scholarly journals Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model

2019 ◽  
Vol 9 (12) ◽  
pp. 2562 ◽  
Author(s):  
Mohammad Javad Moradi ◽  
Mohammad Amin Hariri-Ardebili
Keyword(s):  
Neural Network ◽  
Numerical Models ◽  
Shear Walls ◽  
Experimental Tests ◽  
Experimental Models ◽  
Test Procedures ◽  
Meta Model ◽  
The Neural Network ◽  
The Right ◽  
Comprehensive Study

There is a large amount of useful information from past experimental tests, which are usually ignored in test-setup for the new ones. Variation of assumptions, materials, test procedures, and test objectives make it difficult to choose the right model for validation of the numerical models. Results from different experiments are sometimes in conflict with each other, or have minimum correlation. Furthermore, not all these information are easily accessible for researchers and engineers. Therefore, this paper presents the results of a comprehensive study on different experimental models for steel plate and reinforced concrete shear walls. A unique library of up to 13 parameters (mechanical properties and geometric characteristics) affecting the strength, stiffness and drift ratio of the shear walls are gathered including their sensitivity analysis. Next, a predictive meta-model is developed based on artificial neural network. It is capable of forecasting the responses for any desired shear wall with good accuracy. The proposed network can be used to as an alternative to the nonlinear numerical simulations or expensive experimental test.

Design of Neural Network Based on Rough Set

2012 ◽  
Vol 263-266 ◽  
pp. 3378-3381
Author(s):  
Xue Min Zhang ◽  
Zhen Dong Mu
Keyword(s):  
Neural Network ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Neural Network Classification ◽  
The Neural Network ◽  
Sample Test ◽  
Low Efficiency ◽  
The Right ◽  
Test Module

After years of development, the neural network classification, clustering and forecasting applications have a lot of development, but the neural network has the inevitable defects, if you enter the attribute set, the classification boundaries are not clear, convergence low efficiency and accuracy, there may even be the state does not converge, using rough set theory, the right value to modify the function to be modified, and joined the contradictions sample test module, after the use of EEG to verify reached the deletion of number of features and the purpose to improve the classification accuracy.

Estimating an Origin-Destination Table Under Repeated Counts of In-Out Volumes at Highway Ramps: Use of Artificial Neural Networks

2000 ◽  
Vol 1739 (1) ◽  
pp. 59-66 ◽  
Author(s):  
Shinya Kikuchi ◽  
Mitsuru Tanaka
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Traditional Method ◽  
Freeway Traffic ◽  
Hand Column ◽  
The Neural Network ◽  
Artificial Neural ◽  
Trip Production ◽  
The Right

A method is proposed that applies an artificial neural network model to estimate an origin-destination (O-D) matrix for a freeway network for which the data on inflow and outflow at the ramps are gathered regularly. This problem is the same as estimating the elements of an O-D table, given that many sets of data about the right-hand column total (trip production) and the bottom row total (trip attraction) are available. A neural network model is developed to emulate the stimulusresponse process on the freeway traffic, in which the stimulus is the inflow at the entrance ramps and the response the outflow at the exit ramps. After the neural network of a particular structure is trained by many sets of data (e.g., sets of daily volumes), the weights of the neural network are found to represent the ramp-to-ramp volume expressed in the proportion of the in-flow at the corresponding ramps. The model is applied to estimate a ramp-to-ramp O-D table for the Tokyo expressway network. The result is compared with the actual O-D table obtained from a survey. The model is found to be useful not only for estimating the O-D volume with much less data than for the traditional method, but also for verifying the existence of a pattern in the traffic flow.

scholarly journals Moisture Estimation in Cabinet Dryer with Thin-Layer Relationships Using Genetic Algorithm and Neural Network

2019 ◽  
Author(s):  
Behzad Maleki ◽  
Mahyar Ghazvini ◽  
Mohammad Hossein Ahmadi ◽  
Heydar Maddah ◽  
Shahab Shamshirband
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Thin Layer ◽  
Experimental Models ◽  
Moisture Loss ◽  
Squared Error ◽  
The Neural Network ◽  
Quality Product ◽  
Neural Network Structure ◽  
Moisture Estimation

Nowadays industrial dryers are used instead of traditional methods for drying. In designing dryers suitable for controlling the process of drying and reaching a high quality product, it is necessary to predict the instantaneous moisture loss during drying. For this purpose, ten mathematical-experimental models with a neural network model based on the kinetic data of pistachio drying are studied. The data obtained from the cabinet dryer will be evaluated at four temperatures of inlet air and different air velocities. The pistachio seeds will be placed in a thin layer on an aluminum sheet on a drying tray and weighed by a scale attached to the computer at different times. In the neural network, data are divided into three parts: educational (60%), validation (20%) and test (20%). Finally, the best mathematical-experimental model using genetic algorithm and the best neural network structure for predicting instantaneous moisture are selected based on the least squared error and the highest correlation coefficient.

scholarly journals KLASIFIKASI PEMINJAMAN NASABAH BANK MENGGUNAKAN METODE NEURAL NETWORK

