فهرس المقالات Radial Basis Function

• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  1 - حل عددی مسأله ریلی- استوکس کسری با استفاده از توابع پایه شعاعی مکان- زمان
  نفیسه نقره ای اصغر کرایه چیان علیرضا سهیلی
  در این مقاله، جواب مسأله دو بعدی ریلی- استوکس برای یک جریان گرمایی درجه دوم تعمیم یافته با مشتق کسری ‏‎را‎‏ تقریب می‌زنیم. ‏این تقریب بر پایه استفاده از توابع ‏پایه شعاعی (‏RBFs‏) مکان- زمان و روش انتگرال گیری عددی سینک می‌باشد. در این رو أکثر

  در این مقاله، جواب مسأله دو بعدی ریلی- استوکس برای یک جریان گرمایی درجه دوم تعمیم یافته با مشتق کسری ‏‎را‎‏ تقریب می‌زنیم. ‏این تقریب بر پایه استفاده از توابع ‏پایه شعاعی (‏RBFs‏) مکان- زمان و روش انتگرال گیری عددی سینک می‌باشد. در این روش، از تابع پایه ‏شعاعی گاوسین استفاده شده و بین متغیرهای زمان و مکان تمایز قائل نمی‌شویم و نقاط هم‌محلی‏، هم شامل مختصات ‏زمان و هم شامل مختصات ‏مکان هستند.‏ از روش انتگرال گیری عددی سینک با تبدیل نمایی یگانه برای تقریب قسمت انتگرالی مشتق کسری استفاده ‏‏می‌کنیم. ‏مشتق کسری، ریمان- لیوویل انتخاب شده است.روش ارائه شده روی دو مثال با مقادیر مختلف برای مرتبه مشتق کسری، پیاده سازی شده که نتایج حاصل، اثر بخشی روش را تأیید می‌کند ‏و نشان می‌دهد که با استفاده از تعداد کمی از نقاط هم‌محلی برای تابع پایه شعاعی می‌توان نتایج دقیقی بدست آورد‏.‏ لازم به ذکر است که تمامی ‏محاسبات با کمک نرم‎ ‎افزار متمتیکا انجام شده است.‏ تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  2 - DEA-neural network approach to solve binary classification problems
  Saeeid Kashanifar Mona Farahnak Roudsary
  10.30495/ijdea.2023.73639.1197
  In this paper, we propose a new hybrid neural network including Data Envelopment Analysis(DEA) and Radial Basis Function Network (RBFN)for binary classification problems. In the supervised learning phase of the neural network, the additive model is used to learn the cla أکثر

  In this paper, we propose a new hybrid neural network including Data Envelopment Analysis(DEA) and Radial Basis Function Network (RBFN)for binary classification problems. In the supervised learning phase of the neural network, the additive model is used to learn the classification function and Gaussian Radial Basis Function (GRBF) is used in the unsupervised learning phase of the neural network. Compared with the existing RBFN-DEA model for solving classification problems, the proposed model has low CPU time and can be applied to solve classification problems with negative data. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  3 - مدل‌سازی بار رسوب کل رودخانه‌ها با استفاده از شبکه‌های عصبی مصنوعی
  امین فلامکی مهناز اسکندری عبدالحسین بغلانی سید احمد احمدی
  برآورد بار رسوب کل رودخانه ها از مسائل مهم و کاربردی در مدیریت و برنامه ریزی منابع آب است. غلظت رسوب می تواند به روش های مستقیم و یا غیرمستقیم محاسبه شود که معمولاً روش های مستقیم پرهزینه و زمان بر هستند. همچنین بار رسوب کل می تواند به کمک روابط مختلف انتقال رسوب محاسبه أکثر

