Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "neural model" wg kryterium: Temat


Tytuł:
Obtaining fluid flow pattern for turbine stage with neural model
Autorzy:
Butterweck, Anna
Powiązania:
https://bibliotekanauki.pl/articles/2073533.pdf
Data publikacji:
2019
Wydawca:
Politechnika Gdańska. Wydział Inżynierii Mechanicznej i Okrętownictwa
Tematy:
turbine
diagnostics
neural model
pattern
fluid flow
Opis:
In the paper possibility of applying neural model to obtaining patterns of proper operation for fluid flow in turbine stagefor fluid-flow diagnostics is discussed. Main differences between Computational Fluid Dynamics (CFD) solvers and neural model is given, also limitations and advantages of both are considered. Time of calculations of both methods was given, also possibilities of shortening that time with preserving the accuracy of the calculations are discussed. Gathering training data set and neural networks architecture is presented in detail. Range of work of neural model was given. Required input data for neural model and reason why it is different than in computational fluid dynamics solvers isexplained. Results obtained with neural model in 21 tests are discussed. Arithmetic mean and median of relative errors of recreating distribution of pressure and temperature are shown. Achieved results are analysed.
Źródło:
Journal of Polish CIMEEAC; 2019, 14, 1; 45--50
1231-3998
Pojawia się w:
Journal of Polish CIMEEAC
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
To recognize the manuscript texts of Arabic letters in ancient Uzbek script
Autorzy:
Nurmamatovna, Iskandarova Sayyora
Powiązania:
https://bibliotekanauki.pl/articles/1076553.pdf
Data publikacji:
2019
Wydawca:
Przedsiębiorstwo Wydawnictw Naukowych Darwin / Scientific Publishing House DARWIN
Tematy:
Arabic text
Hemming
biologic neural
method
neural model
neural scheme
recognize
software product
Opis:
This article describes the Hemming method of the neural model for automatic identification of Arabic texts on the computer. The main problem of recognizing manuscript mantles in Arabic is that of the elements that they have created. Usually, the text is divided into rows, and then separated by separate words. The development of the Arabic language signifies a great deal of controversy over Arabic language. Hemming is based on the neuronal model and the description of the software product.
Źródło:
World Scientific News; 2019, 115; 160-173
2392-2192
Pojawia się w:
World Scientific News
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Neuronowy model do identyfikacji makrouszkodzeń ziarniaków
Neural model for identification of damages of corn kernels
Autorzy:
Nowakowski, K.
Boniecki, P.
Powiązania:
https://bibliotekanauki.pl/articles/336815.pdf
Data publikacji:
2008
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Maszyn Rolniczych
Tematy:
model neuronowy
makrouszkodzenie
ziarniak
identyfikacja
neural model
damage
corn kernel
identification
Opis:
Realizacja projektu obejmowała zbudowanie i wytrenowanie neuronowego modelu do identyfikacji makrouszkodzeń ziarniaków. Rozpoznawania uszkodzeń dokonywano na podstawie cyfrowych fotografii skonwertowanych przez wytworzony system informatyczny do postaci zbiorów uczących dedykowanych dla sztucznej sieci neuronowej. Do uczenia sieci wybrano zestaw reprezentatywnych cech. W zbiorze tym zawarto informacje o barwie (zakodowanej do postaci liczbowej), polu powierzchni, obwodzie i wybranych współczynnikach kształtu. Pojedynczy przypadek uczący zawierał 1031 zmiennych, z czego 1024 to zmienne zawierające informacje o barwie. Identyfikacji makrouszkodzeń dokonano na ziarniakach kukurydzy odmiany Clarica FAO 280.
The realization of project enclosed construction and training neuronal model to identification of damages of corn kernels. Recognizing the damages was made on basis of digital photos converted by produced computer system to learning files dedicated for artificial neural network. The network was learned on chosen representative tags. The taught model marks abilities of identification approximate quality to human. Neural model can in real time identify larger number of kernels than man. The number of kernels is only limited by method of images acquisition and the computational power of applied equipment to implementation of model. Big advantage is also the lack of natural man limitations which for example are: fatigue and subjective opinion.
Źródło:
Journal of Research and Applications in Agricultural Engineering; 2008, 53, 2; 79-81
1642-686X
2719-423X
Pojawia się w:
Journal of Research and Applications in Agricultural Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Self-adaptive whale optimization for the design and modelling of boiler plant
Autorzy:
Savargave, S. B.
Deshpande, A. M.
Powiązania:
https://bibliotekanauki.pl/articles/1839098.pdf
Data publikacji:
2018
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
boiler
whale optimization
neural model
temperature outlet
feed water flow
Opis:
Recently, boiler plants are have been the subject of intensive investigations in the context of energy-saving technologies and management for power saving and reduction of emissions. Modern boiler design offers several benefits with this respect. In the past, improper design of boilers has been the cause of explosions which led to the loss of life and property. Modern designs attempt to avoid such mishaps. This paper presents a novel Self-Adaptive Whale Optimization Algorithm (SAWOA) for improving the learning characteristic of the neural network, the major intention being to model the characteristics of the boiler plant and so to effectively predict the boiler behaviour. The performance analysis of the introduced model has been carried out using the three test cases with consideration of several parameters. In the experimental analysis, the introduced technique is compared with the existing ones, based on such approaches as Neural Model (NM), Firefly (FF-NM), Adaptive Firefly NM (AFF-NM), and Whale Optimization Algorithm-NM (WOANM). In this comparison, the error, i.e. the difference between the actual and the predicted value, was used, and the results revealed that the error is lower for the introduced technique under different experimental scenarios. The experimental results demonstrate that the performance level of SAWOA is by 18% better than those of NM, FF-NM, and AFF-NM, and by 3.74% better than that of WOA-NM. This confirms the quality of performance of the proposed approach regarding boiler plants.
Źródło:
Control and Cybernetics; 2018, 47, 4; 329-356
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The neural analysis of quarters healthiness of high yield cows in selected cowshed
Neuronowa analiza zdrowotności wymion krów wysokowydajnych w wybranej oborze mlecznej
Autorzy:
Jędruś, A.
Boniecki, P.
Powiązania:
https://bibliotekanauki.pl/articles/337371.pdf
Data publikacji:
2013
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Maszyn Rolniczych
Tematy:
neural model
cows
somatic cell count
model neuronowy
krowy
liczba komórek somatycznych
Opis:
Commonly recognized predictive abilities represented by selected ANN (Artificial Neural Networks) topologies are widely used in practice. They often support the decision-making processes that occur in agri-alimentary processing, such as milk production. The aim of the study was to use ANN as a predictive tool in the estimation process of the influence of selected zootechnical characteristics of cows on the milk quality, which is determined by the standards defining the requirements compliance concerning the level of somatic cell counts in the obtained milk. The work resulted in creation of the optimum predictive model which is a neural topology of the MLP-6:17:1 (MultiLayer Perceptron). The performed analysis of the generated neural model’s sensitivity to the individual input variables showed the impact of some of the zootechnical characteristics on somatic cell counts in the obtained milk.
Uznane zdolności predykcyjne, jakie reprezentują wybrane topologie SNN (Sztuczne Sieci Neuronowe), wykorzystywane są powszechnie również w szeroko rozumianej praktyce, np. wspomagają procesy decyzyjne zachodzące w przetwórstwie rolno-spożywczym, np. w branży mleczarskiej. Celem pracy było wykorzystanie SNN jako narzędzia predykcyjnego w procesie oceny wpływu wybranych cech zootechnicznych krów na jakość mleka krów, która określana jest przez normy definiujące spełnienie wymogów odnośnie poziomu zawartości komórek somatycznych w pozyskiwanym mleku. W pracy wytworzono optymalny model predykcyjny będący neuronową topologią typu MLP: 6-17-1 (MultiLayer Perceptron). Przeprowadzona analiza wrażliwości wygenerowanego modelu neuronowego na poszczególne zmienne wejściowe wykazała istotny wpływ wybranych cech zootechnicznych na liczbę komórek somatycznych w pozyskanym mleku.
Źródło:
Journal of Research and Applications in Agricultural Engineering; 2013, 58, 2; 55-57
1642-686X
2719-423X
Pojawia się w:
Journal of Research and Applications in Agricultural Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Feedforward neural networks and the forecasting of multi-sectional demand for telecom services: a comparative study of effectiveness for hourly data
Jednokierunkowe sieci neuronowe w prognozowaniu wieloprzekrojowego popytu na usługi telefoniczne – porównawcze badania efektywności dla danych godzinowych
Autorzy:
Kaczmarczyk, P.
Powiązania:
https://bibliotekanauki.pl/articles/2117264.pdf
Data publikacji:
2020
Wydawca:
Szkoła Główna Gospodarstwa Wiejskiego w Warszawie. Wydawnictwo Szkoły Głównej Gospodarstwa Wiejskiego w Warszawie
Tematy:
Prediction System
feedforward neural network
regressive-neural model
forecasting
jednokierunkowa sieć neuronowa
model regresyjno-neuronowy
prognozowanie
system prognostyczny
Opis:
The presented research focuses on the construction of a model to effectively forecast demand for connection services – it is thus relevant to the Prediction System (PS) of telecom operators. The article contains results of comparative studies regarding the effectiveness of neural network models and regressive-neural (integrated) models, in terms of their short-term forecasting abilities for multi-sectional demand of telecom services. The feedforward neural network was used as the neural network model. A regressive-neural model was constructed by fusing the dichotomous linear regression of multi-sectional demand and the feedforward neural network that was used to model the residuals of the regression model (i.e. the residual variability). The response variable was the hourly counted seconds of outgoing calls within the framework of the selected operator network. The calls were analysed within: type of 24 hours (e.g. weekday/weekend), connection categories, and subscriber groups. For both compared models 35 explanatory variables were specified and used in the estimation process. The results show that the regressive-neural model is characterised by higher approximation and predictive capabilities than the non-integrated neural model.
