scholarly journals Fluoride contamination - Artificial neural network modeling and inverse distance weighting approach

2012 ◽  
Vol 25 (2) ◽  
pp. 165-182 ◽  
Author(s):  
Imran Ahmad Dar ◽  
K. Sankar ◽  
Mithas Ahmad Dar ◽  
Mrinmoy Majumder
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Neural Network Modeling ◽  
Chemical Parameters ◽  
Underground Waters ◽  
Distance Weighting ◽  
Distance Weighted ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Inverse Distance

The underground waters in the Mamundiyar basin, India, present real chemical quality problems. Their fluoride content always exceeds the recommended levels. The Inverse Distance Weighted (IDW) method has been used for spatial interpolation of various key chemical parameters. Artificial Neural Network (ANN) modeling was applied to understand the correlation and sensitivity of all chemical parameters with respect to fluorides. The correlation of all the considered parameters is found to be poor where the highest correlation observed was only 0.37. This result showed that four of the parameters, namely pH, chlorides, sulphates and calcium, were found to have greater capacity of influencing fluorides than the other eight parameters. Chlorides were found to be the parameter that was the most sensitive and most correlated to fluorides.

Prediction of Cutting Temperatures by Using Back Propagation Neural Network Modeling when Cutting Hardened H-13 Steel in CNC End Milling

2012 ◽  
Vol 576 ◽  
pp. 91-94 ◽  
Author(s):  
Erry Yulian Triblas Adesta ◽  
Muataz H.F. Al Hazza ◽  
M.Y. Suprianto ◽  
Muhammad Riza
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
End Milling ◽  
Back Propagation ◽  
Cutting Temperature ◽  
Neural Network Modeling ◽  
Feed Forward Back Propagation ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Cnc End Milling

Machining of hardened steel at high cutting speeds produces high temperatures in the cutting zone, which affects the surface quality and cutting tool life. Thus, predicting the temperature in early stage becomes utmost importance. This research presents a neural network model for predicting the cutting temperature in the CNC end milling process. The Artificial Neural Network (ANN) was applied as an effective tool for modeling and predicting the cutting temperature. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the cutting temperature. The artificial neural network (ANN) was applied to predict the cutting temperature. Twenty hidden layer has been used with feed forward back propagation hierarchical neural networks were designed with Matlab2009b Neural Network Toolbox. The results show a high correlation between the predicted and the observed temperature which indicates the validity of the models.

scholarly journals Perancangan Sistem Pendukung Keputusan Untuk Prediksi Penerima Beasiswa Menggunakan Metode Neural Network Backpropagation

2018 ◽  
Vol 5 (2) ◽  
pp. 157 ◽  
Author(s):  
Ade Pujianto ◽  
Kusrini Kusrini ◽  
Andi Sunyoto
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Artificial Neural Network ◽  
Human Brain ◽  
Learning Rate ◽  
Neural Network Modeling ◽  
Complex Problems ◽  
Backpropagation Method ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

<p class="Judul21">Seleksi di Amikom masih mengalami kendala pada proses pengambilan keputusan, banyaknya data menyebabkan pengambil keputusan membutuhkan tools yang dapat membantu dalam menentukan penerima beasiswa, salah satu metode yang sering digunakan adalah artificial neural network (ANN). Metode ini meniru jaringan pemodelan saraf otak manusia berupa neuron-neuron untuk menyelesaikan suatu permasalahan. Salah satu penerapan neural network adalah untuk melakukan prediksi atau peramalan terhadap suatu peristiwa tertentu serta dianggap mampu menyelesaikan masalah yang komplek seperti penalaran otak manusia. Untuk menyelesaiakn masalah yang komplek neural network memerlukan banyak neuron atau yang biasa disebut layer (lapis). Salah satu metode neural network multi lapis adalah backpropagation yang mampu mengoptimalisasi bobot pada neuron dan menyelesaikan masalah yang komplek. Hasil dari penelitian ini adalah sebuah perancangan sistem prediksi dengan menggunakan metode neural network backpropagation untuk melakukan peramalan terhadap mahasiswa yang mendaftar beasiswa. hasil akhir penelitian ini adalah nilai akurasi sebesar 90% dan nilai error terkecil sebesar 0,000101 pada epoch ke 329 dengan jumlah 3000 data dengan pembagian data training 2.250 dan 750 data testing serta konfigurasi learning rate sebesar 0,2 dan momentum 0,2.</p><p class="Abstrak"> </p><p><strong>Kata kunci</strong>: <em>Artificial Neural netwok</em><em>, </em><em>Backpropagarion, </em><em>Prediksi, beasiswa, Pengambilan Keputusan.</em></p><p><em> </em></p><p class="Judul21"><em>Abstract</em></p><p class="Judul21"><em>Selection in Amikom is still constrained in the decision-making process, the number of data causing decision makers need tools that can assist in determining scholarship recipients, one of the most commonly used method is artificial neural network (ANN). This method mimics the neural network modeling of the human brain in the form of neurons to solve a problem. One application of neural network is to make predictions or forecasting of a particular event and is considered capable of solving complex problems such as human brain reasoning. To solve the problem the complex neural network requires many neurons or so-called layers. One method of multi layer neural network is backpropagation that is able to optimize the weight of neurons and solve complex problems. The result of this research is a prediction system design using neural network backpropagation method to forecast the students who apply for scholarship. the final result of this research is the accuracy value of 90% and the smallest error value of 0.000101 on epoch to 329 with the amount of 3000 data with sharing training 2,250 and 750 data testing and learning rate configuration of 0.2 and momentum 0.2.</em></p><p><strong>Keywords</strong>: <em>Artificial Neural Netwok, Backpropagarion, Prediction, Scholarship, Decision Making.</em></p>

