Loading...
Search for:
multilayer
0.008 seconds
Total 186 records
Node Representation Learning in Challenging Data Domains and Distributions
, Ph.D. Dissertation Sharif University of Technology ; Rabiee, Hamid Reza (Supervisor) ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
Graphs are powerful tools for modeling real-world data. Data analysis using graphs allows us to study the samples relations and identify rich patterns. Although graph modeling can result in a better understanding of data, it requires having strong methods. Graph neural network models have attracted more attention in recent years. These networks are able to simultaneously analyze data features and their relationships to each other and find node representation in low-dimensional feature space. However, due to the novelty of this field, many challenges are still unexplored.In this study, we intend to examine the challenges in this field by focusing on improving the representation of nodes with...
Developing a feed forward multilayer neural network model for prediction of CO2 solubility in blended aqueous amine solutions
, Article Journal of Natural Gas Science and Engineering ; Volume 21 , November , 2014 , Pages 19-25 ; ISSN: 18755100 ; Mazinani, S ; Davardoost, F ; Mokhtare, A ; Najibi, H ; Van der Bruggen, B ; Darvishmanesh, S ; Sharif University of Technology
Abstract
Absorption of carbon dioxide (CO2) in aqueous solutions can be improved by the addition of other compounds. However, this requires a large amount of equilibrium data for solubility estimation in a wide ranges of temperature, pressure and concentration. In this paper, a model based on an artificial neural network (ANN) was proposed and developed with mixtures containing monoethanolamine (MEA), diethanolamine (DEA), methyldiethanolamine (MDEA), 2-amino-2-methyl-1-propanol (AMP), methanol, triethanolamine (TEA), piperazine (PZ), diisopropanolamine (DIPA) and tetramethylensulfone (TMS) to predict solubility of CO2 in mixed aqueous solution (especially in binary and ternary mixtures) over wide...
A coupled wellbore-reservoir flowmodel for numerical pressure transient analysis in vertically heterogeneous reservoirs
, Article Journal of Porous Media ; Volume 16, Issue 5 , 2013 , Pages 395-400 ; 1091028X (ISSN) ; Soltanieh, M ; Farhadpour, F. A ; Sharif University of Technology
2013
Abstract
Pressure transient analysis in vertically heterogeneous reservoirs is examined. The inclusion of a separate model for the free fluid flow in the wellbore is essential to allow for hydraulic communication and mixing of the fluid issuing from different reservoir layers. A two-dimensional model coupling Darcy flow in the reservoir with Navier-Stokes flow in the wellbore is developed and solved by the finite element technique. The coupled wellbore-reservoir flow model is used to analyze a layered reservoir with an abrupt change in permeability and a thick formation showing a gradual change in permeability with depth. Contrary to conventional reservoir models, this new model is able to capture...
The prediction of permeability using an artificial neural network system
, Article Petroleum Science and Technology ; Volume 30, Issue 20 , 2012 , Pages 2108-2113 ; 10916466 (ISSN) ; Nikookar, M ; Dehnavi, M ; Al Anazi, B ; Sharif University of Technology
2012
Abstract
The authors studied the efficiency and accuracy of neural network model for prediction of permeability as a key parameter in reservoir characterization. So, some multilayer perceptron (MLP) neural network models with different learning algorithms of Levenberg-Margnardt, back propagation, improved back propagation (IBP), and quick propagation with three layers and different node numbers (3, 4, 5, 6, 7) in the middle layer have been presented. These models have been obtained by 630 permeability data from one of offshore reservoirs located in Saudi Arabia. The accuracy of models was studied by comparing the obtained results of each model with experimental data. So, the neural network with IBP...
High-quality integrated inductors based on multilayered meta-conductors
, Article IEEE Microwave and Wireless Components Letters ; Volume 22, Issue 7 , 2012 , Pages 345-347 ; 15311309 (ISSN) ; Schellevis, H ; Rejaei, B ; Fitch, R ; Zhuang, Y ; Sharif University of Technology
2012
Abstract
We demonstrate high-quality integrated inductors built from a multilayer of alternating copper and ferromagnetic films. The multilayer acts as a meta-conductor whose effective permeability becomes nearly zero at its ferromagnetic anti-resonance frequency. This leads to a suppression of the skin effect and a significant increase in the quality factor of the device. Experiments show an up to 86% increase in quality factor compared to conventional copper-based spiral inductors at high frequencies
Neural network prediction of mechanical properties of porous NiTi shape memory alloy
, Article Powder Metallurgy ; Volume 54, Issue 3 , Nov , 2011 , Pages 450-454 ; 00325899 (ISSN) ; Hafizpour, H. R ; Sadrnezhaad, S. K ; Akhondzadeh, A ; Abbasi Gharacheh, M ; Sharif University of Technology
2011
Abstract
A multilayer back propagation learning algorithm was used as an artificial neural network tool to predict the mechanical properties of porous NiTi shape memory alloys fabricated by press/sintering of the mixed powders. Effects of green porosity, sintering time and the ratio of the average Ti to Ni particle sizes on properties of the product were investigated. Hardness and tensile strength of the compacts were determined by hardness Rockwell B method and shear punch test. Three-fourths of 36 pairs of experimental data were used for training the network within the toolbox of the MATLAB software. Porosity, sintering time and particle size ratios were defined as the input variables of the model....