Zaprezentowane wyniki badań są związane z systemem prognostycznym przeznaczonym dla operatorów telekomunikacyjnych, ponieważ są skoncentrowane na sposobie konstrukcji modelu do efektywnego prognozowania popytu na usługi połączeniowe. Artykuł zawiera wyniki porównawczych badań efektywności modelu sieci neuronowej i modelu regresyjno-neuronowego (zintegrowanego) w zakresie krótkookresowego prognozowania zapotrzebowania na usługi telefoniczne. Jako model sieci neuronowej zastosowany został model sieci jednokierunkowej. Model regresyjno-neuronowy został zbudowany na podstawie połączenia dychotomicznej regresji liniowej wieloprzekrojowego popytu i jednokierunkowej sieci neuronowej, która służyła do modelowania reszt modelu regresji (tj. pozostałej zmienności). Zmienną objaśnianą były sumowane co godzinę liczby sekund rozmów wychodzących z sieci wybranego operatora. Połączenia telefoniczne były analizowane pod względem: typów doby, kategorii połączeń i grup abonentów. Wyszczególniono 35 zmiennych objaśniających, które wykorzystano w procesie estymacji obu porównywanych modeli. Stwierdzono, że model regresyjno-neuronowy charakteryzuje się większymi możliwościami aproksymacyjnymi i predykcyjnymi niż niezintegrowany model neuronowy.
Źródło:
Acta Scientiarum Polonorum. Oeconomia; 2020, 19, 3; 13-25
1644-0757
Pojawia się w:
Acta Scientiarum Polonorum. Oeconomia
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Prognozowanie plonów wybranych płodów rolnych z wykorzystaniem modeli neuronowych w postaci szeregów czasowych
Expectation crops of chosen agricultural fetuses with the help of neural model by time series
Autorzy:
Boniecki, P.
Mueller, W.
Powiązania:
https://bibliotekanauki.pl/articles/337153.pdf
Data publikacji:
2006
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Maszyn Rolniczych
Tematy:
sieć neuronowa
prognozowanie
płody rolne
plon
model neuronowy
szereg czasowy
neural network
prognose
neural model
time series
agricultural fetuses
yield
Opis:
Jednym z ważnych etapów badania oraz analizy systemów empirycznych jest proces prognozowania, mający praktyczne zastosowanie w szerokim zakresie działalności ludzkiej. W przypadku przewidywania wielkości płodów rolnych mamy do czynienia z szeregiem złożonych bodźców, które w efekcie przekładają się na wynik końcowy, jakim jest plon. Jakość tych prognoz ma ogromne znaczenie dla kolejnych etapów w łańcuchu produkcyjno-dystrybucyjnym płodów rolnych. Sieci neuronowe w postaci szeregów czasowych są wysublimowaną techniką modelowania, zdolną odwzorować bardzo złożone funkcje. Celem analizy szeregów czasowych jest ustalenie prognozy przyszłych wartości pewnej zmiennej, której wartości zmieniają się w czasie. Najczęściej dąży się do obliczenia prognozy korzystając z wcześniejszych wartości tej samej zmiennej, której wartość ma być przewidywana. Zbiór uczący, wykorzystywany przy neuronowej analizie szeregów czasowych, budowany jest zwykle w oparciu o pojedynczą zmienną, której typ określony jest jako "Wejściowo-Wyjściowy". Oznacza to, że jest ona wykorzystywana zarówno jako wejście sieci neuronowej, jak i jako jej wyjście.
Prediction becomes a very important stage in many activities. In case of expectation crops of chosen agricultural foetuses we deal with a number of stimuli which consequently transform into the end effect. It is clear that the quality of those predictions has a great influence on subsequent stages in the production and distribution chain of agricultural foetuses. Neural networks by time series are a sophisticated technique of modeling capable of reflecting very complex functions. In time series problems, the objective is to predict ahead the value of a variable which varies in time, using previous values of that and/or other variables. The time series training data set therefore typically has a single variable, and this has type input/output (i.e., it is used both for network input and network output).
Źródło:
Journal of Research and Applications in Agricultural Engineering; 2006, 51, 4; 40-43
1642-686X
2719-423X
Pojawia się w:
Journal of Research and Applications in Agricultural Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Design of iterative learning control for simple robot based on neural network robot model
Synteza iteracyjnie uczqcego siq sterowania prostego robota na podstawie neuronowego modelu robota
Autorzy:
Lesewed, A. A.
Kurek, J.
Powiązania:
https://bibliotekanauki.pl/articles/154502.pdf
Data publikacji:
2009
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
model neuronowy robota przemyslowego
iteracyjnie uczące się sterowanie
neural model of industrial robot
iterative learning control
Opis:
Design of the iterative learning control (TLC) for robot manipulator with 2 degree of freedom based on model of the robot approximated by neural network is presented. The robot model has form of the Lagrange-Euler equation and neural network was trained to estimate the model parameters. Then, the estimated model was used for synthesis of ILC.
W pracy przedstawiono syntezy iteracyjnie uczącego się sterowania dla robota o 2 stopniach swobody na podstawie modelu aproksymowanego przy pomocy sieci neuronowych. Model robota ma formę równań Lagrange'a-Eulera, którego nieliniowe funkcje zostały wyznaczone przez odpowiednio wytrenowaną sieć neuronową. Aproksymowany model został następnie wykorzystany do syntezy regulatora.
Źródło:
Pomiary Automatyka Kontrola; 2009, R. 55, nr 3, 3; 205-208
0032-4140
Pojawia się w:
Pomiary Automatyka Kontrola
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Quantum inspiration to build a neural model based on the Day-Ahead Market of the Polish Power Exchange
Autorzy:
Ruciński, Dariusz
Powiązania:
https://bibliotekanauki.pl/articles/2052430.pdf
Data publikacji:
2021
Wydawca:
Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach
Tematy:
Neural Modeling
day-ahead market
Polish power exchange
mean square error
determination index
quantum inspired neural model
Opis:
The article is an attempt of the methodological approach to the proposed quantum-inspired method of neural modeling of prices quoted on the Day-Ahead Market operating at TGE S.A. In the proposed quantum-inspired neural model it was assumed, inter alia, that it is composed of 12 parallel Perceptron ANNs with one hidden layer. Moreover, it was assumed that weights and biases as processing elements are described by density matrices, and the values flowing through the Artificial Neural Network of Signals are represented by qubits. Calculations checking the correctness of the adopted method and model were carried out with the use of linear algebra and vector-matrix calculus in MATLAB and Simulink environments. The obtained research results were compared to the results obtained from the neural model with the use of a comparative model.
Źródło:
Studia Informatica : systems and information technology; 2021, 1-2(25); 23-37
1731-2264
Pojawia się w:
Studia Informatica : systems and information technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Model neuronowy zmian temperatury podczas konwekcyjnego suszenia zrębków wierzby energetycznej
Neural model of temperature changes during convection drying of energy willow chips
Autorzy:
Łapczyńska-Kordon, B.
Francik, S.
Ślipek, Z.
Powiązania:
https://bibliotekanauki.pl/articles/289751.pdf
Data publikacji:
2008
Wydawca:
Polskie Towarzystwo Inżynierii Rolniczej
Tematy:
wierzba
zrębki
model neuronowy
zmiana temperatury
suszenie konwekcyjne
willow chips
neural model
temperature change
convection drying
Opis:
W pracy podjęto próbę zastosowania sztucznych sieci neuronowych do modelowania rozkładu temperatury w zrębkach suszonych konwekcyjnie. W modelu uwzględniono cztery zmienne wejściowe: temperaturę czynnika suszącego, początkową zawartość wody, wymiary zrębka, czas suszenia oraz jedna wyjściową - temperaturę materiału. Do budowy modelu posłużyły wyniki badań procesu konwekcyjnego suszenia zrębków wierzby, w trzech temperaturach: 50, 60 i 70°C, w suszarce z wymuszonym obiegiem powietrza. Podczas suszenia, w równych odstępach czasowych, określano zawartość wody i temperaturę materiału. Sformułowany model w oparciu o sztuczne sieci neuronowe został wybrany na podstawie najmniejszej wartości błędu średnio kwadratowego dla zbioru walidacyjnego. Następnie model ten poddano testowaniu i weryfikacji za pomocą wyników pomiarów wykonanych w takich samych warunkach jak opisane powyżej. Stwierdzono, że model poprawnie opisuje kinetykę zmian temperatury materiału w zależności od wybranych czterech czynników wejściowych.
The paper demonstrates an attempt to employ artificial neural networks to model temperature distribution in chips being dried in the convection process. Four input variables were taken into account in the model: drying medium temperature, initial water content, chip dimensions and drying time, and one output variable - material temperature. Examination results for willow chips convection drying process, carried out at three temperature values: 50, 60 and 70°C in a drier with forced air flow were used to build the model. During drying the researchers were determining water content and material temperature at equal time intervals. The model formulated using artificial neural networks was selected according to the lowest mean square error value for validation set. Then, this model was subject to testing and verification using results of measurements performed in the same conditions as those described above. It has been observed that the model correctly describes kinetics of changes in material temperature depending on the selected four input factors.
Źródło:
Inżynieria Rolnicza; 2008, R. 12, nr 11(109), 11(109); 149-155
1429-7264
Pojawia się w:
Inżynieria Rolnicza
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Model neuronowy zmian zawartości wody w zrębkach wierzby podczas konwekcyjnego suszenia
Neural model of changes in water content in willow chips during convection drying
Autorzy:
Łapczyńska-Kordon, B.
Francik, S.
Powiązania:
https://bibliotekanauki.pl/articles/289777.pdf
Data publikacji:
2008
Wydawca:
Polskie Towarzystwo Inżynierii Rolniczej
Tematy:
zrębki
wierzba
model neuronowy
zawartość wody
suszenie konwekcyjne
willow chips
neural model
water content
convection drying
Opis:
Celem pracy było opracowanie modelu zmian zawartości wody w zrębkach wierzby energetycznej w czasie, w postaci sztucznej sieci neuronowej. Model został opracowany w oparciu o wyniki badań procesu konwekcyjnego suszenia zrębków wierzby o długości 2 cm, ale różnej średnicy, w suszarce laboratoryjnej z wymuszonym przepływem powietrza. Materiał był suszony w temperaturach 40, 50, 60 i 70°C. Na podstawie otrzymanych wyników badań został sformułowany, za pomocą SSN, model zmian zawartości wody w zależności od sześciu zmiennych wejściowych: czasu suszenia, temperatury czynnika suszącego, długości i średnicy zrębków oraz początkowej zawartości wody i masy zrębków. Spośród opracowanych modeli wybrano model o architekturze MLP 6:6-15-14-1:1, ponieważ podczas weryfikacji empirycznej stwierdzono, że obliczony błąd średniokwadratowy dla tego modelu był najmniejszy.
