scholarly journals Potential of neural networks for maximum displacement predictions in railway beams on frictionally damped foundations

2021 ◽  
Author(s):  
Miguel Abambres ◽  
Rita Corrêa ◽  
AP Costa ◽  
F Simões
Keyword(s):  
Neural Networks ◽  
Computing Time ◽  
Maximum Error ◽  
Moving Loads ◽  
Maximum Displacement ◽  
Know How ◽  
Independent Variables ◽  
Data Points ◽  
Input Variables ◽  
Two Independent Variables

<p>Since the use of finite element (FE) simulations for the dynamic analysis of railway beams on frictionally damped foundations are (i) very time consuming, and (ii) require advanced know-how and software that go beyond the available resources of typical civil engineering firms, this paper aims to demonstrate the potential of Artificial Neural Networks (ANN) to effectively predict the maximum displacements and the critical velocity in railway beams under moving loads. Four ANN-based models are proposed, one per load velocity range ([50, 175] ∪ [250, 300] m/s; ]175, 250[ m/s) and per displacement type (upward or downward). Each model is function of two independent variables, a frictional parameter and the load velocity. Among all models and the 663 data points used, a maximum error of 5.4 % was obtained when comparing the ANN- and FE-based solutions. Whereas the latter involves an average computing time per data point of thousands of seconds, the former does not even need a millisecond. This study was an important step towards the development of more versatile (i.e., including other types of input variables) ANN-based models for the same type of problem. </p>

scholarly journals Potential of neural networks for maximum displacement predictions in railway beams on frictionally damped foundations

2019 ◽  
Author(s):  
Miguel Abambres ◽  
Rita Corrêa ◽  
António Pinto da Costa ◽  
Fernando Simões
Keyword(s):  
Neural Networks ◽  
Computing Time ◽  
Maximum Error ◽  
Moving Loads ◽  
Maximum Displacement ◽  
Know How ◽  
Independent Variables ◽  
Data Points ◽  
Input Variables ◽  
Two Independent Variables

Since the use of finite element (FE) simulations for the dynamic analysis of railway beams on frictionally damped foundations are (i) very time consuming, and (ii) require advanced know-how and software that go beyond the available resources of typical civil engineering firms, this paper aims to demonstrate the potential of Artificial Neural Networks (ANN) to effectively predict the maximum displacements and the critical velocity in railway beams under moving loads. Four ANN-based models are proposed, one per load velocity range ([50, 175] ∪ [250, 300] m/s; ]175, 250[ m/s) and per displacement type (upward or downward). Each model is function of two independent variables, a frictional parameter and the load velocity. Among all models and the 663 data points used, a maximum error of 5.4 % was obtained when comparing the ANN- and FE-based solutions. Whereas the latter involves an average computing time per data point of thousands of seconds, the former does not even need a millisecond. This study was an important step towards the development of more versatile (i.e., including other types of input variables) ANN-based models for the same type of problem.

scholarly journals Potential of neural networks for maximum displacement predictions in railway beams on frictionally damped foundations

2020 ◽  
Author(s):  
Abambres M ◽  
Rita Corrêa ◽  
AP Costa ◽  
F Simões
Keyword(s):  
Neural Networks ◽  
Computing Time ◽  
Maximum Error ◽  
Moving Loads ◽  
Maximum Displacement ◽  
Know How ◽  
Independent Variables ◽  
Data Points ◽  
Input Variables ◽  
Two Independent Variables

<p>Since the use of finite element (FE) simulations for the dynamic analysis of railway beams on frictionally damped foundations are (i) very time consuming, and (ii) require advanced know-how and software that go beyond the available resources of typical civil engineering firms, this paper aims to demonstrate the potential of Artificial Neural Networks (ANN) to effectively predict the maximum displacements and the critical velocity in railway beams under moving loads. Four ANN-based models are proposed, one per load velocity range ([50, 175] ∪ [250, 300] m/s; ]175, 250[ m/s) and per displacement type (upward or downward). Each model is function of two independent variables, a frictional parameter and the load velocity. Among all models and the 663 data points used, a maximum error of 5.4 % was obtained when comparing the ANN- and FE-based solutions. Whereas the latter involves an average computing time per data point of thousands of seconds, the former does not even need a millisecond. This study was an important step towards the development of more versatile (i.e., including other types of input variables) ANN-based models for the same type of problem. </p>

scholarly journals Potential of neural networks for maximum displacement predictions in railway beams on frictionally damped foundations

