scholarly journals Artificial Neural Network for Response Inference of a Nonvolatile Resistance-Switch Array

Micromachines ◽  
2019 ◽  
Vol 10 (4) ◽  
pp. 219 ◽  
Author(s):  
Guhyun Kim ◽  
Vladimir Kornijcuk ◽  
Dohun Kim ◽  
Inho Kim ◽  
Cheol Hwang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Applied Voltage ◽  
High Resistance State ◽  
Input Vector ◽  
Crossbar Array ◽  
Input And Output ◽  
Highly Nonlinear ◽  
Resistance State ◽  
Artificial Neural

An artificial neural network was utilized in the behavior inference of a random crossbar array (10 × 9 or 28 × 27 in size) of nonvolatile binary resistance-switches (in a high resistance state (HRS) or low resistance state (LRS)) in response to a randomly applied voltage array. The employed artificial neural network was a multilayer perceptron (MLP) with leaky rectified linear units. This MLP was trained with 500,000 or 1,000,000 examples. For each example, an input vector consisted of the distribution of resistance states (HRS or LRS) over a crossbar array plus an applied voltage array. That is, for a M × N array where voltages are applied to its M rows, the input vector was M × (N + 1) long. The calculated (correct) current array for each random crossbar array was used as data labels for supervised learning. This attempt was successful such that the correlation coefficient between inferred and correct currents reached 0.9995 for the larger crossbar array. This result highlights MLP that leverages its versatility to capture the quantitative linkage between input and output across the highly nonlinear crossbar array.

scholarly journals A Convex Combination Approach for Artificial Neural Network of Interval Data

2021 ◽  
Vol 11 (9) ◽  
pp. 3997
Author(s):  
Woraphon Yamaka ◽  
Rungrapee Phadkantha ◽  
Paravee Maneejuk
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Convex Combination ◽  
Reference Points ◽  
Combination Method ◽  
Suitable Alternative ◽  
Input And Output ◽  
Artificial Neural ◽  
Conventional Models ◽  
Interval Valued

As the conventional models for time series forecasting often use single-valued data (e.g., closing daily price data or the end of the day data), a large amount of information during the day is neglected. Traditionally, the fixed reference points from intervals, such as midpoints, ranges, and lower and upper bounds, are generally considered to build the models. However, as different datasets provide different information in intervals and may exhibit nonlinear behavior, conventional models cannot be effectively implemented and may not be guaranteed to provide accurate results. To address these problems, we propose the artificial neural network with convex combination (ANN-CC) model for interval-valued data. The convex combination method provides a flexible way to explore the best reference points from both input and output variables. These reference points were then used to build the nonlinear ANN model. Both simulation and real application studies are conducted to evaluate the accuracy of the proposed forecasting ANN-CC model. Our model was also compared with traditional linear regression forecasting (information-theoretic method, parametrized approach center and range) and conventional ANN models for interval-valued data prediction (regularized ANN-LU and ANN-Center). The simulation results show that the proposed ANN-CC model is a suitable alternative to interval-valued data forecasting because it provides the lowest forecasting error in both linear and nonlinear relationships between the input and output data. Furthermore, empirical results on two datasets also confirmed that the proposed ANN-CC model outperformed the conventional models.

Application of Artificial Neural Network Over Nickel-Based Catalyst for Combined Steam-Carbon Dioxide of Methane Reforming (CSDRM)

2020 ◽  
Vol 20 (9) ◽  
pp. 5716-5719 ◽  
Author(s):  
Cho Hwe Kim ◽  
Young Chul Kim
Keyword(s):  
Neural Network ◽  
Carbon Dioxide ◽  
Artificial Neural Network ◽  
Mean Squared Error ◽  
Coefficient Of Determination ◽  
Feed Ratio ◽  
Squared Error ◽  
Highly Nonlinear ◽  
Feed Forward Network ◽  
Artificial Neural

The application of artificial neural network (ANN) for modeling, combined steam-carbon dioxide reforming of methane over nickel-based catalysts, was investigated. The artificial neural network model consisted of a 3-layer feed forward network, with hyperbolic tangent function. The number of hidden neurons is optimized by minimization of mean square error and maximization of R2 (R square, coefficient of determination) and set of 8 neurons. With feed ratio, flow rate, and temperature as independent variables, methane, carbon dioxide conversion, and H2/CO ratio, were measured using artificial neural network. Coefficient of determination (R2) values of 0.9997, 0.9962, and 0.9985 obtained, and MAE (Mean Absolute Error), MSE (Mean Squared Error), RMSE (Root Mean Squared Error), and MAPE (Mean Absolute Percentage Error) showed low value. This study indicates ANN can successfully model a highly nonlinear process and function.