2019 ◽  
Vol 15 (2) ◽  
pp. 163-170
Author(s):  
Nur Hadianto ◽  
Hafifah Bella Novitasari ◽  
Ami Rahmawati
Keyword(s):  
Neural Network ◽  
Roc Curve ◽  
Confusion Matrix ◽  
Total Income ◽  
Monthly Expenditure ◽  
The Neural Network ◽  
Average Education ◽  
Neural Network Algorithm ◽  
The Right ◽  
Very High

Payment of loans that experience difficulties in repayment or often called bad credit is a very detrimental thing for the bank, with the occurrence of bad credit the bank does not have the maximum ability to make money for investment. Choosing the right customer must go through the right analysis because the decision to approve or disagree with the loan is the main point that determines the possibility of bad credit. This study aims to classify eligible customers to obtain loans by taking into account existing parameters such as age, total income, number of families, monthly expenditure average, education level and others. This study uses a data mining classification method with a neural network model, to assess the accuracy of data processing using rapid miners then proceed with measurements using confusion matrix, ROC curve. The results of the neural network algorithm after going through confusion matrix testing, the ROC curve shows a very high accuracy value, and the dominant value of AUC and algorithm. The accuracy value is 98.24% with AUC of 0.979

scholarly journals Deep Learning Neural Network Algorithm for Computation of SPICE Transient Simulation of Nonlinear Time Dependent Circuits

Electronics ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 15
Author(s):  
David Černý ◽  
Josef Dobeš
Keyword(s):  
Neural Network ◽  
Truncation Error ◽  
Experimental Tests ◽  
Special Method ◽  
Electrical Circuits ◽  
Numerical Integrator ◽  
The Neural Network ◽  
Neural Network Algorithm ◽  
The Individual ◽  
Deep Learning Neural Network

In this paper, a special method based on the neural network is presented, which is conveniently used to precompute the steps of numerical integration. This method approximates the behaviour of the numerical integrator with respect to the local truncation error. In other words, it allows the precomputation of the individual steps in such a way that they do not need to be estimated by an algorithm but can be directly estimated by a neural network. Experimental tests were performed on a series of electrical circuits with different component parameters. The method was tested for two integration methods implemented in the simulation program SPICE (Trapez and Gear). For each type of circuit, a custom network was trained. Experimental simulations showed that for well-defined problems with a sufficiently trained network, the method allows in most cases reducing the total number of iteration steps performed by the algorithm during the simulation computation. Applications of this method, drawbacks, and possible further optimizations are also discussed.

scholarly journals The prediction of molecule atomization energy using neural network and extreme gradient boosting

2021 ◽  
Vol 2072 (1) ◽  
pp. 012005
Author(s):  
M Sumanto ◽  
M A Martoprawiro ◽  
A L Ivansyah
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Atomization Energy ◽  
Gradient Boosting ◽  
Intelligence System ◽  
The Neural Network ◽  
Extreme Gradient Boosting ◽  
Boosting Method ◽  
The Right ◽  
Parameter Values

Abstract Machine Learning is an artificial intelligence system, where the system has the ability to learn automatically from experience without being explicitly programmed. The learning process from Machine Learning starts from observing the data and then looking at the pattern of the data. The main purpose of this process is to make computers learn automatically. In this study, we will use Machine Learning to predict molecular atomization energy. From various methods in Machine Learning, we use two methods namely Neural Network and Extreme Gradient Boosting. Both methods have several parameters that must be adjusted so that the predicted value of the atomization energy of the molecule has the lowest possible error. We are trying to find the right parameter values for both methods. For the neural network method, it is quite difficult to find the right parameter value because it takes a long time to train the model of the neural network to find out whether the model is good or bad, while for the Extreme Gradient Boosting method the time needed to train the model is shorter, so it is quite easy to find the right parameter values for the model. This study also looked at the effects of the modification on the dataset with the output transformation of normalization and standardization then removing molecules containing Br atoms and changing the entry in the Coulomb matrix to 0 if the distance between atoms in the molecule exceeds 2 angstrom.

Prothesis Movements Pattern Recognition Based on Auto-Regressive Model and Wavelet Neural Network

2011 ◽  
Vol 121-126 ◽  
pp. 2156-2161 ◽  
Author(s):  
Cheng Gao ◽  
Jiao Ying Huang ◽  
Wei Guo
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Ar Model ◽  
Wavelet Neural Networks ◽  
Time Frequency ◽  
The Neural Network ◽  
Time Frequency Localization ◽  
Auto Regressive ◽  
The Right

Wavelet neural networks (WNN) combine the functions of time–frequency localization from the wavelet transform and of self-studying from the neural network, which make them particularly suitable for the classification of complex patterns. Based on auto-regressive (AR) model and WNN, pattern recognition of prothesis movements was studied in this paper. Firstly, an AR model was used to analysis the surface myoelectric signals (SMES) which recorded on the ulnar flexor carpi and extensor carpi region of the right hand in resting position. Four types of prosthesis movements are recognized by extracting four-order AR coefficient and construct them as eigenvector into WNN, which was used to study the correlation between SMES and wristwork. This paper compares the classification accuracy of four movements such as hand open (HO), hand close (HC), forearm intorsion (FI) and forearm extorsion (FE).The experimental results show that the proposed method can classify correctly for at least 93.75% of the test data.

