Informacja

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

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "multilayer network" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 19
Tytuł:
Soft computing tools for virtual drug discovery
Autorzy:
Hagan, D.
Hagan, M.
Powiązania:
https://bibliotekanauki.pl/articles/91628.pdf
Data publikacji:
2018
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
drug discovery
virtual screening
multilayer network
SOM
Opis:
In this paper, we describe how several soft computing tools can be used to assist in high throughput screening of potential drug candidates. Individual small molecules (ligands) are assessed for their potential to bind to specific proteins (receptors). Committees of multilayer networks are used to classify protein-ligand complexes as good binders or bad binders, based on selected chemical descriptors. The novel aspects of this paper include the use of statistical analyses on the weights of single layer networks to select the appropriate descriptors, the use of Monte Carlo cross-validation to provide confidence measures of network performance (and also to identify problems in the data), the addition of new chemical descriptors to improve network accuracy, and the use of Self Organizing Maps to analyze the performance of the trained network and identify anomalies. We demonstrate the procedures on a large practical data set, and use them to discover a promising characteristic of the data. We also perform virtual screenings with the trained networks on a number of benchmark sets and analyze the results.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2018, 8, 3; 173-189
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Platforma do budowania sieci stwierdzeń
Environment for statement network design
Autorzy:
Cholewa, W.
Chrzanowski, P.
Rogala, T.
Amarowicz, M.
Powiązania:
https://bibliotekanauki.pl/articles/152694.pdf
Data publikacji:
2011
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
sieć stwierdzeń
wielowarstwowa sieć stwierdzeń
sieć Bayesa
model diagnostyczny
statement network
multilayer statement network
Bayes network
diagnostics model
Opis:
W niniejszym artykule przedstawiono wyniki badań związanych z zastosowaniem metod i technik sztucznej inteligencji w obszarze diagnostyki technicznej. Szczególną uwagę zwrócono na możliwość budowania systemów doradczych opartych na wielowarstwowych sieciach stwierdzeń. Przedstawiono ogólną koncepcję platformy do budowania sieci stwierdzeń. Nakreślono plan prac związanych z rozwojem platformy, który umożliwi stosowanie różnego typu sieci w ramach jednego modelu oraz integrację z innymi systemami.
This paper deals with the results of studies relevant to the methods and techniques of artificial intelligence in the field of technical diagnostics. At the beginning, the basic concepts, such as the statement and statement network, are described. Then, the concept of a multilayer statement network (Fig. 1) which is generalization of a single-layer statement network is presented. Special attention is paid to possibility of using the multilayer statement networks for development of multi-scale statement networks. Next, the general concept of a platform for development of the multilayer statement network and description of the main classes of objects resulting from using the platform are given. The choice of R environment for development of the platform is justified and its advantages are emphasized. The data exchange with other systems using XML format and the file structure is described. The process of construction of the multilayer statement network is discussed based on an example of the two-layer network shown in Fig. 2. The obtained results show the correctness of the platform operation. Finally, the main advantages of platforms, such as possibility of development of multilayer statement networks or commenting of the particular objects are discussed. The schedule of the development of platforms, including e.g. extension of the learning process of the network structure and tuning the network parameters basing on the available data sets or extension-training opportunities to construct multilayer network models with different types of networks on a different layers is also presented.
Źródło:
Pomiary Automatyka Kontrola; 2011, R. 57, nr 9, 9; 1079-1082
0032-4140
Pojawia się w:
Pomiary Automatyka Kontrola
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of Statistical Features and Multilayer Neural Network to Automatic Diagnosis of Arrhythmia by ECG Signals
Autorzy:
Slama, A. B.
Lentka, Ł.
Mouelhi, A.
Diouani, M. F.
Sayadi, M.
Smulko, J.