  برآورد بار رسوب کل رودخانه ها از مسائل مهم و کاربردی در مدیریت و برنامه ریزی منابع آب است. غلظت رسوب می تواند به روش های مستقیم و یا غیرمستقیم محاسبه شود که معمولاً روش های مستقیم پرهزینه و زمان بر هستند. همچنین بار رسوب کل می تواند به کمک روابط مختلف انتقال رسوب محاسبه شود، لیکن به طور معمول کاربرد این روابط نیاز به شرایط معینی داشته و به علاوه در بیشتر موارد نتایج حاصل از آن ها با یکدیگر و با مقادیر اندازه گیری شده متفاوت است. هدف از این پژوهش ارائه روشی بر پایه شبکه های عصبی مصنوعی (ANN) در تخمین بار رسوب کل بود. بدین منظور از دو نوع شبکه عصبی پرسپترون چند لایه (MLP) و توابع پایه شعاعی (RBF) و 200 نمونه، استفاده شد. 75 درصد از داده ها برای آموزش و 25 درصد برای آزمون شبکه ها در نظر گرفته شدند. متغیرهای ورودی مدل ها شامل سرعت متوسط جریان، شیب کف آبراهه، عمق متوسط، عرض آبراهه و قطر میانه ذرات رسوب و خروجی مدل، غلظت رسوب بود. متغیرهای ورودی مرحله به مرحله به شبکه ها اضافه شدند و هر بار نتایج ارزیابی شد تا مناسب ترین مدل تعیین شود. سپس نتایج حاصل از مدل های ANN با پنج معادله معروف انتقال رسوب مقایسه شدند. شاخص‌های آماری نشان داد که دقت شبکه های عصبی به ویژه مدل MLP در تخمین بار رسوب کل با ضریب همبستگی 96/0 بیش از سایر مدل هاست. همچنین مشخص شد که برای افزایش دقت مدل نیاز به آموزش آن با هر دو نوع داده های هیدرولوژیک و رسوب است. رابطه Ackersو White در برآورد مقدار بار رسوب کل بسیار بیش برآورد و سایر روابط، کم برآورد بودند. نتایج این پژوهش نشان داد که مدل های ارائه شده بر پایه شبکه های عصبی با مقادیر رسوب کل مشاهده شده هم خوانی بیشتری دارند و بویژه شبکه MLP می تواند مقدار رسوب را در نقاط پیک به خوبی برآورد نماید. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  4 - Numerical ‎S‎olution of Two-Dimensional Hyperbolic Equations with Nonlocal Integral Conditions Using Radial Basis Functions‎
  E. Shivanian M. Aslefallah
  This paper proposes a numerical method to the two-dimensional hyperbolic equations with nonlocal integral conditions. The nonlocal integral equation is of major challenge in the frame work of the numerical solutions of PDEs. The method benefits from collocation radial b أکثر

  This paper proposes a numerical method to the two-dimensional hyperbolic equations with nonlocal integral conditions. The nonlocal integral equation is of major challenge in the frame work of the numerical solutions of PDEs. The method benefits from collocation radial basis function method, the generalized thin plate splines radial basis functions are used.Therefore, it does not require any struggle to determine shape parameter (In other RBFs, it is time-consuming step). تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  5 - Numerical Simulation of 1D Linear Telegraph Equation With Variable Coefficients Using Meshless Local Radial Point Interpolation (‎MLRPI)
  E. Shivanian S. Abbasbandy A. Khodayari
  In the current work, we implement the meshless local radial point interpolation (MLRPI) method to find numerical solution of one-dimensional linear telegraph equations with variable coefficients. The MLRPI method, as a meshless technique, does not require any background أکثر