Numerical Modelling of the Experimental Response of SRG Systems

2019 ◽  
Vol 817 ◽  
pp. 37-43
Author(s):  
Marialaura Malena ◽  
Marialuigia Sangirardi ◽  
Francesca Roscini ◽  
Gianmarco de Felice
Keyword(s):  
Numerical Modelling ◽  
Large Scale ◽  
Numerical Models ◽  
High Strength ◽  
Experimental Tests ◽  
Tensile Tests ◽  
Technical Committee ◽  
Structural Performance ◽  
Rilem Technical Committee ◽  
Test Procedures

Modern repairing and retrofitting methods for existing structures make use of composite materials, consisting of high strength textiles and a matrix, which can be either polymeric or inorganic. These kinds of techniques have been largely applied to masonry structures, since they significantly improve structural performance with a small increase of weight and a minimum invasiveness. However, the application of organic gluing agents on masonry has revealed some well-known drawbacks, which are almost all overcome resorting to inorganic matrixes, namely cement or lime mortars. An entire class of composites is thus identified as TRM (Textile Reinforced Mortars) or FRCM (Fibre Reinforced Cementitious Matrices). Among them, Steel Reinforced Grout (SRG) are characterized by Ultra High Tensile Strength Steel (UHTSS) cords embedded in mortar matrix and their use to improve the structural performance of existing historical masonry buildings is becoming more and more diffused. Qualification tests and acceptance criteria for SRG have just been defined. Nonetheless, numerical simulation of current available test procedures is mandatory to identify peculiar aspects of the response that at a following stage become an integral part of large scale models, when entire reinforced structures or portions need to be analysed. To this end, this work presents the numerical modelling of two different direct tensile tests on SRG systems: the Clamping-grip setup (RILEM Technical Committee 232-TDT 2016) and the Clevis-grip setup (ICC-ES AC434 2016). Numerical models able to replicate experimental tests and catch fundamental differences in their failure mechanisms are present

scholarly journals Prediction of Corrosion Inhibitor Efficiency of Some Aromatic Hydrazides and Schiff Bases Compounds by Using Artificial Neural Network

2009 ◽  
Vol 2 (1) ◽  
pp. 108-113
Author(s):  
Hanan A. Al-Hazam
Keyword(s):  
Neural Network ◽  
Corrosion Inhibitor ◽  
Molecular Orbital ◽  
Schiff Bases ◽  
Experimental Tests ◽  
Molecular Volume ◽  
Inhibitor Efficiency ◽  
The Neural Network ◽  
Artificial Neural ◽  
Neural Network Input

Artificial neural networks are used for evaluating the corrosion inhibitor efficiency of some aromatic hydrazides and Schiff bases compounds. The nodes of neural network input layer represent the quantum parameters, total negative charge (TNC) on molecule, energy of highest occupied molecular orbital (E Homo), energy of lowest unoccupied molecular orbital (E Lomo), dipole moment (μ), total energy (TE), molecular volume (V), dipolar-polarizability factor (Π) and inhibitor  concentration (C). The neural network output is the corrosion inhibitor efficiency (E) for the mentioned compounds. The training and testing of the developed network are based on a database of 31 published experimental tests obtained by weight loss. The neural network predictions for corrosion inhibitor efficiency are more reliable than prediction using other conventional theoretical methods such as AM1, PM3, Mindo, and Mindo-3. Key words: Neural network; Corrosion inhibitor efficiency. © 2010 JSR Publications. ISSN: 2070-0237 (Print); 2070-0245 (Online). All rights reservedDOI: 10.3329/jsr.v2i1.2757                 J. Sci. Res. 2 (1), 108-113  (2010) 

scholarly journals Global Ductility of Dual Steel Frames with Replaceable Dissipative Shear Walls

2015 ◽  
Vol 11 (3) ◽  
pp. 23-30
Author(s):  
Calin Neagu ◽  
Florea Dinu ◽  
Dan Dubina
Keyword(s):  
Numerical Models ◽  
Intervention Strategy ◽  
Steel Frames ◽  
Shear Walls ◽  
Experimental Tests ◽  
Response Spectra ◽  
Q Factor ◽  
Dynamic Analyses ◽  
Story Building ◽  
Numerical Program

Abstract The paper presents the results of a numerical program that was used to investigate the seismic performance of dual steel frames with dissipative shear walls. Nonlinear static and dynamic analyses were employed in order to evaluate the global ductility and the q factor for a twelve story building. The influence of the q factor on the estimated level of damage and post-earthquake intervention strategy was investigated. The dynamic analyses were conducted using two groups of accelerograms, selected to match the response spectra of two types of grounds. The numerical models were validated against experimental tests. The results show that q factor values adopted in design influence the level of damage. If re-centering capacity is properly controlled by design, the replacement of damaged walls can minimize the time and cost of intervention, thus supporting disaster resilience of buildings

Sign in / Sign up

Export Citation Format

Share Document