The purpose of the work was to develop a model of changes in time of water content in energy willow chips using artificial neural networks (ANN). The model was developed on the grounds of examination results obtained for convection process applied for drying of 20mm-long willow chips with different diameters, carried out in a laboratory drier with forced air flow. The material was dried at the temperature of 40, 50, 60 and 70°C. Obtained examination results provided grounds to formulate, using the ANN, the model of changes in water content depending on six input variables: drying time, drying medium temperature, length and diameter of chips, and initial water content and weight of chips. The model with MLP architecture 6:6-15-14-1:1 was chosen from among all developed models because empirical verification proved that computed mean square error for that model was lowest.
Źródło:
Inżynieria Rolnicza; 2008, R. 12, nr 11(109), 11(109); 143-148
1429-7264
Pojawia się w:
Inżynieria Rolnicza
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Neural modeling of plant tissue cultures: a review
Autorzy:
Zielinska, S.
Kepczynska, E.
Powiązania:
https://bibliotekanauki.pl/articles/81293.pdf
Data publikacji:
2013
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
artificial neural network
biomass
plant tissue
neural model
tissue culture
in vitro condition
micropropagation
radial neural network
neural network
somatic embryo
Źródło:
BioTechnologia. Journal of Biotechnology Computational Biology and Bionanotechnology; 2013, 94, 3
0860-7796
Pojawia się w:
BioTechnologia. Journal of Biotechnology Computational Biology and Bionanotechnology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Black box dynamic modelling of proton exchange membrane fuel cells with artificial neural networks
Autorzy:
Kapica, J.
Powiązania:
https://bibliotekanauki.pl/articles/411175.pdf
Data publikacji:
2016
Wydawca:
Polska Akademia Nauk. Oddział w Lublinie PAN
Tematy:
PEM fuel cells
neural network model
dynamic behaviour
black box
Opis:
The fuel cells are energy sources which can play an important role in transition of the energy sector into broader use of renewable energy. Numerical modelling provides an easy way to investigate properties of the objects modelled. There are various ways to model dynamic behaviour of the PEM fuel cells including methods using artificial neural networks. There are no clear rules of how a neural network should be configured: how many neurons in the hidden layer and which training algorithm should be used. In a time series modelling task additional parameters including sampling frequency, learning data set duration and number of past data points used for training need to be determined. The paper presents results of research on the influence of various model parameters on the PEM fuel cell modelling accuracy.
Źródło:
ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes; 2016, 5, 4; 85-89
2084-5715
Pojawia się w:
ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Incidences of variables in labor absenteeism: an analysis of neural networks
Autorzy:
Pérez-Campdesuñer, Reyner
De Miguel-Guzmán, Margarita
García-Vidal, Gelmar
Sánchez-Rodríguez, Alexander
Martínez-Vivar, Rodobaldo
Powiązania:
https://bibliotekanauki.pl/articles/407357.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
labor absenteeism
neural networks model
human resource management
ANOVA analysis
Opis:
Labor absenteeism is a factor that affects the good performance of organizations in any part of the world, from the instability that is generated in the functioning of the system. This is evident in the effects on quality, productivity, reaction time, among other aspects. The direct causes by which it occurs are generally known and with greater reinforcement the diseases are located, without distinguishing possible classifications. However, behind these or other causes can be found other possible factors of incidence, such as age or sex. This research seeks to explore, through the application of neural networks, the possible relationship between different variables and their incidence in the levels of absenteeism. To this end, a neural networks model is constructed from the use of a population of more than 12,000 employees, representative of various classification categories. The study allowed the characterization of the influence of the different variables studied, supported in addition to the performance of an ANOVA analysis that allowed to corroborate and clarify the results of the neural network analysis.
Źródło:
Management and Production Engineering Review; 2020, 11, 1; 3--12
2080-8208
2082-1344
Pojawia się w:
Management and Production Engineering Review
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The Influence of the Artificial Neural Network type on the quality of learning on the Day-Ahead Market model at Polish Power Exchange joint-stock company
Autorzy:
Ruciński, Dariusz
Powiązania:
https://bibliotekanauki.pl/articles/1819257.pdf
Data publikacji:
2019
Wydawca:
Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach
Tematy:
Perceptron Artificial Neural Network
Radial Artificial Neural Network
Recursive Artificial Neural Network
neural model quality
Day-Ahead Market
Polish Power Exchange
Mean square error
determination index
Opis:
The work contains the results of the Day-Ahead Market modeling research at Polish Power Exchange taking into account the numerical data on the supplied and sold electricity in selected time intervals from the entire period of its operation (from July 2002 to June 2019). Market modeling was carried out based on three Artificial Neural Network models, ie: Perceptron Artificial Neural Network, Recursive Artificial Neural Network, and Radial Artificial Neural Network. The examined period of the Day-Ahead Market operation on the Polish Power Exchange was divided into sub-periods of various lengths, from one month, a quarter, a half a year to the entire period of the market's operation. As a result of neural modeling, 1,191 models of the Market system were obtained, which were assessed according to the criterion of the least error MSE and the determination index R2.
Źródło:
Studia Informatica : systems and information technology; 2019, 1-2(23); 77--93
1731-2264
Pojawia się w:
Studia Informatica : systems and information technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analiza jakościowa modeli neuronowych na przykładzie wytrzymałości kinetycznej granul
Qualitaty models analysis neural networks on the example of the pellet quality
Autorzy:
Rynkiewicz, M.
Powiązania:
https://bibliotekanauki.pl/articles/290587.pdf
Data publikacji:
2006
Wydawca:
Polskie Towarzystwo Inżynierii Rolniczej
Tematy:
wytrzymałość kinetyczna
sztuczna sieć neuronowa
pellets
kinetic strength
neural networks model
Opis:
W pracy dokonano analizy działania modeli neuronowych, które różniły się parametrami tj. liczbą neuronów i liczbą warstw ukrytych. Ocenę jakości działania przeprowadzono w oparciu o wartości uzyskanych błędów względnych i odchylenia standardowego. Do nauczania sieci neuronowych wykorzystano dane, dotyczące zależności pomiędzy średnią średnicą granulowanych cząstek komponentów i temperatury pary wodnej podawanej do kondycjonera granulatora a wytrzymałością kinetyczną granul.
In this work analyses of action of neural model were made. The neural models differed in parameters: number of neurons and the number of hidden layers. The assessment of the quality of action was carried in the support of relative mistakes gotten about value and of standard deviation. Data, concerning the relation was used to teaching neural networks between the average diameter particles of components and the temperature of given steam to conditioner and with kinetic durability of pellets.
Źródło:
Inżynieria Rolnicza; 2006, R. 10, nr 6(81), 6(81); 241-248
1429-7264
Pojawia się w:
Inżynieria Rolnicza
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Acoustical Assessment of Automotive Mufflers Using FEM, Neural Networks, and a Genetic Algorithm
Autorzy:
Chang, Y.-C.
Chiu, M.-C.
Wu, M.-R.
Powiązania:
https://bibliotekanauki.pl/articles/177901.pdf
Data publikacji:
2018
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
acoustics
finite element method
genetic algorithm
muffler optimization
polynomial neural network model
Opis:
In order to enhance the acoustical performance of a traditional straight-path automobile muffler, a multi-chamber muffler having reverse paths is presented. Here, the muffler is composed of two internally parallel/extended tubes and one internally extended outlet. In addition, to prevent noise transmission from the muffler’s casing, the muffler’s shell is also lined with sound absorbing material. Because the geometry of an automotive muffler is complicated, using an analytic method to predict a muffler’s acoustical performance is difficult; therefore, COMSOL, a finite element analysis software, is adopted to estimate the automotive muffler’s sound transmission loss. However, optimizing the shape of a complicated muffler using an optimizer linked to the Finite Element Method (FEM) is time-consuming. Therefore, in order to facilitate the muffler’s optimization, a simplified mathematical model used as an objective function (or fitness function) during the optimization process is presented. Here, the objective function can be established by using Artificial Neural Networks (ANNs) in conjunction with the muffler’s design parameters and related TLs (simulated by FEM). With this, the muffler’s optimization can proceed by linking the objective function to an optimizer, a Genetic Algorithm (GA). Consequently, the discharged muffler which is optimally shaped will improve the automotive exhaust noise.
Źródło:
Archives of Acoustics; 2018, 43, 3; 517-529
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analiza stanu naprężeń i przemieszczeń konstrukcji aluminiowej z wymienianymi elementami
The analysis of stresses and displacements in the aluminium structure with replaceable elements
Autorzy:
Potrzeszcz-Sut, B
Pabisek, E.
Powiązania:
https://bibliotekanauki.pl/articles/390675.pdf
Data publikacji:
2013
Wydawca:
Politechnika Lubelska. Wydawnictwo Politechniki Lubelskiej
Tematy:
analiza numeryczna
model materiału Ramberga – Osgooda
sztuczna sieć neuronowa
neuronowy model materiału
numerical analysis
Ramberg-Osgood material model
artificial neural network
neural material model
Opis:
Praca dotyczy nieliniowej analizy numerycznej naprężeń i przemieszczeń węzłów kratownicowej wieży aluminiowej. Założono model materiału Ramberga – Osgooda (RO) przedstawiający potęgową zależność między odkształceniem i naprężeniem: ε(σ). W celu identyfikacji zależności odwrotnej – σ(ε), dla materiału aluminiowego, zastosowano sztuczną sieć neuronową (SSN). W związku z koniecznością wzmocnienia konstrukcji, do układu wprowadzono sprężyste elementy stalowe. Przeprowadzono analizę stanu naprężeń i ekstremalnych przemieszczeń podczas cyklicznego obciążania i odciążania układu. Wykonano dwa rodzaje globalnych odciążeń – sprężyste i sprężysto – plastyczne. Przedstawione zostały zależności między wartością parametru obciążenia konfiguracyjnego, a wychyleniem wierzchołka A wieży. Analiza została wykonana za pomocą programu hybrydowego integrującego MES i SSN.
The paper concerns the non-linear analysis of stresses and displacements in an aluminium truss tower. The Ramberg – Osgood material model was assumed. This model introduced power type relation between stresses and strains. In order to identify the inverse relation, a neural network was used. Because of the need to strengthen the tower, a number of aluminium bars was replaced by steel bars. The perfect elastic material model was assumed for the steel bars. The analysis of stresses and extreme displacements was performed during the cyclic loading and unloading of the system. Two global unloading processes were considered: elastic and elastic-plastic processes. The relationship between the load factor and deflection of the top of the tower is shown. Analysis was performed using a hybrid FEM/ANN program.