2019 ◽  
Vol 11 (2) ◽  
Author(s):  
Miguel Abambres ◽  
Rita Corrêa ◽  
António Pinto da Costa ◽  
Fernando Simões
Keyword(s):  
Neural Networks ◽  
Computing Time ◽  
Maximum Error ◽  
Moving Loads ◽  
Maximum Displacement ◽  
Know How ◽  
Independent Variables ◽  
Data Points ◽  
Input Variables ◽  
Two Independent Variables

Since the use of finite element (FE) simulations for the dynamic analysis of railway beams on frictionally damped foundations are (i) very time consuming, and (ii) require advanced know-how and software that go beyond the available resources of typical civil engineering firms, this paper aims to demonstrate the potential of Artificial Neural Networks (ANN) to effectively predict the maximum displacements and the critical velocity in railway beams under moving loads. Four ANN-based models are proposed, one per load velocity range ([50, 175] ∪ [250, 300] m/s; ]175, 250[ m/s) and per displacement type (upward or downward). Each model is function of two independent variables, a frictional parameter and the load velocity. Among all models and the 663 data points used, a maximum error of 5.4 % was obtained when comparing the ANN- and FE-based solutions. Whereas the latter involves an average computing time per data point of thousands of seconds, the former does not even need a millisecond. This study was an important step towards the development of more versatile (i.e., including other types of input variables) ANN-based models for the same type of problem.

scholarly journals Potential of neural networks for maximum displacement predictions in railway beams on frictionally damped foundations

2020 ◽  
Author(s):  
Abambres M ◽  
Rita Corrêa ◽  
AP Costa ◽  
F Simões
Keyword(s):  
Neural Networks ◽  
Computing Time ◽  
Maximum Error ◽  
Moving Loads ◽  
Maximum Displacement ◽  
Know How ◽  
Independent Variables ◽  
Data Points ◽  
Input Variables ◽  
Two Independent Variables

<p>Since the use of finite element (FE) simulations for the dynamic analysis of railway beams on frictionally damped foundations are (i) very time consuming, and (ii) require advanced know-how and software that go beyond the available resources of typical civil engineering firms, this paper aims to demonstrate the potential of Artificial Neural Networks (ANN) to effectively predict the maximum displacements and the critical velocity in railway beams under moving loads. Four ANN-based models are proposed, one per load velocity range ([50, 175] ∪ [250, 300] m/s; ]175, 250[ m/s) and per displacement type (upward or downward). Each model is function of two independent variables, a frictional parameter and the load velocity. Among all models and the 663 data points used, a maximum error of 5.4 % was obtained when comparing the ANN- and FE-based solutions. Whereas the latter involves an average computing time per data point of thousands of seconds, the former does not even need a millisecond. This study was an important step towards the development of more versatile (i.e., including other types of input variables) ANN-based models for the same type of problem. </p>

scholarly journals ESTIMATION OF EUCALYPTUS TREE HEIGHT IN CLONAL AND PROGENY TESTS USING ARTIFICIAL NEURAL NETWORKS

2018 ◽  
Vol 41 (6) ◽  
Author(s):  
Ana Carolina de Albuquerque Santos ◽  
Filipe Monteiro Almeida ◽  
Ramon Barreto Souza ◽  
Raul Chaves ◽  
Haroldo Nogueira de Paiva ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Age Groups ◽  
Tree Height ◽  
Two Samples ◽  
Data Points ◽  
Kolmogorov Smirnov ◽  
Progeny Tests ◽  
Artificial Neural ◽  
Input Variables

ABSTRACT The goal of this study was to test the applicability of artificial neural networks for estimating tree heights in clonal tests and progenies. We used data from 8,329 clonal tests collected for six age groups, divided into six blocks and five repetitions. For the progeny tests, we used 36,793 data points, collected at age 5 and divided into ten blocks and five repetitions. The categorical input variables considered were age, treatment, and block. The diameter (dap) was used with continuous input variables. For training the networks, we used two samples. Sub-sample 1 was composed of the first tree of each block. In sub-sample 2, the tree was selected randomly within each block. This selection was made in both tests. The selected data were separated, with 70% used for training and 30% used for validation. The other unselected trees were used for generalization. For each age and treatment, we used the Kolmogorov-Smirnov (KS) test to verify the normality of the errors. The results show that ANNs can be used to estimate the heights of trees subjected to various experimental plot treatments, with no loss of accuracy or estimation precision.