  In the current work, we implement the meshless local radial point interpolation (MLRPI) method to find numerical solution of one-dimensional linear telegraph equations with variable coefficients. The MLRPI method, as a meshless technique, does not require any background integration cells and all integrations are carried out locally over small quadrature domains of regular shapes, such as lines in one dimensions, circles or squares in two dimensions and spheres or cubes in three dimensions. Weak form formulation of the discretized equations has been constructed on local subdomains, hence the domain and boundary integrals in the weak form methods can easily be evaluated over the regularly shaped subdomains by some numerical quadratures. Radial basis functions augmented with monomials are used in to create shape functions. These shape functions have delta function property. Also the time derivatives is eliminated by using two-step finite differences approximation. Two illustrative numerical examples are given to show the stability and accuracy of the present method. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  6 - Construction of ‎P‎seudospectral Meshless Radial Point Interpolation for Sobolev Equation with Error Analysis‎
  S. Abbasbandy E. Shivanian
  10.30495/ijim.2022.19382
  In this study, we develop an approximate formulation for two-dimensional (2D) Sobolev equations based on pseudospectral meshless radial point interpolation (PSMRPI). The Sobolev equations which are arisen in the fluid flow penetrating rocks, soils, or different viscous أکثر

  In this study, we develop an approximate formulation for two-dimensional (2D) Sobolev equations based on pseudospectral meshless radial point interpolation (PSMRPI). The Sobolev equations which are arisen in the fluid flow penetrating rocks, soils, or different viscous media do not have an exact solution except in some special cases. The problem can be rigorously solved particularly when the geometry of the domain is more complex. In the PSMRPI method, the nodal points do not need to be regularly distributed and can even be quite arbitrary. It is easy to have high order derivatives of unknowns in terms of the values at nodal points by constructing operational matrices. It is proved that the method is convergent and unconditionally stable in some sense with respect to the time. The main results of the Sobolev equation are demonstrated by some examples to show the validity and trustworthiness of the PSMRPI technique. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  7 - Prediction of Residual Stresses by Radial Basis Neural Network in HSLA-65 Steel Weldments
  M. Heidari
  This paper investigates the residual stress fields in the vicinity of weld bead in HSLA-65 steel weldments using a neural network. This study consists of two cases: (i) the experimental analysis was carried out on the measurement of residual stresses by XRD technique. M أکثر

  This paper investigates the residual stress fields in the vicinity of weld bead in HSLA-65 steel weldments using a neural network. This study consists of two cases: (i) the experimental analysis was carried out on the measurement of residual stresses by XRD technique. Many different specimens that were subjected to different conditions were studied. The values and distributions of residual stresses occurring in welding of HSLA-65 plate under various conditions were determined. (ii) The mathematical modeling analysis has proposed the use of radial basis (RB) NN to determine the residual stresses based on the welding conditions. The input of RBNN are welding current, welding voltage, welding heat input, travel speed of welding, wire feed speed and distance from weld. The best fitting training data set was obtained with 18 neurons in the hidden layer, which made it possible to predict residual stresses with accuracy of at least as good as the experimental error, over the whole experimental range. After training, it was found that the regression values (R2) are 0.999664 and 0.999322 for newrbe and newrb functions respectively. Similarly, these values for testing data are 0.999425 and 0.998505, respectively. Based on the verification errors, it was shown that the radial basis function of neural network with newrbe function is superior in this particular case, and has the average error of 7.70% in predicting the residual stresses in HSLA-65. This method is conceptually straightforward, and it is also applicable to other type of welding for practical purposes. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  8 - Remote Sensing and Land Use Extraction for Kernel Functions Analysis by Support Vector Machines with ASTER Multispectral Imagery
  E. Akbari N. Amiri H. Azizi
  Land use is being considered as an element in determining land change studies, environmental planning and natural resource applications. The Earth’s surface Study by remote sensing has many benefits such as, continuous acquisition of data, broad regional coverage, أکثر