Źródło:
Budownictwo i Architektura; 2013, 12, 1; 275-282
1899-0665
Pojawia się w:
Budownictwo i Architektura
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Wykorzystanie sieci neuronowych w modelowaniu zależności między wybranymi cechami fizykochemicznymi i elektrycznymi miodu
The use of artificial neural networks for modeling of the relationships between physicochemical and electrical properties of honey
Autorzy:
Luczycka, D.
Pentos, K.
Powiązania:
https://bibliotekanauki.pl/articles/796772.pdf
Data publikacji:
2014
Wydawca:
Szkoła Główna Gospodarstwa Wiejskiego w Warszawie. Wydawnictwo Szkoły Głównej Gospodarstwa Wiejskiego w Warszawie
Tematy:
miod
cechy fizykochemiczne
cechy elektryczne
zaleznosci
sieci neuronowe sztuczne
analiza wrazliwosci
modele neuronowe
honey
physicochemical trait
electrical property
trait relationship
artificial neural network
sensitivity analysis
neural model
Opis:
Na cechy chemiczne i elektryczne miodu mają wpływ jego skład pyłkowy oraz zawartość wody. O ile zawartość wody można powiązać z analizowanymi parametrami zależnością funkcyjną, o tyle wpływ zawartości pyłków na badane cechy chemiczne i elektryczne miodu jest bardziej skomplikowanym zagadnieniem. W jednej próbce miodu można stwierdzić kilka do kilkunastu rodzajów pyłków różnych roślin, dlatego analiza jedynie wpływu pyłku przewodniego nie jest wystarczająca. Przedmiotem pracy jest wykorzystanie dwóch rodzajów sztucznych sieci neuronowych do tworzenia możliwie dokładnych modeli matematycznych uwzględniających zależność takich cech miodu, jak zawartość cukrów, aminokwasów, wolnych kwasów oraz przewodność elektryczna patoki od zawartości pyłków roślin i zawartości wody w próbce. Wykorzystując perceptron wielowarstwowy jako model matematyczny opisanych wyżej zależności, dokonano analizy wrażliwości. Na podstawie tej analizy możliwa była ocena wpływu parametrów wejściowych modelu na poszczególne wielkości wyjściowe. Sztuczne sieci neuronowe są wygodnym narzędziem do modelowania zależności pomiędzy cechami chemicznymi i elektrycznymi miodu a jego składem pyłkowym oraz zawartością wody. Większą dokładność modelu uzyskano wykorzystując perceptron wielowarstwowy o stosunkowo prostej strukturze. Sieci RBF generują model o znacznie niższej dokładności.
Pollen content and water content may influence the chemical and electrical parameters of honey. Water content can be related to analysed parameters by functional relationship but the influence of pollen content on honey chemical and electric parameters is more complicated. In one honey sample may be a few or several pollen of various plant types. The analysis only primary pollen influence is not adequate. The subject of this work is the use of two types of artificial neural networks to obtain accurate mathematical models describing the relationship between honey parameters like the content of sugars, amino acids, free acids, strained honey conductivity and both pollen content and water content. A total of 50 honey samples were used for this study. The honey samples with different production origin and varieties have been collected. Regarding the type of honey, in the samples group there were nectar, nectar-honeydew and honeydew honeys. Artificial neural networks are an useful tool for modeling relationships between chemical and electrical honey features as the output model parameters and both pollen content and water content as the input model parameters. Two neural network types were used for modeling task – multilayer perceptron and RBF network. Several dozen network structures were investigated and model quality assessment was based on the value of average relative error and standard deviation of the relative error calculated for both, training and test data sets. The values of average relative error as well as standard deviation of the relative error calculated for best network structures obtained in simulation tests prove the practical utility of neural models. The results obtained for RBF network show that the practical utility of this model is lower than multilayer perceptron (the values of average relative error exceed 20% for all structures tested). Using the multilayer perceptron as a mathematical model of these relationships, sensitivity analysis were executed. On the basis of this analysis, the assessment of the influence of model input parameters on some selected output parameters was possible. The results of the sensitivity analysis show that all input model parameters are statistically significant for all output model parameters (error quotient ≥ 1). In case of the model describing relationship between strained honey conductivity and both, water content and pollen content, one can not identify dominant explanatory variables. The most significant influence on glucose/ fructose content ratio, free acids content and proline content was observed for content of two pollen: Brassica napus and Brassicaceae.
Źródło:
Zeszyty Problemowe Postępów Nauk Rolniczych; 2014, 576
0084-5477
Pojawia się w:
Zeszyty Problemowe Postępów Nauk Rolniczych
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Study on maritime logistics warehousing center model and precision marketing strategy optimization based on fuzzy method and neural network model
Autorzy:
Xiao, K.
Hu, X.
Powiązania:
https://bibliotekanauki.pl/articles/260268.pdf
Data publikacji:
2017
Wydawca:
Politechnika Gdańska. Wydział Inżynierii Mechanicznej i Okrętownictwa
Tematy:
maritime logistics warehousing center mode
precision marketing strategy optimization
fuzzy method
neural network model
polarity reversal
Opis:
The bulk commodity, different with the retail goods, has a uniqueness in the location selection, the chosen of transportation program and the decision objectives. How to make optimal decisions in the facility location, requirement distribution, shipping methods and the route selection and establish an effective distribution system to reduce the cost has become a burning issue for the e-commerce logistics, which is worthy to be deeply and systematically solved. In this paper, Logistics warehousing center model and precision marketing strategy optimization based on fuzzy method and neural network model is proposed to solve this problem. In addition, we have designed principles of the fuzzy method and neural network model to solve the proposed model because of its complexity. Finally, we have solved numerous examples to compare the results of lingo and Matlab, we use Matlab and lingo just to check the result and to illustrate the numerical example, we can find from the result, the multi-objective model increases logistics costs and improves the efficiency of distribution time.
Źródło:
Polish Maritime Research; 2017, S 2; 30-38
1233-2585
Pojawia się w:
Polish Maritime Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Hybrid MES/SSN analysis of the elastic-plastic truss under cyclic loading
Analiza hybrydowa MES/SSN sprężysto-plastycznej konstrukcji kratowej poddanej obciążeniu cyklicznemu
Autorzy:
Potrzeszcz-Sut, B
Powiązania:
https://bibliotekanauki.pl/articles/402477.pdf
Data publikacji:
2014
Wydawca:
Politechnika Świętokrzyska w Kielcach. Wydawnictwo PŚw
Tematy:
nonlinear numerical analysis
inverse problem
Ramberg-Osgood material model
artificial neural network
neural material model
nieliniowa analiza numeryczna
problem odwrotny
model materiału Ramberg-Osgood
sztuczne sieci neuronowe
neuronowy model materiału
Opis:
The paper presents the application of a hybrid program that integrates finite element method (FEM) and artificial neural network (ANN) for nonlinear analysis of plane truss. ANN, used for the solving the inverse problem has been formulated in ‘off line’ mode. Learning and testing of ANN were carried out using pseudo empirical data. The network formed thereby constitutes the neural material model (NMM), describes the Ramberg-Osgood nonlinear physical relationship. NMM makes it possible to determine the stress and tangential module during cyclic loading of the structure. Numerical tests indicate that the developed FEM/ANN program may be applied to analyse other boundary problems in the uniaxial stress state.
Źródło:
Structure and Environment; 2014, 6, 4; 12-16
2081-1500
Pojawia się w:
Structure and Environment
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Noise Elimination of Reciprocating Compressors Using FEM, Neural Networks Method, and the GA Method
Autorzy:
Chang, Y.-C.
Chiu, M.-C.
Xie, J.-L.
Powiązania:
https://bibliotekanauki.pl/articles/178126.pdf
Data publikacji:
2017
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
finite element method
polynomial neural network model
genetic algorithm
group method of data handling
reciprocating compressor
optimization
Opis:
Industry often utilizes acoustical hoods to block noise emitted from reciprocating compressors. However, the hoods are large and bulky. Therefore, to diminish the size of the compressor, a compact discharge muffler linked to the compressor outlet is considered. Because the geometry of a reciprocating compressor is irregular, COMSOL, a finite element analysis software, is adopted. In order to explore the acoustical performance, a mathematical model is established using a finite element method via the COMSOL commercialized package. Additionally, to facilitate the shape optimization of the muffler, a polynomial neural network model is adopted to serve as an objective function; also, a Genetic Algorithm (GA) is linked to the OBJ function. During the optimization, various noise abatement strategies such as a reverse expansion chamber at the outlet of the discharge muffler and an inner extended tube inside the discharge muffler, will be assessed by using the artificial neural network in conjunction with the GA optimizer. Consequently, the discharge muffler that is optimally shaped will decrease the noise of the reciprocating compressor.
Źródło:
Archives of Acoustics; 2017, 42, 2; 189-197
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Shape Optimisation of Multi-Chamber Acoustical Plenums Using BEM, Neural Networks, and GA Method
Autorzy:
Chang, Y.-C.
Cheng, H.-C.
Chiu, M.-C.
Chien, Y.-H.
Powiązania:
https://bibliotekanauki.pl/articles/177780.pdf
Data publikacji:
2016
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
boundary element method
plenum
centre-opening baffle
polynomial neural network model
group method of data handling
optimisation
genetic algorithm
Opis:
Research on plenums partitioned with multiple baffles in the industrial field has been exhaustive. Most researchers have explored noise reduction effects based on the transfer matrix method and the boundary element method. However, maximum noise reduction of a plenum within a constrained space, which frequently occurs in engineering problems, has been neglected. Therefore, the optimum design of multi-chamber plenums becomes essential. In this paper, two kinds of multi-chamber plenums (Case I: a two-chamber plenum that is partitioned with a centre-opening baffle; Case II: a three-chamber plenum that is partitioned with two centre-opening baffles) within a fixed space are assessed. In order to speed up the assessment of optimal plenums hybridized with multiple partitioned baffles, a simplified objective function (OBJ) is established by linking the boundary element model (BEM, developed using SYSNOISE) with a polynomial neural network fit with a series of real data – input design data (baffle dimensions) and output data approximated by BEM data in advance. To assess optimal plenums, a genetic algorithm (GA) is applied. The results reveal that the maximum value of the transmission loss (TL) can be improved at the desired frequencies. Consequently, the algorithm proposed in this study can provide an efficient way to develop optimal multi-chamber plenums for industry.
Źródło:
Archives of Acoustics; 2016, 41, 1; 43-53
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Effect of ship neural domain shape on safe and optimal trajectory
Autorzy:
Lisowski, J.