scholarly journals Artificial Neural Network Modeling of MoS2 Supercapacitor for Predicative Synthesis

2019 ◽  
Vol 9 (2) ◽  
pp. 554-560
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Energy Storage ◽  
Neural Network Modeling ◽  
Ann Model ◽  
Energy Storage Devices ◽  
Storage Devices ◽  
Artificial Neural ◽  
Forward Calculation ◽  
Artificial Neural Network Ann

Energy storage systems are fundamental to the activity of intensity frameworks. They guarantee coherence of vitality supply and improve the dependability of the framework. The first area is centered on various energy storage frameworks, considering capacity limit, voltage and current proportions, and energy accessibility. Among the energy storage devices, supercapacitor is widely used because it is a high-limit capacitor with capacitance esteem a large amount than different capacitors. In the supercapacitor we have used MoS2 material synthesized with various Electrolytes. In perspective on the above mentioned, we report an Artificial Neural Network (ANN) strategy to achieve the predictable results. Levenberg- Marquardt feed-forward calculation prepares the neural network. We measure the exhibition of the ANN model with respect to mean square error (MSE) and the relationship coefficient between anticipated yield and yield given by the system. Results confirm the stability of supercapacitor over the other energy storage devices. To show such kind of conduct, we give Synthesis technique, Electrolyte, Cycle Life as an info esteems and Specific limit as yield esteem. For the amalgamation technique info esteem we have taken both compound and physical strategies by normalizing it. The practiced ANN demonstrating confirmations a higher number of concealed neuron design showing ideal execution as respects to expectation exactness

scholarly journals Photodegradation of roxarsone in the aquatic environment: influencing factors, mechanisms and artificial neural network modeling

2021 ◽  
Author(s):  
Jizhong Meng ◽  
Arong Arong ◽  
Shoujun Yuan ◽  
Wei Wang ◽  
Juliang Jin ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Influencing Factors ◽  
Aquatic Environment ◽  
Feed Additive ◽  
Neural Network Modeling ◽  
Factors Affecting ◽  
Indirect Photolysis ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Abstract Roxarsone (ROX) is an organoarsenic feed additive, and can be discharged into aquatic environment. ROX can photodegrade into more toxic inorganic arsenics, causing arsenic pollution. However, the photodegradation behavior of ROX in aquatic environment is still unclear. To better understand ROX photodegradation behavior, this study investigated the ROX photodegradation mechanism and influencing factors, and modeled the photodegradation process. The results showed that ROX in the aquatic environment was degraded to inorganic As(III) and As(V) under light irradiation. The degradation efficiency was enhanced by 25 % with the increase of light intensity from 300 µW/cm2 to 800 µW/cm2 via indirect photolysis. The photodegradation was temperature dependence, but was only slightly affected by pH. Nitrate ion (NO3−) had an obvious influence, but sulfate, carbonate, and chlorate ions had a negligible effect on ROX degradation. Dissolved organic matter (DOM) in the solution inhibited the photodegradation. ROX photodegradation was mainly mediated by reactive oxygen species (in the form of single oxygen 1O2) generated through ROX self-sensitization under irradiation. Based on the data of factors affecting ROX photodegradation, ROX photodegradation model was built and trained by an artificial neural network (ANN), and the predicted degradation rate was in good agreement with the real values with a root mean square error of 1.008. This study improved the understanding of ROX photodegradation behavior and provided a basis for controlling the pollution from ROX photodegradation.