Powiązania:
https://bibliotekanauki.pl/articles/221289.pdf
Data publikacji:
2018
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
Multilayer Neural Network
arrhythmia diagnosis
ECG signal processing
Principal Component Analysis
Fisher’s Linear Discriminant
Opis:
Abnormal electrical activity of heart can produce a cardiac arrhythmia. The electrocardiogram (ECG) is a non-invasive technique which is used as a diagnostic tool for cardiac diseases. Non-stationarity and irregularity of heartbeat signal imposes many difficulties to clinicians (e.g., in the case of myocardial infarction arrhythmia). Fortunately, signal processing algorithms can expose hidden information within ECG signal contaminated by additive noise components. This paper explores a method of de-noising ECG signal by the discrete wavelet transform (DWT) and further detecting arrhythmia by estimated statistical parameters. Parameters of the de-noised ECG signals were used to form an input data vector determining whether the examined patient suffers from a cardiac arrhythmia or not. Input data were transformed using selected linear methods in order to reduce dimension of the input vector. A neural network was used to detect illness. Compared with the results of recent studies, the proposed method provides more accurate diagnosis based on the examined ECG signal data.
Źródło:
Metrology and Measurement Systems; 2018, 25, 1; 87-101
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Time - frequency method and artificial neural network classifier for induction motor drive system defects classification
Autorzy:
Behim, Meriem
Merabet, Leila
Saad, Salah
Powiązania:
https://bibliotekanauki.pl/articles/31341644.pdf
Data publikacji:
2024
Wydawca:
Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
Tematy:
energy
L-kurtosis
wavelet packet decomposition
multilayer perceptron neural network
induction motor defects
vibratory signals
Opis:
In this paper, by introducing two statistical parameters, energy and L-kurtosis, a new fault diagnostic system combining Wavelet Packet Decomposition and Multilayer Perceptron Neural Network is designed to improve efficiency and precision of induction motor defects diagnosis. This method is applied to vibratory signals of asynchronous motor running at two different rotational speeds (1500 rpm and 2000 rpm) at a sampling frequency of 8 KHz to detect three main types of defects: bearing faults, load imbalance and misalignment. These speeds are considered as the usual medium running speeds of induction motor. According to the results, the high performance and accuracy of this new faults diagnostic system is proved and confirmed, thus it can be used in the detection of other machines defects.
Źródło:
Diagnostyka; 2024, 25, 1; art. no. 2024110
1641-6414
2449-5220
Pojawia się w:
Diagnostyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Safety Analysis of Interdependent Critical Infrastructure Networks
Autorzy:
Blokus, A.
Dziula, P.
Powiązania:
https://bibliotekanauki.pl/articles/116995.pdf
Data publikacji:
2019
Wydawca:
Uniwersytet Morski w Gdyni. Wydział Nawigacyjny
Tematy:
critical infrastructure
safety analysis
interdependent critical infrastructure networks
critical infrastructure network
safety characteristics
random interdependency matrix
critical infrastructure system
multilayer infrastructure network framework
Opis:
Certain critical infrastructure networks show some interconnections, relations and interactions with other ones, most frequently when located and operating within particular areas. Failures arising within one critical infrastructure network, can then negatively impact not only on associated systems, societies and natural environment, but also on mutual critical infrastructure networks. Therefore, interdependent critical infrastructure networks can be determined as network of critical infrastructure networks (network of networks approach). The paper presents safety analysis of the network of critical infrastructure networks, taking into account interconnections, relations and interactions between particular ones. Critical infrastructures networks as multistate systems are considered, by distinguishing subsets of no-hazards safety states, and crisis situation states, and by analysing transitions between particular ones. Issues introduced in the article are based on the assumption that one key critical infrastructure network impacts on functioning of other critical infrastructure networks - can reduce their functionality and change level of their safety and inoperability, furthermore, other networks can impact each other, too. Safety characteristics of network of critical infrastructure networks: safety function, mean values and standard deviations of lifetimes in particular safety state subsets, are determined, taking into account interdependencies between particular networks. The results are related to various values of coefficients defining the significance of influence of interdependencies among networks.
Źródło:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation; 2019, 13, 4; 781-787
2083-6473
2083-6481
Pojawia się w:
TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of neural networks to detect eccentricity of induction motors
Autorzy:
Ewert, P.