On the formation of SWCNTs and MWCNTs by arc-discharge in aqueous solutions: The role of iron charge and counter ions
, Article Fullerenes Nanotubes and Carbon Nanostructures ; Volume 19, Issue 4 , 2011 , Pages 317-328 ; 1536383X (ISSN) ; Shervin, S. H ; Simchi, A ; Sharif University of Technology
Abstract
Single-walled carbon nanotubes (SWCNTs) and multiwalled carbon nanotubes (MWCNTs) were synthesized in aqueous solutions containing FeCl2, FeCl3, FeSO4 and Fe2(SO4) 3. The effects of iron charge and the counter ions on the formation of carbon nanotubes (CNTs) were investigated. Thermogravimetric (TG) analysis indicated that carbon multilayer structures including CNTs and multishell graphite particles were formed in deionized (DI) water without the iron precursor. SWCNTs were also synthesized in the presence of the iron ions. It was also found that the mole ratio of [Fe2+]/[Fe3+] in the solution has a significant influence on the purity of CNTs and the process yield. The highest yield was...
Effect of electron irradiation on polypropylene films
, Article Plasma Science and Technology ; Volume 13, Issue 2 , 2011 , Pages 194-196 ; 10090630 (ISSN) ; Wiener, J ; Ghoranneviss, M ; Anvari, A ; Sharif University of Technology
Abstract
Effects of both electron beam irradiation on the properties of polypropylene (PP) films and the irradiation on the different layers of a multilayer PP film are studied. A Fourier transform infrared spectroscope was used to investigate the chemical structure of the films. The results showed that the chemical properties of the first layer were improved, that is, more functional groups responsible for dye ability and hydrophilicity of the film were produced on its surface, while noticeable improvement was not detected on the surface of other layers. This was also confirmed by testing the dye ability of the layers. However, the results obtained by atomic force microscopy showed that the electron...
Elimination of the effect of bottom-plate capacitors in C-2C DAC using a layout technique
, Article Microelectronics Journal ; Volume 46, Issue 12 , 2015 , Pages 1275-1282 ; 00262692 (ISSN) ; Sharifkhani, M ; Sharif University of Technology
Abstract
An efficient layout technique is proposed to eliminate the effect of the bottom-plate capacitors in a C-2C Digital to Analog Converter (DAC). Using this technique, the bottom-plate capacitors of 2C capacitors in the C-2C structure are placed in parallel with 1C capacitors. Then, the effect of the bottom plate capacitors is nulled by modifying the size of the main 1C capacitors. Hence, avoiding the complexity of calibration, this technique can preclude the effect of the bottom-plate to ground capacitance. Statistical simulations prove that the proposed technique is robust to non-ideal effects such as mismatch or parasitic capacitors. A 10-bit C-2C DAC is modeled in COMSOL Multiphysics using...
Optimized echo state networks for drought modeling based on satellite data
, Article International Journal of Innovative Computing, Information and Control ; Volume 11, Issue 3 , 2015 , Pages 1021-1031 ; 13494198 (ISSN) ; Mohammadinezhad, A ; Sharif University of Technology
IJICIC Editorial Office
2015
Abstract
Remotely sensed data obtained through satellite imaging is a useful tool for modeling environmental phenomena such as drought. In this manuscript, we apply optimized echo state networks to model and predict drought severity based on satellite images. To this end, a model is constructed in which the satellite-based vegetation index is fed as an input and drought severity index is obtained as output. We use a Kronecker-based approach to reduce the number of parameters of echo state networks to be optimized (i.e., the internal weights of reservoir). A number of evolutionary algorithms are used to optimize the parameters, of Differential Evolution results in the best performance as compared to...