  Land use is being considered as an element in determining land change studies, environmental planning and natural resource applications. The Earth’s surface Study by remote sensing has many benefits such as, continuous acquisition of data, broad regional coverage, cost effective data, map accurate data, and large archives of historical data. To study land use / cover, remote sensing as an efficient technology, is always desired by experts. In this case, classification could be considered as one of the most important methods of extracting information from digital satellite images. Selecting the best classification method and applying the proper values for parameters extremely influence the trust level of extracted land use maps. This research is an applied study which attempts to introduce Support Vector Machines (SVM) classification method, a recent development from the machine learning community. Moreover, we prove its potential for structure–activity relationship analysis on Aster multispectral data of central county of Kabodar-Ahang region in Hamedan, Iran. Accuracy of SVMs method is varied by the type of kernel functions and its parameters. The purpose of this research is to find the accuracy of Land use extraction by SVM method by Polynomial and radial basis functions kernel with their estimated optimum parameters in addition to compare the results with Maximum Likelihood method. Most of the scientists imply that Maximum Likelihood method is suitable for classification. Therefore, we try to compare SVM with ML method and to deliberate the efficiency of this new method in classification progress on Aster multispectral data. The accuracy of SVM method by Polynomial and radial basis functions kernel with optimum parameters and ML classification methods achieved 93.18%, 91.77% and 88.35 % respectively as an overall accuracy. By comparing the accuracy of these methods, SVM method by Polynomial kernel was evaluated as suitable. Therefore, we can suggest using SVM method especially with the use of Polynomial kernel to determine land use. In general, the results of this research are very practical in natural resources conservation planning and studies. Also, this study verifies the effectiveness and robustness of SVMs in the classification of remotely sensed images. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  9 - Presenting a technique for identifying and diagnosing epileptic seizures using nonlinear feature extraction based on DT-CWT coefficients of brain EEG signals with a deep
  abdullah jafari chashmi
  Epilepsy is a type of brain disease that can be diagnosed by observing EEG signals. The disease often occurs in children. However, some cases are also seen in adults. Diagnosing this disease in the early stages is a challenging task for doctors. In this work, the author أکثر

  Epilepsy is a type of brain disease that can be diagnosed by observing EEG signals. The disease often occurs in children. However, some cases are also seen in adults. Diagnosing this disease in the early stages is a challenging task for doctors. In this work, the authors have classified epileptic and normal EEG signal by adopting deep learning approach. To achieve the efficient features, the dual tree complex wavelet (DTCWT) is considered. Then, the decomposed wavelet coefficients are applied to nonlinear feature extraction. These features are used as input to the Radial Hybrid Basis Function (RBF) class. Using the proposed method, about 99% classification accuracy is observed. This requires significant improvement of the proposed algorithm compared to other previously presented algorithms. It is the first time that nonlinear feature extraction on DT-CWT coefficients of an EEG signal is used to diagnose epilepsy. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  10 - Buckling of Doubly Clamped Nano-Actuators in General form Through Spectral Meshless Radial Point Interpolation (SMRPI)
  Hedayat Fatahi Elyas Shivanian S. J. Hosseini Ghoncheh
  10.22034/jna.2017.01.009
  The present paper is devoted to the development of a kind of spectral meshless radial point interpolation (SMRPI) technique in order to obtain a reliable approximate solution for buckling of nano-actuators subject to different nonlinear forces. To end this aim, a genera أکثر

  The present paper is devoted to the development of a kind of spectral meshless radial point interpolation (SMRPI) technique in order to obtain a reliable approximate solution for buckling of nano-actuators subject to different nonlinear forces. To end this aim, a general type of the governing equation for nano-actuators, containing integro-differential terms and nonlinear forces is considered. This general type for the nano-actuators is a non-linear fourth-order Fredholm integro-differential boundary value problem. The point interpolation method with the help of radial basis functions is used to construct shape functions which play as basis functions in the frame of SMRPI. In the current work, the thin plate splines (TPSs) are used as radial basis functions. This numerical based technique enables us to overcome all kind of nonlinearities in the mentioned boundary value problem and then to obtain fast convergent solution. Thus, it can facilitate the design of nano-actuators. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  11 - معرفی نمایه جدید به منظور تشخیص خودکار شدت پیشرفت بیماری آصم با استفاده از سیگنالهای کپنوگرام
  محسن کاظمی آیک هوتو
  در این مقاله یک نمایه جدید به منظور تشخیص خودکار شدت بیماری آصم با استفاده از پردازش سیگنالهای کپنوگرام ارائه شده است. تحقیقات انجام گرفته در گذشته نشان دهنده ارتباط مهمی بین کپنوگرام و بیماری آصم بوده است .هرچند، اغلب آن تحقیقات از روشهای پردازشی حوزه زمان اسفاده کرده أکثر