Powiązania:
https://bibliotekanauki.pl/articles/24201475.pdf
Data publikacji:
2023
Wydawca:
Uniwersytet Morski w Gdyni. Wydział Nawigacyjny
Tematy:
artificial neural network model
method for optimization
dynamic programming method
ship safety domain
safe ship control
path planning
multi-object decision model
computer simulation
Opis:
This article presents the task of safely guiding a ship, taking into account the movement of many other marine units. An optimally neural modified algorithm for determining a safe trajectory is presented. The possible shapes of the domains assigned to other ships as traffic restrictions for the particular ship were subjected to a detailed analysis. The codes for the computer program Neuro-Constraints for generating these domains are presented. The results of the simulation tests of the algorithm for a navigational situation are presented. The safe trajectories of the ship were compared at different distances, changing the sailing conditions and ship sizes.
Źródło:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation; 2023, 17, 1; 185--191
2083-6473
2083-6481
Pojawia się w:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Small Wind Turbine Output Model for Spatially Constrained Remote Island Micro-Grids
Autorzy:
Žigman, D.
Meštrović, K.
Tomiša, T.
Powiązania:
https://bibliotekanauki.pl/articles/2172468.pdf
Data publikacji:
2022
Wydawca:
Uniwersytet Morski w Gdyni. Wydział Nawigacyjny
Tematy:
wind turbine
small wind turbine
decision tree model
artificial neural network model
random forest model
micro-grids
spatially constrained remote Island micro-grids
remote Island micro-grid
Opis:
Modelling operation of the power supply system for remote island communities is essential for its operation, as well as a survival of a modern society settled in challenging conditions. Micro-grid emerges as a proper solution for a sustainable development of a spatially constrained remote island community, while at the same time reflecting the power requirements of similar maritime subjects, such as large vessels and fleets. Here we present research results in predictive modelling the output of a small wind turbine, as a component of a remote island micro-grid. Based on a month-long experimental data and the machine learning-based predictive model development approach, three candidate models of a small wind turbine output were developed, and assessed on their performance based on an independent set of experimental data. The Random Forest Model out performed competitors (Decision Tree Model and Artificial Neural Network Model), emerging as a candidate methodology for the all-year predictive model development, as a later component of the over-all remote island micro-grid model.
Źródło:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation; 2022, 16, 1; 143--146
2083-6473
2083-6481
Pojawia się w:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Environmental analysis of a product manufactured with the use of an additive technology – AI-based vs. traditional approaches
Autorzy:
Dostatni, Ewa
Dudkowiak, Anna
Rojek, Izabela
Mikołajewski, Dariusz
Powiązania:
https://bibliotekanauki.pl/articles/2204511.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
additive manufacturing
AM
eco-design
life cycle assessment
LCA
artificial intelligence
AI
neural networks model
produkcja dodatkowa
zielony design
szacowanie cyklu życia
sztuczna inteligencja
model sieci neuronowej
Opis:
This paper attempts to conduct a comparative life cycle environmental analysis of alternative versions of a product that was manufactured with the use of additive technologies. The aim of the paper was to compare the environmental assessment of an additive-manufactured product using two approaches: a traditional one, based on the use of SimaPro software, and the authors’ own concept of a newly developed artificial intelligence (AI) based approach. The structure of the product was identical and the research experiments consisted in changing the materials used in additive manufacturing (from polylactic acid (PLA) to acrylonitrile butadiene styrene (ABS)). The effects of these changes on the environmental factors were observed and a direct comparison of the effects in the different factors was made. SimaPro software with implemented databases was used for the analysis. Missing information on the environmental impact of additive manufacturing of PLA and ABS parts was taken from the literature for the purpose of the study. The novelty of the work lies in the results of a developing concurrent approach based on AI. The results showed that the artificial intelligence approach can be an effective way to analyze life cycle assessment (LCA) even in such complex cases as a 3D printed medical exoskeleton. This approach, which is becoming increasingly useful as the complexity of manufactured products increases, will be developed in future studies.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2023, 71, 1; art. no. e144478
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Membrain neural network for visual pattern recognition
Autorzy:
Popko, A.
Jakubowski, M.
Wawer, R.
Powiązania:
https://bibliotekanauki.pl/articles/103198.pdf
Data publikacji:
2013
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
neural network
pattern recognition
neuron model
Opis:
Recognition of visual patterns is one of significant applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In the paper, a simplified neural approach to recognition of visual patterns is portrayed and discussed. This paper is dedicated for investigators in visual patterns recognition, Artificial Neural Networking and related disciplines. The document describes also MemBrain application environment as a powerful and easy to use neural networks’ editor and simulator supporting ANN.
Źródło:
Advances in Science and Technology. Research Journal; 2013, 7, 18; 54-59
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Hybrid demand forecasting models: pre-pandemic and pandemic use studies
Autorzy:
Kolkova, Andrea
Rozehnal, Petr
Powiązania:
https://bibliotekanauki.pl/articles/22443157.pdf
Data publikacji:
2022
Wydawca:
Instytut Badań Gospodarczych
Tematy:
forecastHybrid
demand forecasting
statistic model
neural networks
Opis:
Research background: In business practice and academic sphere, the question of which of the prognostic models is the most accurate is constantly present. The accuracy of models based on artificial intelligence and statistical models has long been discussed. By combining the advantages of both groups, hybrid models have emerged. These models show high accuracy. Moreover, the question remains whether data in a dynamically changing economy (for example, in a pandemic period) have changed the possibilities of using these models. The changing economy will continue to be an important element in demand forecasting in the years to come. In business, where the concept of just in time already proves to be insufficient, it is necessary to open new research questions in the field of demand forecasting. Purpose of the article: The aim of the article is to apply hybrid models to bicycle sales e-shop data with a comparison of accuracy models in the pre-pandemic period and in the pandemic period. The paper examines the hypothesis that the pandemic period has changed the accuracy of hybrid models in comparison with statistical models and models based on artificial neural networks. Models: In this study, hybrid models will be used, namely the Theta model and the new forecastHybrid, compared to the statistical models ETS, ARIMA, and models based on artificial neural networks. They will be applied to the data of the e-shop with the cycle assortment in the period from 1.1. 2019 to 5.10 2021. Whereas the period will be divided into two parts, pre-pandemic, i.e. until 1 March 2020 and pandemic after that date. The accuracy evaluation will be based on the RMSE, MAE, and ACF1 indicators. Findings & value added: In this study, we have concluded that the prediction of the Hybrid model was the most accurate in both periods. The study can thus provide a scientific basis for any other dynamic changes that may occur in demand forecasting in the future. In other periods when there will be volatile demand, it is essential to choose models in which accuracy will decrease the least. Therefore, this study provides guidance for the use of methods in future periods as well. The stated results are likely to be valid even in an international comparison.
Źródło:
Equilibrium. Quarterly Journal of Economics and Economic Policy; 2022, 17, 3; 699-725
1689-765X
2353-3293
Pojawia się w:
Equilibrium. Quarterly Journal of Economics and Economic Policy
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The recognition of partially occluded objects with support vector machines, convolutional neural networks and deep belief networks
Autorzy:
Chu, J. L.
Krzyżak, A.
Powiązania:
https://bibliotekanauki.pl/articles/91650.pdf
Data publikacji:
2014
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
neural networks
belief networks
convolutional neural networks
artificial neural networks
Deep Belief Network
generative model
Opis:
Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Belief Network should perform better on the occluded object recognition task than purely discriminative models such as Convolutional Neural Networks and Support Vector Machines. When the generative models are run in a partially discriminative manner, the data does not support the hypothesis. It is also found that the implementation of Gaussian visible units in a Deep Belief Network trained on occluded image data allows it to also learn to effectively classify non-occluded images.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2014, 4, 1; 5-19
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Neural networks as performance improvement models in intelligent CAPP systems
Autorzy:
Rojek, I.
Powiązania:
https://bibliotekanauki.pl/articles/971020.pdf
Data publikacji:
2010
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
classification model
neural network
tool
manufacturing operation
Opis:
The paper presents neural networks as performance improvement models in intelligent computer aided process planning systems (CAPP systems). For construction of these models three types of neural networks were used: linear network, multi-layer network with error backpropagation, and the Radial Basis Function network (RBF). The models were compared. Due to the comparison, we can say which type of neural network is the best for selection of tools for manufacturing operations. Tool selection for manufacturing operation is a classification problem. Hence, neural networks were built as classification models, meant to improve tool selection for manufacturing. The study was done for selected manufacturing operations: turning, milling and grinding. Models for the milling operation were presented in detail.
Źródło:
Control and Cybernetics; 2010, 39, 1; 54-68
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Neural Network Model for Object Mask Detection in Medical Images
Autorzy:
Tereikovskyi, Igor
Korchenko, Oleksander
Bushuyev, Sergey
Tereikovskyi, Oleh
Ziubina, Ruslan
Veselska, Olga
Powiązania:
https://bibliotekanauki.pl/articles/2200721.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
model
neural network
object mask
medical images
Opis:
In modern conditions in the field of medicine, raster image analysis systems are becoming more widespread, which allow automating the process of establishing a diagnosis based on the results of instrumental monitoring of a patient. One of the most important stages of such an analysis is the detection of the mask of the object to be recognized on the image. It is shown that under the conditions of a multivariate and multifactorial task of analyzing medical images, the most promising are neural network tools for extracting masks. It has also been determined that the known detection tools are highly specialized and not sufficiently adapted to the variability of the conditions of use, which necessitates the construction of an effective neural network model adapted to the definition of a mask on medical images. An approach is proposed to determine the most effective type of neural network model, which provides for expert evaluation of the effectiveness of acceptable types of models and conducting computer experiments to make a final decision. It is shown that to evaluate the effectiveness of a neural network model, it is possible to use the Intersection over Union and Dice Loss metrics. The proposed solutions were verified by isolating the brachial plexus of nerve fibers on grayscale images presented in the public Ultrasound Nerve Segmentation database. The expediency of using neural network models U-Net, YOLOv4 and PSPNet was determined by expert evaluation, and with the help of computer experiments, it was proved that U-Net is the most effective in terms of Intersection over Union and Dice Loss, which provides a detection accuracy of about 0.89. Also, the analysis of the results of the experiments showed the need to improve the mathematical apparatus, which is used to calculate the mask detection indicators.