scholarly journals RUNOFF ESTIMATION IN URBAN CATCHMENT USING ARTIFICIAL NEURAL NETWORK MODELS

2020 ◽  
Vol 21 (Supplement 1) ◽  
Author(s):  
Baharak Motamedvaziri ◽  
Baharak Motamedvaziri ◽  
Baharak Motamedvaziri ◽  
Payam Najafi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Learning Algorithm ◽  
Input Vector ◽  
Physical Models ◽  
Accurate Estimation ◽  
Hydrological Process ◽  
Neural Network Models ◽  
Study Results ◽  
Artificial Neural

Many types of physical models have been developed for runoff estimation with successful results. However, accurate estimation of runoff remains a challenging problem owing to the lack of field data and the complexity of its hydrological process. In this paper, a machine learning method for runoff estimation is presented as an alternative approach to the physical model. Various types of input variables and artificial neural network (ANN) architectures were examined in this study. Results showed that a two-layer network with the tansig activation function and the Levenberg–Marquardt learning algorithm performed the best. For this architecture, the most effective input vector consists of a catchment perimeter, canal length, slope, runoff coefficient, and rainfall intensity. However, results of multivariate analysis of variance indicated the significant interaction effect of input data and the ANN architecture. Thus, to create a suitable ANN model for runoff estimation, a systematic determination of the input vector is necessary

scholarly journals Prediction of water discharge and sediment in teak forested area using artificial neural network model

2017 ◽  
Vol 6 (1) ◽  
pp. 73
Author(s):  
Nining Wahyuningrum
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Discharge ◽  
Ann Modeling ◽  
Highly Nonlinear ◽  
Condition Modeling ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Relationship Of ◽  
The Relationship

Information on the relationship of rainfall with discharge and sediment are required in watershed management.This relationship is known to be highly nonlinear and complex. Although discharge and sediment has been monitored continuously, but sometimes the information is not or less complete. In this condition, modeling is indispensable.The research objective is to create a model to predict the monthly direct runoff and sediment using Artificial Neural Network (ANN).The model was tested using rainfall data at t-3 and t-4 as input, and discharge and sediment at t+3 and t+4 as output. The data used is the data from 2001 to 2014. The results showed that of some models tested there are two models for the prediction of discharge and two models for sediment.The model was chosen because it has the smallest MSE, the largest R2 and satisfying K (0.5 to 0.65).Thus, these models can be used to predict discharge andsediment for a period of t+3 and t+4. Prediction of discharge of t+3 and t+4 may use Q t+3 = 0,64 Q t-3 + 0,05 and Q t+4 = 0,65 Q t-4 + 0,074 res pectively, while for predicting sediment of t+3 and t+4 may use equations QS t+3 = 0,45 QS t-3 + 0,052 and QS t+4 = 0,45 QS t-4 + 0,052. This ANN modeling can be applied to predict the flow and sediment in other locations with an architecture adapted to the conditions of available data.

The Research on Simulation Model in EDM of Insulating Ceramic Si3N4

2012 ◽  
Vol 538-541 ◽  
pp. 556-559 ◽  
Author(s):  
Xiao Bing Xu ◽  
Tian Kai Xiong ◽  
Li Jun Tan ◽  
Yi Zeng
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Simulation Model ◽  
Large Scale ◽  
Ceramic Materials ◽  
Back Propagation Algorithm ◽  
Processing Application ◽  
Highly Nonlinear ◽  
Artificial Neural ◽  
Low Efficiency

Insulating ceramic materials has been regarded as one of leading materials that promotes the industrial progress of the 21st century due to its unique electric and magnetic functions, and its special qualities such as high hardness, wear resistance, high temperature resistance and high pressure resistance also help a lot. Yet its modeling process is quite difficult. The traditional method is to grind it with a diamond after sintering into a certain shape. However, the low efficiency and the high cost certainly affect its widely application. Over the past 20 years, EDM has developed rapidly in ceramic material processing application, and EDM of conductive ceramic materials has become more and more practical. EDM is of the highly nonlinear characteristic, and it is quite difficult to use any specific mathematical expressions to describe its technological system, therefore, the developing trend of the researches in this field lies in the studies of its processing characters and its simulation techniques, of which, the artificial neural network, as a new technology, has provided an effective way for the further researches of EDM. It uses the computer to do a certain abstract, simplification and simulation of the functions of human brain, which can constitute a highly nonlinear large-scale continuous dynamic system. This paper employs the BP (Back Propagation) algorithm of the artificial neural network and makes the result of the orthogonal experiments on the processing technology effect as the learning samples of neural networks, thus establishes the simulation model of the multi-objective technology effect in EDM of insulating ceramic.

Sign in / Sign up

Export Citation Format

Share Document