  در این مقاله یک نمایه جدید به منظور تشخیص خودکار شدت بیماری آصم با استفاده از پردازش سیگنالهای کپنوگرام ارائه شده است. تحقیقات انجام گرفته در گذشته نشان دهنده ارتباط مهمی بین کپنوگرام و بیماری آصم بوده است .هرچند، اغلب آن تحقیقات از روشهای پردازشی حوزه زمان اسفاده کرده بوده و بر این فرضیه استوار بودند که کپنوگرام یک سیگنال ایستان است. در این تحقیق با استفاده از ضرائب پیش بینی خطی (LPC) و روش مدلینگ اتورگرسیو (AR Modelling-Burg Method) سیگنالهای کپنوگرام مورد پردازش قرار گرفته‌اند. با استفاده از نتایج حاصل از این پردازش، تعداد شش ویژگی استخراج شده اند که با استفاده از روشهای آماری مانند ROC, توانایی‌های آنها برای تمایز بیماران آصمی از افراد سالم و همینطور قابلیت آنها برای تشخیص شدت بیماری آصم اثبات شده است. در ادامه با استفاده از به کار بردن این بردار ویژگی در یک شبکه عصبی GRBF, نمایه اشاره شده که همان خروچی این شبکه است، استخراج شده است. این نمایه یک عدد طبیعی بین 1 تا 10 می‌باشد (1 برای افراد سالم و10 نشان دهنده بیمار با شدت آصم ببسیار بالا) که متوسط تشخیص صحیح 90/15 % و خطای 9/85% را داراست. الگوریتم ارائه شده در این پژوهش بر آن دارد که روشی سریع و مقرون به صرفه برای کمک به متخصصان ارائه دهد، چراکه قادر است شدت بیماری آصم را به صورت سریع و خودکار رصد کند. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  12 - ارزیابی جریان راه اندازی موتورهای القایی با استفاده از شبکه عصبی
  ایمان صادق خانی علیرضا صدوقی
  موتورهای القایی به صورت گسترده‌ای در صنعت مورد استفاده قرا می‌گیرند. با این وجود در طول پروسه راه‌اندازی، جریان راه‌اندازی آنها آنچنان بزرگ است که می‌تواند به تجهیزات آسیب برساند. بنابراین این جریان بایستی با دقت تخمین زده شود. در این مقاله، از شبکه عصبی مصنوعی برای ارز أکثر