Micro-optoelectromechanical systems accelerometer based on intensity modulation using a one-dimensional photonic crystal
, Article Applied Optics ; Volume 55, Issue 32 , 2016 , Pages 8993-8999 ; 1559128X (ISSN) ; Abedi, K ; Jafari, K ; Gholamzadeh, R ; Sharif University of Technology
OSA - The Optical Society
Abstract
In this paper, we propose what we believe is a novel sensitive micro-optoelectromechanical systems (MOEMS) accelerometer based on intensity modulation by using a one-dimensional photonic crystal. The optical sensing system of the proposed structure includes an air-dielectric multilayer photonic bandgap material, a laser diode (LD) light source, a typical photodiode (1550 nm) and a set of integrated optical waveguides. The proposed sensor provides several advantages, such as a relatively wide measurement range, good linearity in the whole measurement range, integration capability, negligible cross-axis sensitivity, high reliability, and low air-damping coefficient, which results in a wider...
Prediction of limiting activity coefficients for binary vapor-liquid equilibrium using neural networks
, Article Fluid Phase Equilibria ; Volume 433 , 2017 , Pages 174-183 ; 03783812 (ISSN) ; Bozorgmahry Boozarjomehry, R ; Sharif University of Technology
Elsevier B.V
2017
Abstract
The activity coefficient at infinite dilution is a representative of the limiting non-ideality of a solute in a mixture. Various methods for the prediction of infinite dilution activity coefficients (IDACs) have been developed. Artificial neural networks are powerful mapping tools for nonlinear function approximations. Accordingly, an artificial neural network model is proposed for the prediction of the IDACs of binary systems where the properties of the individual components are used as inputs to the network. The input parameters of the neural network are the mixture temperature, critical temperature, critical pressure, critical volume, molecular weight, dipole moment and the acentric...
Decoupled stability equation for buckling analysis of FG and multilayered cylindrical shells based on the first-order shear deformation theory
, Article Composites Part B: Engineering ; Volume 154 , 2018 , Pages 225-241 ; 13598368 (ISSN) ; Taati, E ; Asghari, M ; Sharif University of Technology
Elsevier Ltd
2018
Abstract
Based on the first-order shear deformation and Donnell's shell theory with von Karman non-linearity, one decoupled stability equation for buckling analysis of functionally graded (FG) and multilayered cylindrical shells with transversely isotropic layers subjected to various cases of combined thermo-mechanical loadings is developed. To this end, the equilibrium equations are uncoupled in terms of the transverse deflection, the force function and a new potential function. Using the adjacent equilibrium method, one decoupled stability equation which is an eighth-order differential equation in terms of transverse deflection is obtained and conveniently solved to present analytical expressions...
The impact of multilayered flux diverters on critical current in HTS transformer windings
, Article 27th Iranian Conference on Electrical Engineering, ICEE 2019, 30 April 2019 through 2 May 2019 ; 2019 , Pages 481-485 ; 9781728115085 (ISBN) ; Vakilian, M ; Hekmati, A ; Fardmanesh, M ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2019
Abstract
Growing interest in high-temperature superconducting (HTS) power devices is the result of commercial availability of the HTS tapes. One of the most promising applications of the HTS technology is HTS transformer. Flux diverters are used for critical current elevation in HTS transformer windings. In this paper multilayered flux diverter arrangements have been introduced to reduce weight and losses of conventional solid flux diverter arrangement. Horizontal and vertical multilayered arrangements have been investigated and compared with solid arrangement. Two dimensional (2D) finite element method (FEM) simulations have been used for comparison between different arrangements
Playing rock-paper-scissors with rasa: a case study on intention prediction in human-robot interactive games
, Article 11th International Conference on Social Robotics, ICSR 2019, 26 November 2019 through 29 November 2019 ; Volume 11876 LNAI , 2019 , Pages 347-357 ; 03029743 (ISSN); 9783030358877 (ISBN) ; Pour, A.G ; Siamy, A ; Taheri, A ; Meghdari, A ; Sharif University of Technology
Springer
2019
Abstract
Interaction quality improvement in a social robotic platform can be achieved through intention detection/prediction of the user. In this research, we tried to study the effect of intention prediction during a human-robot game scenario. We used our humanoid robotic platform, RASA. Rock-Paper-Scissors was chosen as our game scenario. In the first step, a Leap Motion sensor and a Multilayer Perceptron Neural Network is used to detect the hand gesture of the human-player. On the next level, in order to study the intention prediction’s effect on our human-robot gaming platform, we implemented two different playing strategies for RASA. One of the strategies was to play randomly, while the other...