Źródło:
International Journal of Electronics and Telecommunications; 2023, 69, 1; 41--46
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Single-ended quality measurement of a music content via convolutional recurrent neural networks
Autorzy:
Organiściak, Kamila
Borkowski, Józef
Powiązania:
https://bibliotekanauki.pl/articles/1849158.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
audio data analysis
artefacts detection
convolutional neural networks
recurrent neural networks
classification model
Opis:
The paper examines the usage of Convolutional Bidirectional Recurrent Neural Network (CBRNN) for a problem of quality measurement in a music content. The key contribution in this approach, compared to the existing research, is that the examined model is evaluated in terms of detecting acoustic anomalies without the requirement to provide a reference (clean) signal. Since real music content may include some modes of instrumental sounds, speech and singing voice or different audio effects, it is more complex to analyze than clean speech or artificial signals, especially without a comparison to the known reference content. The presented results might be treated as a proof of concept, since some specific types of artefacts are covered in this paper (examples of quantization defect, missing sound, distortion of gain characteristics, extra noise sound). However, the described model can be easily expanded to detect other impairments or used as a pre-trained model for other transfer learning processes. To examine the model efficiency several experiments have been performed and reported in the paper. The raw audio samples were transformed into Mel-scaled spectrograms and transferred as input to the model, first independently, then along with additional features (Zero Crossing Rate, Spectral Contrast). According to the obtained results, there is a significant increase in overall accuracy (by 10.1%), if Spectral Contrast information is provided together with Mel-scaled spectrograms. The paper examines also the influence of recursive layers on effectiveness of the artefact classification task.
Źródło:
Metrology and Measurement Systems; 2020, 27, 4; 721-733
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Software implementation of multiple model neural filter for radar target tracking
Autorzy:
Kazimierski, W.
Wawrzyniak, N.
Powiązania:
https://bibliotekanauki.pl/articles/359024.pdf
Data publikacji:
2012
Wydawca:
Akademia Morska w Szczecinie. Wydawnictwo AMSz
Tematy:
radar target tracking
multiple model filters
neural networks
Opis:
The paper presents a software implementation of multiple model neural filter for radar target tracking. Such a filter may be proposed as an interesting alternative for numerical filters. The main purpose of software implementation is to provide a tool for complex research of the filter possibilities and adjusting options. A concept of a filter is briefly mentioned, however the main body of paper is focused on user-approach detailed description of application with UML use-case diagrams. Examples of detailed presentation of usecases are given and the general use-case diagram for application is included. The application itself is to be an advanced tool for researchers interested in analyzing target tracking process, providing different tracking methods and the possibility of adjusting their parameters. The possibility of simulating any scenario, as well as working with real data (also on-line) was ensured. The research was financed by Polish National Centre of Science under the research project “Development of radar target tracking methods of floating targets with the use of multiple model neural filtering”.
Źródło:
Zeszyty Naukowe Akademii Morskiej w Szczecinie; 2012, 32 (104) z. 2; 88-93
1733-8670
2392-0378
Pojawia się w:
Zeszyty Naukowe Akademii Morskiej w Szczecinie
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
An artificial neural networks approach to product cost estimation. The case study for electric motor
Autorzy:
Leszczyński, Zbigniew
Jasiński, Tomasz
Powiązania:
https://bibliotekanauki.pl/articles/432073.pdf
Data publikacji:
2018
Wydawca:
Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
Tematy:
cost estimation model
artifical neural networks
product cost
Opis:
The aim of this paper is to present, in theoretical and application terms, artificial neural networks (ANNs) as a method of estimating the product cost. The first part of the article reviews the methods used to estimate the product cost. The basic approaches to the problem of product cost estimation, presented by various authors, were described. In the second part an empirical study using artificial neural networks was conducted. Two research methods were used in this paper: literature analysis and empirical research carried out in the form of an extensive case study. The test object is a new generation induction motor. The main research problem of the article is the modelling of artificial neural networks for the estimation process of product costs with advanced production technology. The test procedures focus on the application aspects. The conclusions discuss the usefulness and advantages of using ANN models in estimating the costs of products
Źródło:
Informatyka Ekonomiczna; 2018, 1(47); 72-84
1507-3858
Pojawia się w:
Informatyka Ekonomiczna
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Demand forecasting: an alternative approach based on technical indicator Pbands
Autorzy:
Kolková, Andrea
Ključnikov, Aleksandr
Powiązania:
https://bibliotekanauki.pl/articles/19233720.pdf
Data publikacji:
2021
Wydawca:
Instytut Badań Gospodarczych
Tematy:
demand forecasting
neural network
BATS
hybrid model
Pbands
Opis:
Research background: Demand forecasting helps companies to anticipate purchases and plan the delivery or production. In order to face this complex problem, many statistical methods, artificial intelligence-based methods, and hybrid methods are currently being developed. However, all these methods have similar problematic issues, including the complexity, long computing time, and the need for high computing performance of the IT infrastructure. Purpose of the article: This study aims to verify and evaluate the possibility of using Google Trends data for poetry book demand forecasting and compare the results of the application of the statistical methods, neural networks, and a hybrid model versus the alternative possibility of using technical analysis methods to achieve immediate and accessible forecasting. Specifically, it aims to verify the possibility of immediate demand forecasting based on an alternative approach using Pbands technical indicator for poetry books in the European Quartet countries. Methods: The study performs the demand forecasting based on the technical analysis of the Google Trends data search in case of the keyword poetry in the European Quartet countries by several statistical methods, including the commonly used ETS statistical methods, ARIMA method, ARFIMA method, BATS method based on the combination of the Cox-Box transformation model and ARMA, artificial neural networks, the Theta model, a hybrid model, and an alternative approach of forecasting using Pbands indicator.  The study uses MAPE and RMSE approaches to measure the accuracy. Findings & value added: Although most currently available demand prediction models are either slow or complex, the entrepreneurial practice requires fast, simple, and accurate ones. The study results show that the alternative Pbands approach is easily applicable and can predict short-term demand changes. Due to its simplicity, the Pbands method is suitable and convenient to monitor short-term data describing the demand. Demand prediction methods based on technical indicators represent a new approach for demand forecasting. The application of these technical indicators could be a further forecasting models research direction. The future of theoretical research in forecasting should be devoted mainly to simplifying and speeding up. Creating an automated model based on primary data parameters and easily interpretable results is a challenge for further research.
Źródło:
Oeconomia Copernicana; 2021, 12, 4; 1063-1094
2083-1277
Pojawia się w:
Oeconomia Copernicana
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Genetic algorithms and neural networks for solving water quality model of the Egyptian research reactor
Autorzy:
El-Sayed Wahed, M.
Ibrahim, W. Z.
Effat, A. M.
Powiązania:
https://bibliotekanauki.pl/articles/148150.pdf
Data publikacji:
2009
Wydawca:
Instytut Chemii i Techniki Jądrowej
Tematy:
genetic algorithm
neural networks
model calibration
water distribution system
water quality model
Opis:
The second Egyptian research reactor ETRR-2 became critical on 27th November, 1997. The National Center of Nuclear Safety and Radiation Control (NCNSRC) has the responsibility for the evaluation and assessment of safety of this reactor. Modern managements of water distribution system (WDS) need water quality models that are able to accurately predict the dynamics of water quality variations within the distribution system environment. Before water quality models can be applied to solve system problems, they should be calibrated. The purpose of this paper is to present an approach which combines both macro and detailed models to optimize the water quality parameters. For an efficient search through the solution space, we use a multi-objective genetic algorithm which allows us to identify a set of Pareto optimal solutions providing the decision maker with a complete spectrum of optimal solutions with respect to the various targets. This new combinative algorithm uses the radial basis function (RBF) metamodeling as a surrogate to be optimized for the purpose of decreasing the times of time-consuming water quality simulation and can realize rapidly the calibration of pipe wall reaction coefficients of chlorine model of large-scaled WDS.
Źródło:
Nukleonika; 2009, 54, 4; 239-245
0029-5922
1508-5791
Pojawia się w:
Nukleonika
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Porównanie modeli GRNN utworzonych z wykorzystaniem modułów sieci neuronowych pakietów MATLAB i STATISTICA
Comparison of the GRNN models developed by using neural network moduli of the MATLAB and STATISTICA packets
Autorzy:
Białobrzewski, I.
Powiązania:
https://bibliotekanauki.pl/articles/287990.pdf
Data publikacji:
2005
Wydawca:
Polskie Towarzystwo Inżynierii Rolniczej
Tematy:
model regresyjny
sieci neuronowe GRNN
MATLAB
Statistica
regressive model
GRNN neural networks
Opis:
Przedstawiono wyniki badań wpływu modeli GRNN, utworzonych z wykorzystaniem modułów Sieci Neuronowych pakietów MATLAB i STATISTICA, na dokładność estymacji wartości temperatury powietrza atmosferycznego. Stwierdzono, że model neuronowy GRNN, powstały na bazie Toolbox Neural Networks v.4 pakietu MATLAB, lepiej aproksymuje temperaturę powietrza atmosferycznego niż modele powstałe na bazie modułu Neural Networks pakietu STATISTICA 6.1. Wśród modeli GRNN powstałych na bazie modułu Neural Networks pakietu STATISTICA 6.1 uzyskano lepszą aproksymuję temperatury powietrza atmosferycznego, wykorzystując dostępne opcje funkcji związanych z modułem Projektant sieci użytkownika.
The effects of GRNN models, developed by using the neural network moduli of the MATLAB and STATISTICA packets on the accuracy of atmospherical air temperature estimation, were studied. It was stated that the GRNN neural model developed on the basis of Toolbox Neural Network v.4 of the MATLAB packet approximated the temperature of atmospherical air better than the models based on Neural Network modulus of STATISTICA 6.1 packet. Among the GRNN models developed on the basis of Neural Network modulus of STATISTICA 6.1 packet, the better approximation of air temperature was obtained by using available options of the functions bound to modulus of the “User’s network designer …”
Źródło:
Inżynieria Rolnicza; 2005, R. 9, nr 8, 8; 15-22
1429-7264
Pojawia się w:
Inżynieria Rolnicza
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Elman neural network for modeling and predictive control of delayed dynamic systems
Autorzy:
Wysocki, A.
Ławryńczuk, M.