  موتورهای القایی به صورت گسترده‌ای در صنعت مورد استفاده قرا می‌گیرند. با این وجود در طول پروسه راه‌اندازی، جریان راه‌اندازی آنها آنچنان بزرگ است که می‌تواند به تجهیزات آسیب برساند. بنابراین این جریان بایستی با دقت تخمین زده شود. در این مقاله، از شبکه عصبی مصنوعی برای ارزیابی مقدار پیک جریان راه‌اندازی موتورهای القایی استفاده می‌شود. هر دو ساختار متداول پرسپترون چندلایه (MLP) و تابع پایه‌ای شعاعی (RBF)مورد بررسی قرار می‌گیرند. برای آموزش ساختار MLP از شش الگوریتم پس انتشار (BP)، دلتا-بار-دلتا (DBD)، دلتا-بار-دلتا توسعه‌یافته (EDBD)، جستجوی تصادفی جهت‌دار (DRS)، انتشار سریع (QP) و لونبرگ مارکواردت (LM) استفاده می‌شود. نتایج شبیه‌سازی نشان می‌دهند که هرچند اکثر شبکه‌های آموزش‌دیده قادر به تخمین مناسب مقدار پیک جریان راه‌اندازی هستند، اما الگوریتم‌هایLM و EDBD بهترین نتیجه را بر اساس میانگین خطای نسبی و مطلق ارائه می‌دهد. این روش می‌تواند به شرکت‌های سازنده و اپراتورها برای ارزیابی مقدار پیک جریان راه‌اندازی در مرحله طراحی و بهره‌برداری کمک کند تا بتوانند تدابیر لازم را برای عملکرد ایمن موتور فراهم نمایند. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  13 - Approximate solution of nonlinear fractional order model of HIV infection of CD4+T via Differential Quadrature Radial Basis Functions technique
  کوکب چلمبری حمیده ابراهیمی زینب آیاتی
  In this research, differential quadrature radial basis functions Method is performed to a fractional order model of HIV infection of CD4+T. Here, Caputo fractional derivative is used and it is approximated by forward finite difference method. Results have been compared أکثر

  In this research, differential quadrature radial basis functions Method is performed to a fractional order model of HIV infection of CD4+T. Here, Caputo fractional derivative is used and it is approximated by forward finite difference method. Results have been compared with the results of Laplace Adomian decomposition method (LADM), Laplace Adomian decomposition method-pade (LADM-pade), Runge-Kutta, Variational iteration method (VIM) and Variational iteration method-pade (VIM-Pade) for α_1=α_2=α_3 and residual functions have been plotted. And also approximate solutions of suggested method for different order of fractional derivatives have been shown. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  14 - Meshless RBF Method for Linear and Nonlinear Sobolev Equations
  مهران نعمتی محمود شفیعی حمیده ابراهیمی
  Radial Basis Functions are considered as important tools for scattered data interpolation. Collocation procedure is a powerful technique in meshless methods which is developed on the assumption of radial basis functions to solve partial differential equations in high di أکثر

  Radial Basis Functions are considered as important tools for scattered data interpolation. Collocation procedure is a powerful technique in meshless methods which is developed on the assumption of radial basis functions to solve partial differential equations in high dimensional domains having complex shapes. In this study, a numerical method, implementing the RBF collocation method and finite differences, is employed for solving not only 2-D linear, but also nonlinear Sobolev equations. First order finite differences and Crank-Nicolson method are applied to discretize the temporal part. Using the energy method, it is shown that the applied time-discrete approach is convergent in terms of time variable with order . The spatial parts are approximated by implementation of two-dimensional MQ-RBF interpolation resulting in a linear system of algebraic equations. By solving the linear system, approximate solutions are determined. The proposed scheme is verified by solving different problems and error norms and are computed. Computations accurately demonstrated the efficiency of the suggested method. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  15 - An Artificial Neural Network Method to Predict the COVID-19 Cases in Iran
  Meisam Shamsi رضا بابازاده Mohsen Varmazyar
  The sudden emergence of a Coronavirus and its rapid spread due to the globalization factors, especially the airline network, provoked the reaction of countries. Governments attempt to use all available means, including prediction methods, to control the spread of the Co أکثر