New generalized 2D Ostrowski type inequalities on time scales with k2 points using a parameter

Filomat ◽  
2018 ◽  
Vol 32 (9) ◽  
pp. 3155-3169 ◽  
Author(s):  
Seth Kermausuor ◽  
Eze Nwaeze
Keyword(s):  
Numerical Analysis ◽  
Time Scales ◽  
Type Inequality ◽  
Dimensional Case ◽  
Multiple Points ◽  
Quantum Calculus ◽  
Independent Variables ◽  
Ostrowski Type Inequality ◽  
Two Independent Variables

Recently, a new Ostrowski type inequality on time scales for k points was proved in [G. Xu, Z. B. Fang: A Generalization of Ostrowski type inequality on time scales with k points. Journal of Mathematical Inequalities (2017), 11(1):41-48]. In this article, we extend this result to the 2-dimensional case. Besides extension, our results also generalize the three main results of Meng and Feng in the paper [Generalized Ostrowski type inequalities for multiple points on time scales involving functions of two independent variables. Journal of Inequalities and Applications (2012), 2012:74]. In addition, we apply some of our theorems to the continuous, discrete, and quantum calculus to obtain more interesting results in this direction. We hope that results obtained in this paper would find their place in approximation and numerical analysis.

Explaining Peaceful Change in Central and Eastern Europe

2020 ◽  
Author(s):  
Alexander Tabachnik ◽  
Benjamin Miller
Keyword(s):  
Eastern Europe ◽  
Central And Eastern Europe ◽  
State Capacity ◽  
The State ◽  
National Identities ◽  
Great Power ◽  
Soviet System ◽  
The Balkans ◽  
Independent Variables ◽  
Two Independent Variables

This chapter explains the process of peaceful change in Central and Eastern Europe following the demise of the Soviet system. It also explains the failure of peaceful change in the Balkans and some post-Soviet countries, such as the Ukrainian conflict in 2014. The chapter accounts for the conditions for peaceful change and for the variation between peaceful and violent change by the state-to-nation theory. The two independent variables suggested by the theory are the level of state capacity and congruence—namely the compatibility between state borders and the national identities of the countries at stake. Moreover, according to the theory, great-power engagement serves as an intervening variable and in some conditions, as explained in the chapter, may help with peaceful change.

The Political Theory of Data: Institutions, Algorithms, & Formats in Racial Redlining

2021 ◽  
pp. 009059172110278
Author(s):  
Colin Koopman
Keyword(s):  
Political Theory ◽  
Recent Work ◽  
Academic Disciplines ◽  
The Political ◽  
Know How ◽  
Data Points ◽  
Emergent Literature

Despite widespread recognition of an emergent politics of data in our midst, we strikingly lack a political theory of data. We readily acknowledge the presence of data across our political lives, but we often do not know how to conceptualize the politics of all those data points—the forms of power they constitute and the kinds of political subjects they implicate. Recent work in numerous academic disciplines is evidence of the first steps toward a political theory of data. This article maps some limits of this emergent literature with an eye to enriching its theoretical range. The literature on data politics, both within political theory and elsewhere, has thus far focused almost exclusively on the algorithm. This article locates a further dimension of data politics in the work of formatting technology or, more simply, formats. Formats are simultaneously conceptual and technical in the ways they define what can even count as data, and by extension who can count as data and how they can count. A focus on formats is of theoretical value because it provides a bridge between work on the conceptual contours of categories and the technology-centric literature on algorithms that tends to ignore the more conceptual dimensions of data technology. The political insight enabled by format theory is shown in the context of an extended interrogation of the politics of racialized redlining.

scholarly journals Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Hongbin Ma ◽  
Shuyuan Yang ◽  
Guangjun He ◽  
Ruowu Wu ◽  
Xiaojun Hao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Points ◽  
Few Data
Sign in / Sign up

Export Citation Format

Share Document