Powiązania:
https://bibliotekanauki.pl/articles/229646.pdf
Data publikacji:
2016
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
dynamic models
process control
model predictive control
neural networks
Elman neural network
delayed systems
Opis:
The objective of this paper is to present a modified structure and a training algorithm of the recurrent Elman neural network which makes it possible to explicitly take into account the time-delay of the process and a Model Predictive Control (MPC) algorithm for such a network. In MPC the predicted output trajectory is repeatedly linearized on-line along the future input trajectory, which leads to a quadratic optimization problem, nonlinear optimization is not necessary. A strongly nonlinear benchmark process (a simulated neutralization reactor) is considered to show advantages of the modified Elman neural network and the discussed MPC algorithm. The modified neural model is more precise and has a lower number of parameters in comparison with the classical Elman structure. The discussed MPC algorithm with on-line linearization gives similar trajectories as MPC with nonlinear optimization repeated at each sampling instant.
Źródło:
Archives of Control Sciences; 2016, 26, 1; 117-142
1230-2384
Pojawia się w:
Archives of Control Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Evaluation of models for the dew point temperature determination
Autorzy:
Górnicki, K.
Winiczenko, R.
Kaleta, A.
Choińska, A.
Powiązania:
https://bibliotekanauki.pl/articles/298023.pdf
Data publikacji:
2017
Wydawca:
Uniwersytet Warmińsko-Mazurski w Olsztynie
Tematy:
dew point temperature
relative humidity
model
artificial neural networks
Opis:
The accuracy of the available from the literature models for the dew point temperature determination was compared. The proposal of the modelling using artificial neural networks was also given. The experimental data were taken from the psychrometric tables. The accuracies of the models were measured using the mean bias error MBE, root mean square error RMSE, correlation coefficient R, and reduced chi-square χ2 . Model M3, especially with constants A=237, B=7.5, gave the best results in determining the dew point temperature (MBE: -0.0229 – 0.0038 K, RMSE: 0.1259 – 0.1286 K, R=0.9999, χ2 : 0.0159 – 0.0166 K2 ). Model M1 with constants A=243.5, B=17.67 and A=243.3, B=17.269 can be also considered as appropriate (MBE=-0.0062 and -0.0078 K, RMSE=0.1277 and 0.1261 K, R=0.9999, χ2 =0.0163 and 0.0159 K2 ). Proposed ANN model gave the good results in determining the dew point temperature (MBE=-0.0038 K, RMSE=0.1373 K, R=0.9999, χ2 =0.0189 K2 ).
Źródło:
Technical Sciences / University of Warmia and Mazury in Olsztyn; 2017, 20(3); 241--257
1505-4675
2083-4527
Pojawia się w:
Technical Sciences / University of Warmia and Mazury in Olsztyn
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A MLMVN with arbitrary complex-valued inputs and a hybrid testability approach for the extraction of lumped models using FRA
Autorzy:
Aizenberg, Igor
Luchetta, Antonio
Manetti, Stefano
Piccirilli, Maria Cristina
Powiązania:
https://bibliotekanauki.pl/articles/91696.pdf
Data publikacji:
2019
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
analog circuits
complex-valued neural networks
lumped model
testability
Opis:
A procedure for the identification of lumped models of distributed parameter electromagnetic systems is presented in this paper. A Frequency Response Analysis (FRA) of the device to be modeled is performed, executing repeated measurements or intensive simulations. The method can be used to extract the values of the components. The fundamental brick of this architecture is a multi-valued neuron (MVN), used in a multilayer neural network (MLMVN); the neuron is modified in order to use arbitrary complex-valued inputs, which represent the frequency response of the device. It is shown that this modification requires just a slight change in the MLMVN learning algorithm. The method is tested over three completely different examples to clearly explain its generality.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2019, 9, 1; 5-19
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Comparative Evaluation of the Use of Artificial Neural Networks for Modeling the Rainfall-Runoff Relationship in Water Resources Management
Autorzy:
Turhan, Evren
Powiązania:
https://bibliotekanauki.pl/articles/1838400.pdf
Data publikacji:
2021
Wydawca:
Polskie Towarzystwo Inżynierii Ekologicznej
Tematy:
rainfall-runoff model
artificial neural networks
MLR
Nergizlik Dam
Opis:
Recently, Artificial Neural Network (ANN) methods, which have been successfully applied in many fields, have been considered for a large number of reliable streamflow estimation and modeling studies for the design and project planning of hydraulic structures. The present study aimed to model the rainfall-runoff relationship using different ANN methods. The Nergizlik Dam, located in the Seyhan sub-basin and one of the important basins in Turkey, was chosen as the study area. Analyses were carried out based on streamflow estimation with the help of observed precipitation and runoff data at certain time intervals. Feed Forward Backpropagation Neural Network (FFBPNN) and Generalized Regression Neural Network (GRNN) methods were adopted, and obtained results were compared with Multiple Linear Regression (MLR) method, which is accepted as the traditional method. Also, the models were performed using three different transfer functions to create optimum ANN modeling. As a result of the study, it was seen that ANN methods showed statistically good results in rainfall-runoff modeling, and the developed models can be successfully applied in the estimation of average monthly flows.
Źródło:
Journal of Ecological Engineering; 2021, 22, 5; 166-178
2299-8993
Pojawia się w:
Journal of Ecological Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Sieci neuronowe typu MLP oraz RBF jako narzędzia klasyfikacyjne w analizie obrazu
The neural network type the MLP and RBF as classifying tools in picture analysis
Autorzy:
Boniecki, P.
Powiązania:
https://bibliotekanauki.pl/articles/337163.pdf
Data publikacji:
2006
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Maszyn Rolniczych
Tematy:
sieć neuronowa
sieć neuronowa MLP
sieć neuronowa RBF
analiza obrazu
identyfikacja neuronowa
model neuronowy
neural network
MLP neural network
RBF neural network
picture analysis
neuronal identification
neuronal model
Opis:
Neuronowa identyfikacja danych obrazowych, ze szczególnym naciskiem na analizę ilościową oraz jakościową, coraz częściej wykorzystywana jest do pozyskiwania oraz zgłębiania wiedzy zawartej w danych empirycznych. Ekstrakcja, a następnie klasyfikacja wybranych cech obrazu, pozawala na wytworzenie informatycznych narzędzi do identyfikacji wybranych obiektów, prezentowanych np. w postaci obrazu cyfrowego. W związku z tym, celowym wydaje się być poszukiwanie nowoczesnych metod wspomagających proces edukacyjny w zakresie konstrukcji oraz eksploatacji modeli neuronowych w kontekście ich wykorzystania w procesie analizy obrazu. Dodatkowym celem pracy było porównanie jakości sieci MLP oraz RBF mające na względzie wskazanie optymalnego instrumentu klasyfikacyjnego.
The neuronal identification of pictorial data, with special emphasis on both quantitative & qualitative analysis, is more frequently utilized to gain & deepen the empirical data knowledge. Extraction & then classification of selected picture features, enables one to create computer tools in order to identify these objects presented as, for example, digital pictures. In relationship from this, it seems to be purposeful the search of the modern methods helping educational process in the range of construction as well as exploitation of neuronal models in context of their utilization in picture analysis process. The additional aim of the work was the comparison of neural network of the type MLP and RBF for indication of the optimum classification tool.
Źródło:
Journal of Research and Applications in Agricultural Engineering; 2006, 51, 4; 34-39
1642-686X
2719-423X
Pojawia się w:
Journal of Research and Applications in Agricultural Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application perspective of digitalneural networks in the context of marine technologies
Autorzy:
Konon, V.
Konon, N.
Powiązania:
https://bibliotekanauki.pl/articles/24201415.pdf
Data publikacji:
2022
Wydawca:
Uniwersytet Morski w Gdyni. Wydział Nawigacyjny
Tematy:
marine technology
multi-layer perceptron
neural networks
digital neural networks
maritime industry
MLP algorithm
3D model
Artificial Neural Network
Opis:
This study is focused on the issue of digital neural networks’ implementation in the context of maritime industry. Various algorithms of such networks in the terms of the marine technologies have been reviewed in the current study in order to evaluate the effectiveness of the methodology and to propose a new concept of an artificial neural network’s application in this way. Fire-detection system simulation based on the thermal imagers’ data input had been developed to assess the efficiency of the concept suggested with a multi-layer perceptron (MLP) algorithm integrated into the designed 3d-model.
Źródło:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation; 2022, 16, 4; 743--747
2083-6473
2083-6481
Pojawia się w:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Measurement data processing with the use of art networks
Przetwarzania danych pomiarowych z wykorzystaniem sieci z rezonansem adaptacyjnym ART
Autorzy:
Mrówczyńska, M.
Sztubecki, J.
Powiązania:
https://bibliotekanauki.pl/articles/970998.pdf
Data publikacji:
2018
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
ART neural network
prediction model
vertical displacements
sieci neuronowe ART
model predykcyjny
przemieszczenia pionowe
Opis:
ART (Adaptive Resonance Theory) networks were invented in the 1990s as a new approach to the problem of image classification and recognition. ART networks belong to the group of resonance networks, which are trained without supervision. The paper presents the basic principles for creating and training ART networks, including the possibility of using this type of network for solving problems of predicting and processing measurement data, especially data obtained from geodesic monitoring. In the first stage of the process of creating a prediction model, a preliminary analysis of measurement data was carried out. It was aimed at detecting outliers because of their strong impact on the quality of the final model. Next, an ART network was used to predict the values of the vertical displacements of points of measurement and control networks stabilized on the inner and outer walls of an engineering object.
Sieci neuronowe ART (ang. Adaptive Resonance Theory) zostały opracowane w latach 90 ubiegłego wieku, jako nowe podejście w rozwiązywaniu problemów klasyfikacji i rozpoznawaniu obrazów. Sieci ART należą do grupy sieci rezonansowych, których uczenie prowadzone jest w trybie nie nadzorowanym. W artykule przedstawiono podstawowe zasady budowy i uczenia sieci neuronowych ART wraz z możliwością aplikacji tego rodzaju sieci do rozwiązywania zagadnień predykcji i przetwarzania danych pomiarowych, w szczególności pozyskanych w wyniku prowadzonego monitoringu geodezyjnego. W pierwszym etapie procesu budowy modelu predykcyjnego wykonano wstępną analizę danych pomiarowych związaną z wykrywaniem obserwacji odstających ze względu na ich istotny wpływ na ostateczną jakość modelu. Następnie wykorzystując sieć ART wyznaczono przewidywane wartości przemieszczeń pionowych dla punktów sieci pomiarowo-kontrolnej, zastabilizowanych na wewnętrznych i zewnętrznych ścianach obiektu budowlanego, na których zauważono liczne spękania.