  The sudden emergence of a Coronavirus and its rapid spread due to the globalization factors, especially the airline network, provoked the reaction of countries. Governments attempt to use all available means, including prediction methods, to control the spread of the Coronavirus. In this article, we have developed various models based on artificial neural networks, including multi-layer perceptron, radial basis function, and adaptive-network-based fuzzy inference system with different learning algorithms, transfer functions, membership functions, hidden layers, hidden neurons, and kernels. We have identified five factors influencing the Coronavirus outbreak based on the Pearson correlation coefficient approach. These factors are gasoline consumption, internet pressure, number of wedding ceremonies, online transactions, and mask consumption. The accuracy of the developed models is identified by calculating three types of statistical errors, including root mean square error, mean absolute error, and mean absolute percentage error. The results show that the radial basis function model predicts the number of Covid-19 cases for the one month (mid-term) with an accuracy of over 97%. This study provides an efficient approach to predict the number of COVID-19 cases which help policymakers to make strategic decisions, including closing borders, designing supply chains for medical and health equipment, and enacting new laws. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  16 - Improved solution to nonlinear generalized Benjamin–Bona–Mahony–Burgers (GBBMB) equation by a meshless RBFs method
  مهران نعمتی سیده فائزه تیموری
  In this paper, based on the RBF collocation method and finite differences, a numerical method is proposed to solve nonlinear generalized Benjamin–Bona–Mahony–Burgers (GBBMB) equation. First order finite differences and Crank-Nicolson method are applied أکثر

  In this paper, based on the RBF collocation method and finite differences, a numerical method is proposed to solve nonlinear generalized Benjamin–Bona–Mahony–Burgers (GBBMB) equation. First order finite differences and Crank-Nicolson method are applied to discretize the temporal parts. The spatial parts are approximated by MQ-RBF interpolation which results in a linear system of algebraic equations. Approximate solutions are determined by solving such a system. The proposed scheme is verified by solving some test problems and computing error norms and . Results show the efficiency of the suggested method and the error has been improved. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  17 - On the use of back propagation and radial basis function neural networks in surface roughness prediction
  Angelos P. Markopoulos Sotirios Georgiopoulos Dimitrios E. Manolakos
  Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same pro أکثر

  Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, namely the adaptive back propagation algorithm of the steepest descent with the use of momentum term, the back propagation Levenberg–Marquardt algorithm and the back propagation Bayesian algorithm. Moreover, radial basis function neural networks are examined. All the aforementioned algorithms are used for the prediction of surface roughness in milling, trained with the same input parameters and output data so that they can be compared. The advantages and disadvantages, in terms of the quality of the results, computational cost and time are identified. An algorithm for the selection of the spread constant is applied and tests are performed for the determination of the neural network with the best performance. The finally selected neural networks can satisfactorily predict the quality of the manufacturing process performed, through simulation and input–output surfaces for combinations of the input data, which correspond to milling cutting conditions. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  18 - Entropy-based Kernel Graph Cut with Weighted K-Means for Textural Image Region Segmentation
  Mehrnaz Niazi Kambiz Rahbar Mansour Sheikhan Maryam Khademi
  Recently, image segmentation based on graph cut methods has shown impressive performance on a set of image data. Although the kernel graph cut method provides good performance, its performance is highly dependent on the data mapping to the transformation space and image أکثر

  Recently, image segmentation based on graph cut methods has shown impressive performance on a set of image data. Although the kernel graph cut method provides good performance, its performance is highly dependent on the data mapping to the transformation space and image features. Entropy-based kernel graph cut method is suitable for segmentation of textured images. However, the quality of its segmentation is affected by the quality of extracting kernel centers. This paper examines the segmentation of textured images using the entropy-based kernel graph cut method based on weighted k-means. Using the advantages of kernel space, the objective function consists of two data terms to transfer the data standard deviation of each area in the segmented image and the regularization term. The proposed method, while using the advantages of suitable computational load of graph cut methods, will be a suitable alternative for segmenting textured images. Laboratory results have been taken on a set of well-known datasets that include textured shapes in order to evaluate the efficiency of the algorithm compared to other states-of-the-art methods in the field of kernel graph cut. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  19 - Hourly Wind Speed Prediction using ARMA Model and Artificial Neural Networks
  Farzaneh Tatari Majid Mazouchi
  In this paper, a comparison study is presented on artificial intelligence and time series models in 1-hour-ahead wind speed forecasting. Three types of typical neural networks, namely adaptive linear element, multilayer perceptrons, and radial basis function, and ARMA t أکثر