scholarly journals Modeling of Hydrogen Production by Applying Biomass Gasification: Artificial Neural Network Modeling Approach

Fermentation ◽  
2021 ◽  
Vol 7 (2) ◽  
pp. 71
Author(s):  
Sahar Safarian ◽  
Seyed Mohammad Ebrahimi Saryazdi ◽  
Runar Unnthorsson ◽  
Christiaan Richter
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Comprehensive Evaluation ◽  
Biomass Gasification ◽  
Proximate Analysis ◽  
Neural Network Modeling ◽  
Operating Parameters ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In order to accurately anticipate the proficiency of downdraft biomass gasification linked with a water–gas shift unit to produce biohydrogen, a model based on an artificial neural network (ANN) approach is established to estimate the specific mass flow rate of the biohydrogen output of the plant based on different types of biomasses and diverse operating parameters. The factors considered as inputs to the models are elemental and proximate analysis compositions as well as the operating parameters. The model structure includes one layer for input, a hidden layer and output layer. One thousand eight hundred samples derived from the simulation of 50 various feedstocks in different operating situations were utilized to train the developed ANN model. The established ANN in the case of product biohydrogen presents satisfactory agreement with input data: absolute fraction of variance (R2) is more than 0.999 and root mean square error (RMSE) is lower than 0.25. In addition, the relative impact of biomass properties and operating parameters on output are studied. At the end, to have a comprehensive evaluation, variations of the inputs regarding hydrogen-content are compared and evaluated together. The results show that almost all of the inputs show a significant impact on the smhydrogen output. Significantly, gasifier temperature, SBR, moisture content and hydrogen have the highest impacts on the smhydrogen with contributions of 19.96, 17.18, 15.3 and 10.48%, respectively. In addition, other variables in feed properties, like C, O, S and N present a range of 1.28–8.6% and proximate components like VM, FC and A present a range of 3.14–7.67% of impact on smhydrogen.

scholarly journals ARTIFICIAL NEURAL NETWORK MODELING OF THE CONFORMABLE FRACTIONAL ISOTHERMAL GAS SPHERES

2021 ◽  
Vol 57 (1) ◽  
pp. 189-198
Author(s):  
Yosry A. Azzam ◽  
Emad A-B. Abdel-Salam ◽  
Mohamed I. Nouh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Modeling ◽  
Neural Network Modeling ◽  
Density Profiles ◽  
Emden Equation ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Isothermal Gas

The isothermal gas sphere is a particular type of Lane-Emden equation and is used widely to model many problems in astrophysics, like the formation of stars, star clusters and galaxies. In this paper, we present a computational scheme to simulate the conformable fractional isothermal gas sphere using an artificial neural network (ANN) technique, and we compare the obtained results with the analytical solution deduced using the Taylor series. We performed our calculations, trained the ANN, and tested it using a wide range of the fractional parameter. Besides the Emden functions, we calculated the mass-radius relations and the density profiles of the fractional isothermal gas spheres. The results obtained show that the ANN could perfectly simulate the conformable fractional isothermal gas spheres.

scholarly journals Introducing a Novel Digital Elevation Model Using Artificial Neural Network Algorithm

2020 ◽  
Vol 22 (2) ◽  
pp. 47-51
Author(s):  
Saeed Behzadi ◽  
Amin Jalilzadeh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
The Earth ◽  
Digital Elevation ◽  
Distance Weighting ◽  
Comprehensive Survey ◽  
Neural Network Algorithm ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Elevation Model

Elevation is a basic information of the earth, and different elevation models are provided to better understanding the earth and its different functions. However, it is not always possible to conduct a comprehensive survey in big areas and calculate all surface points. The best way is survey some points, then the elevation estimation is done using these points in each part of study area. The purpose of this paper is to use interpolation methods to estimate elevation. In such cases, different methods are used to interpolate and estimate points with an uncertain height. In this paper, the three usual methods are chosen and introduced then their performance are compared. These methods including: Inverse Distance Weighting (IDW), the Krige method or Kriging, and Artificial Neural Network (ANN). The results show that Artificial Intelligence with RMS = 5.9m is better in compare to Kriging with RMS = 7.2 and IDW with RMS = 9. The obtained result presents that in despite of its convenience, ANN provides DEMs with minimum errors.

Sign in / Sign up

Export Citation Format

Share Document