Powiązania:
https://bibliotekanauki.pl/articles/1193467.pdf
Data publikacji:
2017
Wydawca:
Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Tematy:
neural network
general regression neural network
multilayer perceptron
eccentricity
induction motor
Opis:
The possibility of using neural networks to detect eccentricity of induction motors has been presented. A field-circuit model, which was used to generate a diagnostic pattern has been discussed. The formulas describing characteristic fault frequencies for static, dynamic and mixed eccentricity, occurring in the stator current spectrum, have been presented. Teaching and testing data for neural networks based on a preliminary analysis of diagnostic signals (phase currents) have been prepared. Two types of neural networks were discussed: general regression neural network (GRNN) and multilayer perceptron (MLP) neural network. This paper presents the results obtained for each type of the neural network. Developed neural detectors are characterized by high detection effectiveness of induction motor eccentricity.
Źródło:
Power Electronics and Drives; 2017, 2, 37/2; 151-165
2451-0262
2543-4292
Pojawia się w:
Power Electronics and Drives
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Evidence Based Diagnosis of Mesothelioma
Autorzy:
Malhotra, Isha
Tayal, Akash
Powiązania:
https://bibliotekanauki.pl/articles/1159560.pdf
Data publikacji:
2018
Wydawca:
Przedsiębiorstwo Wydawnictw Naukowych Darwin / Scientific Publishing House DARWIN
Tematy:
Artificial neural Network
Asbestos
Mesothelioma
Multilayer Perceptron
epochs
Opis:
The aim of this study is to extract the hidden patterns by using data mining and artificial intelligence techniques. The concept of artificial neural network depends on the idea that we can imitate the working of human brain by making the right links. Artificial Intelligence has always helped in many research areas including medical diagnosis. One of the basic methodologies for training and testing a network by utilizing medical information is discussed here. We have used SAS for analyzing our data and applying feed forward and back propagation mechanism for our diagnosis. The feed forward neural network with back propagation algorithm can be used to identify the diseased ones among different set of admitted individuals. In this paper, we have used multi-layer neural network to achieve the best performance with the minimum epoch (training iterations) and training time.
Źródło:
World Scientific News; 2018, 113; 117-129
2392-2192
Pojawia się w:
World Scientific News
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Forward and inverse kinematics solution of a robotic manipulator using a multilayer feedforward neural network
Autorzy:
Sharkawy, Abdel-Nasser
Powiązania:
https://bibliotekanauki.pl/articles/2201647.pdf
Data publikacji:
2022
Wydawca:
Politechnika Koszalińska. Wydawnictwo Uczelniane
Tematy:
multilayer neural network
feedforward neural network
forward kinematics
inverse kinematics
2-DOF planar robot
Levenberg-Marquardt algorithm
generated data
sieci neuronowe
sieci neuronowe jednokierunkowe
sieci neuronowe wielowarstwowe
kinematyka prosta
kinematyka odwrotna
algorytm Levenberga-Marquardta
generowanie danych
Opis:
In this paper, a multilayer feedforward neural network (MLFFNN) is proposed for solving the problem of the forward and inverse kinematics of a robotic manipulator. For the forward kinematics solution, two cases are presented. The first case is that one MLFFNN is designed and trained to find solely the position of the robot end-effector. In the second case, another MLFFNN is designed and trained to find both the position and the orientation of the robot end-effector. Both MLFFNNs are designed considering the joints’ positions as the inputs. For the inverse kinematics solution, a MLFFNN is designed and trained to find the joints’ positions considering the position and the orientation of the robot end-effector as the inputs. For training any of the proposed MLFFNNs, data is generated in MATLAB using two different cases. The first case is that data is generated assuming an incremental motion of the robot’s joints, whereas the second case is that data is obtained with a real robot considering a sinusoidal joint motion. The MLFFNN training is executed using the Levenberg-Marquardt algorithm. This method is designed to be used and generalized to any DOF manipulator, particularly more complex robots such as 6-DOF and 7-DOF robots. However, for simplicity, this is applied in this paper using a 2-DOF planar robot. The results show that the approximation error between the desired output and the estimated one by the MLFFNN is very low and it is approximately equal to zero. In other words, the MLFFNN is efficient enough to solve the problem of the forward and inverse kinematics, regardless of the joint motion type.