Źródło:
Civil and Environmental Engineering Reports; 2018, No. 28(2); 186-195
2080-5187
2450-8594
Pojawia się w:
Civil and Environmental Engineering Reports
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Mathematical modelling of thermal processes by the use of regression and neural models
Autorzy:
Rusinowski, H.
Plis, M.
Powiązania:
https://bibliotekanauki.pl/articles/240114.pdf
Data publikacji:
2018
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
mathematical model
empirical functions
neural modeling
regression modeling
model matematyczny
funkcje empiryczne
modelowanie neuronowe
Opis:
The paper presents a description of used methods and exemplary mathematical models which are classified into theoretical-empirical models of thermal processes. Such models encompass equations resulting from the laws of physics and additional empirical functions describing processes for which analytical models are complex and difficult to develop. The principle of developing, advantages and disadvantages of presented models as well as quality prediction assessment were presented. Mathematical models of a steam boiler, a steam turbine as well as a heat recovery steam generator were described. Exemplary calculation results were presented and compared with measurements.
Źródło:
Archives of Thermodynamics; 2018, 39, 3; 111-127
1231-0956
2083-6023
Pojawia się w:
Archives of Thermodynamics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analiza twardości selera w czasie suszenia
Analysis of celery hardness during drying process
Autorzy:
Łapczyńska-Kordon, B.
Francik, S.
Powiązania:
https://bibliotekanauki.pl/articles/289364.pdf
Data publikacji:
2006
Wydawca:
Polskie Towarzystwo Inżynierii Rolniczej
Tematy:
twardość
sztuczna sieć neuronowa
model SSN
seler
hardness
SSN model
artificial neural network
celery
Opis:
W pracy przedstawiono próbę zastosowania modelu sformułowanego na bazie sztucznych sieci neuronowych do opisu zmian twardości selera w czasie konwekcyjnego suszenia w warunkach wymuszonego przepływu powietrza. Model opracowano na podstawie badań. Próbki selera w kształcie cylindrów o wymiarach 10x10 mm poddano suszeniu konwekcyjnemu w temperaturach: 60 i 70°C. Podczas suszenia w równych odstępach czasowych określano twardość materiału metodą Vickersa za pomocą mikrotwardościomierza PMT-3. Do opisu zmian twardości w zależności od zawartości wody, temperatury suszenia i rodzaju obróbki przed suszeniem zastosowano model opracowany za pomocą sztucznych sieci neuronowych SSN. Do budowy modelu zastosowano wielowarstwową jednokierunkową sztuczną sieć neuronową, wykorzystując do uczenia zmodyfikowany algorytm wstecznej propagacji błędu. Analizowano sieci o różnej architekturze w celu zoptymalizowania działania modelu sieciowego. Stwierdzono, że sieć o 3 neuronach w warstwie 1, 3 neuronach w warstwie 2 i 1 neuronie w warstwie wyjściowej jest optymalna. Błąd względny globalny pomiędzy wartościami otrzymanymi z doświadczeń i z obliczeń wyniósł 28,7%.
The paper presents an attempt of using a model created based on artificial neural networks for description of changes in celery hardness during convection drying under forced air circulation conditions. The model was developed based on the tests. Celery samples in a form of cylinders in size of 10x10 mm were put to convection drying at temperatures: 60 and 70°C. During the drying process material hardness was determined at equal time intervals based on the Vickers method using microhardness tester PMT-3. For description of hardness changes as a function of water content, drying temperature and type of treatment before drying a model developed based on artificial neural networks SSN was used. For creating the model a multilayer unidirectional neural network was employed, using a modified algorithm of backward error propagation for learning process. Networks with different architecture were analyzed in order to optimize actions of the network model. The analysis showed that the optimal network was the one with 3 neurons in layer 1, 3 neurons in layer 2 and 1 neuron in output layer. The global relative error between the values obtained from the experiments and from calculations was 28,7%.
Źródło:
Inżynieria Rolnicza; 2006, R. 10, nr 13(88), 13(88); 295-302
1429-7264
Pojawia się w:
Inżynieria Rolnicza
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Prospects of neural networks in business models
Autorzy:
Tereykovskaya, L.
Petrov, O.
Aleksander, M. B.
Powiązania:
https://bibliotekanauki.pl/articles/254320.pdf
Data publikacji:
2015
Wydawca:
Instytut Naukowo-Wydawniczy TTS
Tematy:
electromagnetic radiation
neural networks
business
business model
sieć neuronowa
biznes
model biznesowy
promieniowanie elektromagnetyczne
Opis:
In the article the analysis of existing protective coatings. Presents an algorithm synthesis of protective coating against electromagnetic radiation. The article is devoted to the problem of determining the prospects for the use of neural networks in business models. The possibilities for this most classical types of architecture of neural net-works. A number of conditions which allows you to determine the feasibility of a particular type of neural network. It is shown that the development of business models neural networks should be used only to solve those tasks that belong to a class of pattern recognition, and optimal management of associative memory. It was determined that the greatest practical effect can be expected in the application of neural networks in the classification of sensory information outlines business models.
Źródło:
TTS Technika Transportu Szynowego; 2015, 12; 1539-1545, CD
1232-3829
2543-5728
Pojawia się w:
TTS Technika Transportu Szynowego
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Nonlinearity Correction in Dynamic Measuring Devices Using Neural Network Models
Korekcja nieliniowości za pomocą modeli sieci neuronowych w zastosowaniu do dynamicznych urządzeń pomiarowych
Autorzy:
Al Rawashdeh, Laith Ahmed Mustafa
Zakharov, Igor Petrovitch
Zaporozhets, Oleg Vasyliovych
Powiązania:
https://bibliotekanauki.pl/articles/2068664.pdf
Data publikacji:
2020
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:
artificial neural network
three-layer perceptron
training
inverse model
neural network compensator
sztuczna sieć neuronowa
trójwarstwowy perceptron
uczenie
model odwrotny
kompensator sieci neuronowej
Opis:
A neural network compensator for the nonlinearity of a dynamic measuring instrument is proposed, which allows restoring the value of the measured input signal. The inverse model of a nonlinear dynamic measuring device is implemented based on a three-layer perceptron supplemented by delay lines of input signals. The properties of the proposed neural network compensator are studied through simulation computer modelling using various types of calibration input signals for the training of an artificial neural network.
Zaproponowano kompensator sieci neuronowej dla nieliniowości dynamicznego przyrządu pomiarowego, który umożliwia odtworzenie wartości mierzonego sygnału wejściowego. Odwrotny model nieliniowego dynamicznego urządzenia pomiarowego realizowany jest w oparciu o trójwarstwowy perceptron uzupełniony o linie opóźniające sygnałów wejściowych. Właściwości proponowanego kompensatora sieci neuronowej są badane poprzez symulacyjne modelowanie komputerowe z wykorzystaniem różnego rodzaju sygnałów wejściowych kalibracji do uczenia sztucznej sieci neuronowej.
Źródło:
Pomiary Automatyka Robotyka; 2020, 24, 4; 57--60
1427-9126
Pojawia się w:
Pomiary Automatyka Robotyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Proposed Merging Methods of Digital Elevation Model Based on Artificial Neural Network and Interpolation Techniques for Improved Accuracy
Autorzy:
Alemam, Mustafa K.
Yong, Bin
Sani-Mohammed, Abubakar
Powiązania:
https://bibliotekanauki.pl/articles/27314479.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Centrum Badań Kosmicznych PAN
Tematy:
digital elevation model
GIS
artificial neural network
interpolation methods
SRTM
Opis:
The digital elevation model (DEM) is one of the most critical sources of terrain elevations, which are essential in various geoscience applications. Most of these applications need precise elevations, which are available at a high cost. Thus, sources like the Shuttle Radar Topography Mission (SRTM) DEM are frequently accessible to all users but with low accuracy. Consequently, many studies have tried to improve the accuracy of DEMs acquired from these free sources. Importantly, using the SRTM DEM is not recommended for an area that partly contains high-accuracy data. Thus, there is a need for a merging technique to produce a merged DEM of the whole area with improved accuracy. In recent years, advancements in geographic information systems (GIS) have improved data analysis by providing tools for applying merging techniques (like the minimum, maximum, last, first, mean, and blend (conventional methods)) to improve DEMs. In this article, DEM merging methods based on artificial neural network (ANN) and interpolation techniques are proposed. The methods are compared with other existing methods in commercial GIS software. The kriging, inverse distance weighted (IDW), and spline interpolation methods were considered for this investigation. The essential step for achieving the merging stage is the correction surface generation, which is used for modifying the SRTM DEM. Moreover, two cases were taken into consideration, i.e., the zeros border and the H border. The findings show that the proposed DEM merging methods (PDMMs) improved the accuracy of the SRTM DEM more than the conventional methods (CDMMs). The findings further show that the PDMMs of the H border achieved higher accuracy than the PDMMs of the zeros border, while kriging outperformed the other interpolation methods in both cases. The ANN outperformed all methods with the highest accuracy. Its improvements in the zeros and H border respectively reached 22.38% and 75.73% in elevation, 34.67% and 54.83% in the slope, and 40.28% and 52.22% in the aspect. Therefore, this approach would be cost-effective, especially in critical engineering projects.
Źródło:
Artificial Satellites. Journal of Planetary Geodesy; 2023, 58, 3; 122--170
2083-6104
Pojawia się w:
Artificial Satellites. Journal of Planetary Geodesy
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Estimation, Decoding and Forecasting in HMM and Hybrid HMM/ANN Models : a Case of Seismic Events in Poland
Autorzy:
Bijak, K.
Powiązania:
https://bibliotekanauki.pl/articles/92872.pdf
Data publikacji:
2006
Wydawca:
Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach
Tematy:
infrastructure subsystem
hybrid HMM/ANN model
neural networks
seismic events
Opis:
This paper compares performance of a hidden Markov model (HMM) and a hybrid HMM/ANN model in seismic events modeling. Observation variables are assumed to follow a Poisson distribution. Parameters of the discrete-time two-state models are estimated on the basis of data on seismic events that were recorded in Poland from 1991 to 1995. Then, on the basis of the estimation results, the most likely sequences of states of the hidden Markov chains are found and forecasts for January 1996 are made. It is shown that the hybrid model fits better to the data.
Źródło:
Studia Informatica : systems and information technology; 2006, 1(7); 7-17
1731-2264
Pojawia się w:
Studia Informatica : systems and information technology
Dostawca treści:
Biblioteka Nauki
Artykuł

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies