentiation scheme and PPS in optical burst switching network
PublikacjaIn the paper analytical model for calculating burst loss probabilities for the combination of two service differentiation schemes for OBS network namely: extended offset time based scheme and PPS (Preemption Priority Schemes) is revised. Moreover authors introduce analytical model for calculating burst loss probabilities for an optical path when OBS network employs both service differentiation schemes and JET signaling. The comparison...