Źródło:
Journal of Mechanical and Energy Engineering; 2022, 6, 2; 1--17
2544-0780
2544-1671
Pojawia się w:
Journal of Mechanical and Energy Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Neural Network Model for Control of Operating Modes of Crushing and Grinding Complex
Autorzy:
Kalinchyk, Vasyl
Meita, Olexandr
Pobigaylo, Vitalii
Borychenko, Olena
Kalinchyk, Vitalii
Powiązania:
https://bibliotekanauki.pl/articles/2174915.pdf
Data publikacji:
2022
Wydawca:
Politechnika Koszalińska. Wydawnictwo Uczelniane
Tematy:
classification
modelling
neural network
radial basis function network
RBF
multilayer perceptron
MLP
Opis:
This article investigates the application of neural network models to create automated control systems for industrial processes. We reviewed and analysed works on dispatch control and evaluation of equipment operating modes and the use of artificial neural networks to solve problems of this type. It is shown that the main requirements for identification models are the accuracy of estimation and ease of algorithm implementation. It is shown that artificial neural networks meet the requirements for accuracy of classification problems, ease of execution and speed. We considered the structures of neural networks that can be used to recognise the modes of operation of technological equipment. Application of the model and structure of networks with radial basis functions and multilayer perceptrons for identifying the mode of operation of equipment under given conditions is substantiated. The input conditions for constructing neural network models of two types with a given three-layer structure are offered. The results of training neural models on the model of a multilayer perceptron and a network with radial basis functions are presented. The estimation and comparative analysis of models depending on model parameters are made. It is shown that networks with radial basis functions offer greater accuracy in solving identification problems. The structural scheme of the automated process control system with mode identification based on artificial neural networks is offered.
Źródło:
Rocznik Ochrona Środowiska; 2022, 24; 26--40
1506-218X
Pojawia się w:
Rocznik Ochrona Środowiska
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Solar air heater performance prediction using artificial neural network technique with relevant input variables
Autorzy:
Ghritlahre, Harish Kumar
Chandrakar, Purvi
Ahmad, Ashfaque
Powiązania:
https://bibliotekanauki.pl/articles/240435.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
artificial neural network
solar air heater
thermal performance
multilayer perceptron
Opis:
Solar air heater (SAH) is an important device for solar energy utilization which is used for space heating, crop drying, timber seasoning etc. Its performance mainly depends on system parameters, operating parameters and meteorological parameters. Many researchers have been used these parameters to predict the performance of SAH by analytical or conventional approach and artificial neural network (ANN) technique, but performance prediction of SAH by using relevant input parameters has not been done so far. Therefore, relevant input parameters have been considered in this study. Total ten parameters were used such as mass flow rate, ambient temperature, wind speed, relative humidity, fluid inlet temperature, fluid mean temperature, plate temperature, wind direction, solar elevation and solar intensity to find out the relevant parameters for ANN prediction. Seven different neural models have been constructed using these parameters. In each model 10 to 20 neurons have been selected to find out the optimal model. The optimal neural models for ANN-I, ANN-II, ANN-III, ANN-IV, ANN-V, ANN-VI and ANN-VII were obtained as 10-17-1, 8-14-1, 6-16-1, 5- 14-1, 4-17-1, 3-16-1 and 2-14-1, respectively. It has been found that ANN-II model with 8-14-1 is the optimal model as compared to other neural models. Values of the sum of squared errors, mean relative error, and coefficient of determination were found to be 0.02138, 1.82% and 0.99387, respectively, which shows that the ANN-II developed with mass flow rate, ambient temperature, inlet and mean temperature of air, plate temperature, wind speed and direction, relative humidity, and relevant input parameters performed better. The above results show that these eight parameters are relevant for prediction.
