A Sequential Method for the Development of Visual Interactive Meta-Simulation Models Using Neural Networks

2000 ◽  
Vol 51 (6) ◽  
pp. 712 ◽  
Author(s):  
R. D. Hurrion
Keyword(s):  
Neural Networks ◽  
Simulation Models ◽  
Sequential Method

scholarly journals Simulation of flood flow in a river system using artificial neural networks

2005 ◽  
Vol 9 (4) ◽  
pp. 313-321 ◽  
Author(s):  
R. R. Shrestha ◽  
S. Theobald ◽  
F. Nestmann
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Flow Simulation ◽  
Simulation Models ◽  
River System ◽  
Training Data ◽  
Data Sets ◽  
Network Training ◽  
Artificial Neural ◽  
Flood Flow

Abstract. Artificial neural networks (ANNs) provide a quick and flexible means of developing flood flow simulation models. An important criterion for the wider applicability of the ANNs is the ability to generalise the events outside the range of training data sets. With respect to flood flow simulation, the ability to extrapolate beyond the range of calibrated data sets is of crucial importance. This study explores methods for improving generalisation of the ANNs using three different flood events data sets from the Neckar River in Germany. An ANN-based model is formulated to simulate flows at certain locations in the river reach, based on the flows at upstream locations. Network training data sets consist of time series of flows from observation stations. Simulated flows from a one-dimensional hydrodynamic numerical model are integrated for network training and validation, at a river section where no measurements are available. Network structures with different activation functions are considered for improving generalisation. The training algorithm involved backpropagation with the Levenberg-Marquardt approximation. The ability of the trained networks to extrapolate is assessed using flow data beyond the range of the training data sets. The results of this study indicate that the ANN in a suitable configuration can extend forecasting capability to a certain extent beyond the range of calibrated data sets.

scholarly journals DEVELOPMENT OF REMOTE SENSING METHODS FOR NATURAL FIRE PREVENTION

2021 ◽  
pp. 149-161
Author(s):  
Almaz T. Gizatullin ◽  
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Simulation Models ◽  
Fire Spread ◽  
Simulation Modelling ◽  
Fire Danger ◽  
Fire Prevention ◽  
Natural Fire ◽  
The Subject ◽  
Remote Sensing Methods

The study deals with remote sensing methods for natural fire prevention, provides analysis and systematization on the subject. It traces the historical development and demonstrates the diversity of the methods. The main development stages and their characteristics were identified taking into account the increasing number of the sources and types of remote sensing and deepening knowledge of the subject. Fire interpretation includes fundamentally different processes of ignition and fire spread. The concepts of fire danger and its factors were introduced, the ways for their selection and application in the methods were analyzed. The source data for the methods were defined: satellite imagery of various resolutions (Landsat, Sentinel, MODIS/Terra-Aqua, AVHRR/NOAA, etc.), UAV images, lidar data, as well as technologies to process those. The study demonstrates that the most commonly used are traditional methods of geoinformation analysis, simulation modelling and neural networks. The methods were described, features of their implementation were identified. The description includes specific examples of fire danger assessment methods based on GIS, simulation models of fire spread, fire prevention methods based on neural networks and their application for territories of different spatial levels – global, regional and local.

scholarly journals Estimation of Uncertainty in the Lateral Vibration Attenuation of a Beam with Piezo-Elastic Supports by Neural Networks

2018 ◽  
Vol 885 ◽  
pp. 293-303
Author(s):  
Benedict Götz ◽  
Sebastian Kersting
Keyword(s):  
Neural Networks ◽  
Surrogate Model ◽  
Simulation Models ◽  
Feedforward Neural Networks ◽  
Piezoelectric Transducers ◽  
Density Estimate ◽  
Model Estimation ◽  
Lateral Vibration ◽  
Maximal Amplitude ◽  
Vibration Attenuation

Quantification of uncertainty in technical systems is often based on surrogate models of corresponding simulation models. Usually, the underlying simulation model does not describe the reality perfectly, and consequently the surrogate model will be imperfect.In this article we propose an improved surrogate model of the vibration attenuation of a beam with shunted piezoelectric transducers. Therefore, experimentally observed and simulated variations in the vibration attenuation are combined in the model estimation process, by using multi--layer feedforward neural networks. Based on this improved surrogate model, we construct a density estimate of the maximal amplitude in the vibration attenuation.The density estimate is used to analyze the uncertainty in the vibration attenuation, resulting from manufacturing variations.

scholarly journals Digital Model: Behavior Forecast in Transport Processes

2019 ◽  
Vol 17 (2) ◽  
pp. 6-14
Author(s):  
V. N. Gridin ◽  
V. V. Doenin ◽  
V. V. Panishchev ◽  
I. S. Razzhivaykin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Methodological Approach ◽  
Simulation Models ◽  
Transport Processes ◽  
Control Algorithms ◽  
Data Sets ◽  
Number Of Factors ◽  
Object Based ◽  
Source Data

In today’s world, many processes and events depend on forecasting. With development of mathematical models, an increasing number of factors influencing the final result of the forecast are taken into account, which in turn leads to the use of neural networks. But for training a neural network, source data sets are required, which are often not always sufficient or may not exist at all. The article describes a method of obtaining information as close to reality as possible. The proposed approach is to generate input data using simulation models of an object. The solution of a problem of generation of data sets and of training of a neural network is shown at the example of a typical marshalling railway station, and of a simulation of operations of a shunting hump. The considered examples confirmed the validity of the proposed methodological approach to generation of source data for neural networks using simulation models of a real object, based on a digital mathematical model, which makes it possible to obtain a simulation model of movement of transport objects, which is reliable in forecasting transport processes and creating relevant control algorithms.

scholarly journals NEURAL NETWORKS SURROGATE MODELS FOR SIMULATING PAYMENT RISK IN PAVEMENT CONSTRUCTION/NEURONINIŲ TINKLŲ PAKAITALO MODELIS MOKĖJIMO RIZIKAI KELIŲ STATYBOJE NUSTATYTI

2008 ◽  
Vol 14 (4) ◽  
pp. 235-240 ◽  
Author(s):  
Anshu Manik ◽  
Kasthurirangan Gopalakrishnan ◽  
Abhishek Singh ◽  
Shengquan Yan
Keyword(s):  
Neural Networks ◽  
Simulation Models ◽  
Detailed Examination ◽  
Surrogate Models ◽  
Average Error ◽  
Speed Up ◽  
Pavement Construction ◽  
To Receive ◽  
Highway Pavement

A common provision in quality control/quality assurance (QC/QA) highway pavement construction contracts is the adjustment of the pay that a contractor receives on the basis of the quality of the construction. It is important to both the contractor and the contracting agency to examine the amount of pay that the contractor can expect to receive for a given level of construction quality. Previous studies have shown that computer simulations can provide a better, more detailed examination of the pay schedule than is possible by simply determining the expected pay. In particular, the simulation process can provide an indication of the variability of pay at various quality levels and can identify the factors most responsible for pay adjustments. Stochastic simulation models are very useful in estimating and analyzing payment risk in highway pavement construction. However, such models are constrained by their computational requirements, and it is often necessary to couple them with simpler models to speed up the process of decision‐making. This paper investigates the use of Neural Networks (NN) to build surrogate models for a pavement construction payment‐risk prediction model. The results show that although the average error associated with the NN predictions are acceptable; in some particular cases the errors may be unacceptably high. Santrauka Bendroji sąlyga kokybės kontrolės užtikrinimo (QC/QA) kelių tiesimo sutartyse yra užmokesčio nustatymas. Jį rangovas gauna atsižvelgdamas į statybos kokybę. Svarbu rangovui ir agentūrai išnagrinėti užmokesčio kiekį, kurio rangovas gali tikėtis gauti už tam tikrą statybų kokybę. Ankstesni tyrimai parodė, kad pasitelkiant kompiuterinį modeliavimą galima gauti geresnį, daug išsamesnį apmokėjimo vaizdą. Tai galima padaryti paprasčiausiai nustatant tikėtiną užmokestį. Modeliavimo procesas rodo užmokesčio kitimą paisant kokybės ir gali pateikti veiksnius, nuo kurių priklauso kainos nustatymas. Tikimybinis modelis yra labai naudingas apskaičiuojant ir analizuojant užmokesčio riziką tiesiant kelių dangas. Tačiau tokie modeliai yra suvaržyti kompiuterinių reikalavimų, ir dažnai juos reikia susieti su paprastesniais modeliais norint greitinti sprendimų priėmimo procesą. Šiame straipsnyje tyrinėjamas neuroninių tinklų naudojimas pakeičiantiems modeliams sukurti norint teisingai nustatyti kelių dangos tiesimo užmokestį. Rezultatai parodė, kad vidutinė paklaida, susijusi su neuroninių tinklų spėjimu, yra priimtina, tačiau kai kuriais atvejais paklaidos gali būti neleistinai didelės.