Prediction of the pressure drop for CuO/(Ethylene glycol-water) nanofluid flows in the car radiator by means of Artificial Neural Networks analysis integrated with genetic algorithm
, Article Physica A: Statistical Mechanics and its Applications ; Volume 546 , 2020 ; Ghazvini, M ; Maddah, H ; Kahani, M ; Pourfarhang, S ; Pourfarhang, A ; Zeinali Herisg, S ; Sharif University of Technology
Elsevier B.V
2020
Abstract
In this investigation, neural networks were used to predict pressure drop of CuO-based nanofluid in a car radiator. For this purpose, the neural network with the multilayer perceptron structure was used to formulate a model for estimating the pressure drop In this way, different concentrations of copper oxide-based nanofluid were prepared. The base fluid was the mixture of ethylene glycol and pure water (60:40 wt%) which usually used as the cooling fluid in automotive industries. The prepared nanofluid samples were used in a car radiator and the pressure drop of nanofluid flows in the system at different Reynolds were measured. The main purpose of this study was developing the optimized...
Towards improving robustness of deep neural networks to adversarial perturbations
, Article IEEE Transactions on Multimedia ; Volume 22, Issue 7 , 2020 , Pages 1889-1903 ; Ghaemmaghami, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2020
Abstract
Deep neural networks have presented superlative performance in many machine learning based perception and recognition tasks, where they have even outperformed human precision in some applications. However, it has been found that human perception system is much more robust to adversarial perturbation, as compared to these artificial networks. It has been shown that a deep architecture with a lower Lipschitz constant can generalize better and tolerate higher level of adversarial perturbation. Smooth regularization has been proposed to control the Lipschitz constant of a deep architecture and in this work, we show how a deep convolutional neural network (CNN), based on non-smooth regularization...
Processing scintillation gamma-ray spectra by artificial neural network
, Article Journal of Radioanalytical and Nuclear Chemistry ; Volume 325, Issue 2 , 2020 , Pages 471-483 ; Vosoughi, N ; Saheli, F ; Sharif University of Technology
Springer Netherlands
2020
Abstract
Elemental analysis can be performed using obtained gamma-ray spectrum of the sample under study. In this work, simple Multi-Layer Perceptron (MLP) neural network models are proposed for analyzing a gamma-ray emitting sample using whole information of its obtained gamma-ray spectrum. Elemental analysis is performed in two fields of study using 3 × 3 inch NaI(Tl) detectors: Radio-Isotope Identification (RIID) and Prompt Gamma Neutron Activation Analysis (PGNAA). The gamma-ray point sources are used for an empirical study in RIID field, while a Monte Carlo simulation study is considered for determining chlorine and water content of crude oil using combination of PGNAA technique and a MLP model....
Numerical and analytical simulation of multilayer cellular scaffolds
, Article Journal of the Brazilian Society of Mechanical Sciences and Engineering ; Volume 42, Issue 5 , 2 May , 2020 ; Rahmati, S ; Nikkhoo, M ; Haghpanahi, M ; Akbari, J ; Sharif University of Technology
Springer
2020
Abstract
Due to the advent and maturity of the additive manufacturing technology, it is possible now to construct complex microstructures with unprecedented accuracy. In addition, to the influence of network unit cell types and porosities in recent years, researchers have studied the number of scaffold layers fabricated by additive manufacturing on mechanical properties. The objective of this paper is to assess the numerical and analytical simulations of the multilayer scaffolds. For this purpose, 54 different regular scaffolds with a unit cell composed of multilayer scaffolds were simulated under compressive loading and compared with the analytical relationships based on the Euler–Bernoulli and...
A novel adaptive tracking algorithm for maneuvering targets based on information fusion by neural network
, Article EUROCON 2007 - The International Conference on Computer as a Tool, Warsaw, 9 September 2007 through 12 September 2007 ; December , 2007 , Pages 818-822 ; 142440813X (ISBN); 9781424408139 (ISBN) ; Sadati, N ; Sharif University of Technology
2007
Abstract
The current statistical model and adaptive filtering (CSMAF) algorithm is one of the most effective methods for tracking the maneuvering targets. However, it is still worthy to investigate the characteristics of the CSMAF algorithm, which has a higher precision in tracking the maneuvering targets with larger accelerations while it has a lower precision in tracking the maneuvering targets with smaller acceleration. In this paper a novel adaptive tracking algorithm for maneuvering targets is proposed. To overcome the disadvantage of the CSMAF algorithm, a simple multi-layer feedforward neural network (NN) is used By introducing NN, two sources of information of the filter are fused while its...