Źródło:
Archives of Thermodynamics; 2020, 41, 3; 255-282
1231-0956
2083-6023
Pojawia się w:
Archives of Thermodynamics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Forecasting the Energy Consumption of an Industrial Enterprise Based on the Neural Network Model
Autorzy:
Kalinchyk, Vasyl
Meita, Olexandr
Pobigaylo, Vitalii
Kalinchyk, Vitalii
Filyanin, Danylo
Powiązania:
https://bibliotekanauki.pl/articles/2069887.pdf
Data publikacji:
2021
Wydawca:
Politechnika Koszalińska. Wydawnictwo Uczelniane
Tematy:
electrical load
daily schedule
modelling
neural network
multilayer perceptron
MLP
Opis:
This research paper investigates the application of neural network models for forecasting in energy. The results of forecasting the weekly energy consumption of the enterprise according to the model of a multilayer perceptron at different values of neurons and training algorithms are given. The estimation and comparative analysis of models depending on model parameters is made.
Źródło:
Rocznik Ochrona Środowiska; 2021, 23; 484--492
1506-218X
Pojawia się w:
Rocznik Ochrona Środowiska
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Modeling and Forecasting of Monthly Global Price of Bananas Using Seasonal Arima And Multilayer Perceptron Neural Network
Modelowanie i prognozowanie miesięcznej globalnej ceny bananów z wykorzystaniem sezonowej ARIMA i wielowarstwowej sieci neuronowej perceptronowej
Autorzy:
Chi, Yeong Nain
Chi, Orson
Powiązania:
https://bibliotekanauki.pl/articles/1748958.pdf
Data publikacji:
2021
Wydawca:
Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
Tematy:
bananas
global price
time series
modeling
forecasting
seasonal ARIMA
multilayer perceptron neural network
banany
cena globalna
szeregi czasowe
modelowanie
prognozowanie
sezonowy model ARIMA
wielowarstwowa sieć neuronowa perceptronowa
Opis:
The primary purpose of this study was to pursue the analysis of the time series data and to demonstrate the role of time series model in the predicting process using long-term records of the monthly global price of bananas from January 1990 to November 2020. Following the Box-Jenkins methodology, ARIMA(4,1,2)(1,0,1)[12] with the drift model was selected to be the best fit model for the time series, according to the lowest AIC value in this study. Empirically, the results revealed that the MLP neural network model performed better compared to ARIMA(4,1,2)(1,0,1)[12] with the drift model at its smaller MSE value. Hence, the MLP neural network model can provide useful information important in the decision-making process related to the impact of the change of the future global price of bananas. Understanding the past global price of bananas is important for the analyses of current and future changes of global price of bananas. In order to sustain these observations, research programs utilizing the resulting data should be able to improve significantly our understanding and narrow projections of the future global price of bananas.
Podstawowym celem tego badania była analiza danych szeregów czasowych oraz wskazanie ważności modelu szeregów czasowych w procesie predykcji z wykorzystaniem długoterminowych zapisów miesięcznej ceny bananów na świecie od stycznia 1990 r. do listopada 2020 r. Zgodnie z metodologią Boxa-Jenkinsa wybrano jako najlepiej dopasowany dla szeregu czasowego model ARIMA(4,1,2)(1,0,1)[12] z dryfem, zgodnie z najniższą wartością AIC. Na podstawie wyników empirycznych stwierdzono, że model sieci neuronowej MLP działał lepiej w porównaniu z modelem ARIMA(4,1,2)(1,0,1)[12] z dryfem z mniejszą wartością MSE. Wynika z tego, że model sieci neuronowej MLP może dostarczyć użytecznych informacji, które są ważne w procesie decyzyjnym dotyczącym wpływu zmian przyszłej globalnej ceny bananów. Postrzeganie przeszłych światowych cen bananów jest ważne dla analiz zarówno bieżących, jak i przyszłych zmian światowych cen. Aby podtrzymać te obserwacje, programy badawcze wykorzystujące uzyskane dane powinny umożliwiać znaczne poprawianie wnioskowania i zawężać prognozy przyszłych światowych cen bananów.
Źródło:
Econometrics. Ekonometria. Advances in Applied Data Analytics; 2021, 25, 3; 21-41
1507-3866
Pojawia się w:
Econometrics. Ekonometria. Advances in Applied Data Analytics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Study of multi-layer flow in coextrusion processes
Issledovanie mnogoslojjnogo techenija v processakh coehkstruzii
Autorzy:
Levanichev, V.
Powiązania:
https://bibliotekanauki.pl/articles/792713.pdf
Data publikacji:
2014
Wydawca:
Komisja Motoryzacji i Energetyki Rolnictwa
Tematy:
coextrusion
multilayer structure
gravimetric control network
polymeric material
non-Newtonian liquid
physical model
Źródło:
Teka Komisji Motoryzacji i Energetyki Rolnictwa; 2014, 14, 1
1641-7739
Pojawia się w:
Teka Komisji Motoryzacji i Energetyki Rolnictwa
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Estimation of Suspended Sediment Load Using Artificial Neural Network in Khour Al Zubair Port, Iraq
Autorzy:
Hassan, Ayman A.
Ibrahim, Husham T.
Al-Aboodi, Ali H.
Powiązania:
https://bibliotekanauki.pl/articles/24201740.pdf
Data publikacji:
2023
Wydawca:
Polskie Towarzystwo Inżynierii Ekologicznej
Tematy:
suspended sediment concentration
multilayer perceptron
neural network
Khour Al-Zubair port
Basrah city
Opis:
The port of Khour Al-Zubair is located 60.0 km south of the city centre of Basrah; it is also located 105.0 kilometres from the northern tip of the Arabian Gulf. The main goal of this paper is to estimate the concentration of suspended deposit (SSC) in “Khour Al-Zubair” port using a Multilayer Perceptron Neural Network (MLP) based on hydraulic and local boundary parameters while also studying the effect of these parameters on estimating the SSC. Five input parameters (channel width, water depth, discharge, cross-section area, and flow velocity) are used for estimating SSC. Different input hydraulic and local boundary parameter combinations in the three sections (port center, port south, and port north) were used for creating nine models. The use of both hydraulic and local boundary parameters for SSC estimation is very important in the port area for estimating sediment loads without the need for field measurements, which require effort and time.
Źródło:
Journal of Ecological Engineering; 2023, 24, 6; 54--64
2299-8993
Pojawia się w:
Journal of Ecological Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Machine learning methods applied to sea level predictions in the upper part of a tidal estuary
Autorzy:
Guillou, N.
Chapalain, G.
Powiązania:
https://bibliotekanauki.pl/articles/2078822.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Instytut Oceanologii PAN
Tematy:
multiple regression model
artificial neural network
multilayer perceptron
regression function
machine learning algorithm
sea level
Opis:
Sea levels variations in the upper part of estuary are traditionally approached by relying on refined numerical simulations with high computational cost. As an alternative efficient and rapid solution, we assessed here the performances of two types of machine learning algorithms: (i) multiple regression methods based on linear and polynomial regression functions, and (ii) an artificial neural network, the multilayer perceptron. These algorithms were applied to three-year observations of sea levels maxima during high tides in the city of Landerneau, in the upper part of the Elorn estuary (western Brittany, France). Four input variables were considered in relation to tidal and coastal surge effects on sea level: the French tidal coefficient, the atmospheric pressure, the wind velocity and the river discharge. Whereas a part of these input variables derived from large-scale models with coarse spatial resolutions, the different algorithms showed good performances in this local environment, thus being able to capture sea level temporal variations at semi-diurnal and spring-neap time scales. Predictions improved furthermore the assessment of inundation events based so far on the exploitation of observations or numerical simulations in the downstream part of the estuary. Results obtained exhibited finally the weak influences of wind and river discharges on inundation events.
Źródło:
Oceanologia; 2021, 63, 4; 531-544
0078-3234
Pojawia się w:
Oceanologia
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 19

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