scholarly journals Application of Neural Networks in the Problem of Quantitative Analysis of Air Composition

2020 ◽  
Vol 24 (1) ◽  
pp. 159-174
Author(s):  
O. G. Bondar ◽  
E. O. Brezhneva ◽  
R. E. Chernyshov
Keyword(s):  
Neural Networks ◽  
Mathematical Models ◽  
Gas Sensors ◽  
Environmental Parameters ◽  
Simulation Models ◽  
Training Data ◽  
Data Sets ◽  
Separate Determination ◽  
Gas Analyzer ◽  
Cross Sensitivity

Purpose of reseach is to develop a method for generating training data to enable the use of artificial neural networks (ANN) method in gas analyzer systems. The problem of increasing the accuracy of separate determination of gas concentrations in multicomponent mixtures under conditions of environmental parameters changes is considered. It is proposed to increase the accuracy of determining target gas concentrations by using the ANN method for joint processing of sensor signals.Methods: Training data for the neural network were generated using numerical experiments and mathematical simulation methods. To assess the accuracy of training, the standard deviation (SD) was used and the relative error was calculated. ANN training and research were conducted in the MATLAB environment (the Neural Networks Toolbox application). When developing mathematical models of gas sensors, the theory of electrical circuits, electronic theory of chemisorption and the adsorption theory of heterogeneous catalysis were applied.Results: A method for generating training data sets using mathematical models of gas sensors is described. The proposed training method has been tested on a specific task, in particular, a decision-making device based on ANN for a four-component gas analyzer has been developed. The efficiency of using neural networks for tuning out from the mutual cross-sensitivity of sensors was evaluated.Conclusion: A method for generating training data using simulation models is proposed, which allows automazing the process of training, research, choosing the architecture and structure of ANN and their testing. The method was tested. Based on the analysis of the obtained errors, conclusions are made about the efficiency of using neural networks to reduce errors caused by cross sensitivity at different concentrations of the main and interfering gases.

THE POSSIBILITIES OF CLUSTERING LEARNING METHODS IN STUDENT EDUCATION

2019 ◽  
Vol 5 ◽  
pp. 344
Author(s):  
Pēteris Grabusts
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Cluster Analysis ◽  
Fuzzy Logic ◽  
Artificial Neural Networks ◽  
Clustering Algorithms ◽  
Simulation Models ◽  
Clustering Methods ◽  
Learning Methods ◽  
Mining Methods

Many educational courses operate with models that were previously available only in mathematics or other learning disciplines. As a possible solution, there could be the use of package IBM SPSS Statistics and Modeler in realization of different algorithms for IT studies. Series of research were carried out in order to demonstrate the suitability of the IBM SPSS for the purpose of visualization of various simulation models of some data mining disciplines – particularly cluster analysis. Students are very interested in modern data mining methods, such as artificial neural networks, fuzzy logic and clustering. Clustering methods are often undeservedly forgotten, although the implementation of their algorithms is relatively simple and can be implemented even for students. In the research part of the study the modelling capabilities in data mining studies, clustering algorithms and real examples are demonstrated.

Sign in / Sign up

Export Citation Format

Share Document