  In this paper, a comparison study is presented on artificial intelligence and time series models in 1-hour-ahead wind speed forecasting. Three types of typical neural networks, namely adaptive linear element, multilayer perceptrons, and radial basis function, and ARMA time series model are investigated. The wind speed data used are the hourly mean wind speed data collected at Binalood site in Iran. Simulation results indicate the ability of the proposed methods in 1-hour-ahead wind speed forecasting in Binalood of Iran. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  20 - A numerical solution of mixed Volterra Fredholm integral equations of Urysohn type on non-rectangular regions using meshless methods
  M. Nili Ahmadabadi H. Laeli Dastjerdi
  In this paper, we propose a new numerical method for solution of Urysohn two dimensional mixed Volterra-Fredholm integral equations of the second kind on a non-rectangular domain. The method approximates the solution by the discrete collocation method based on inverse m أکثر

  In this paper, we propose a new numerical method for solution of Urysohn two dimensional mixed Volterra-Fredholm integral equations of the second kind on a non-rectangular domain. The method approximates the solution by the discrete collocation method based on inverse multiquadric radialbasis functions (RBFs) constructed on a set of disordered data. The method is a meshless method, because it is independent of the geometry of the domain and it does not require any background interpolation or approximation cells. The error analysisof the method is provided. Numerical results are presented, which confirm the theoretical prediction of the convergence behavior of the proposed method. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  21 - The method of radial basis functions for the solution of nonlinear Fredholm integral equations system.
  J. Nazari M. Nili Ahmadabadi H. Almasieh
  In this paper, An effective and simple numerical method is proposed for solving systems of integral equations using radial basis functions (RBFs). We present an algorithm based on interpolation by radial basis functions including multiquadratics (MQs), using Legendre-Ga أکثر

  In this paper, An effective and simple numerical method is proposed for solving systems of integral equations using radial basis functions (RBFs). We present an algorithm based on interpolation by radial basis functions including multiquadratics (MQs), using Legendre-Gauss-Lobatto nodes and weights. Also a theorem is proved for convergence of the algorithm. Some numerical examples are presented and results are compared to the analytical solution and Triangular functions (TF), Delta basis functions (DFs), block-pulse functions , sinc fucntions, Adomian decomposition, computational, Haar wavelet and direct methods to demonstrate the validity and applicability of the proposed method. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  22 - An efficient method for the numerical solution of functional integral equations
  M. Nili Ahmadabadi
  We propose an efficient mesh-less method for functional integral equations. Its convergence analysis has been provided. It is tested via a few numerical experiments which show the efficiency and applicability of the proposed method. Attractive numerical results have bee أکثر

  We propose an efficient mesh-less method for functional integral equations. Its convergence analysis has been provided. It is tested via a few numerical experiments which show the efficiency and applicability of the proposed method. Attractive numerical results have been obtained. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  23 - Numerical Solution of Nonlinear PDEs by Using Two-Level Iterative Techniques and Radial Basis Functions
  Sara Hosseini
  ‎Radial basis function method has been used to handle linear and‎ ‎nonlinear equations‎. ‎The purpose of this paper is to introduce the method of RBF to‎ ‎an existing method in solving nonlinear two-level iterative‎ ‎techniques and al أکثر

  ‎Radial basis function method has been used to handle linear and‎ ‎nonlinear equations‎. ‎The purpose of this paper is to introduce the method of RBF to‎ ‎an existing method in solving nonlinear two-level iterative‎ ‎techniques and also the method is implemented to four numerical‎ ‎examples‎. ‎The results reveal that the technique is very effective‎ ‎and simple. The main property of the method lies in its‎ ‎flexibility and ability to solve nonlinear equations accurately‎ ‎and conveniently. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  24 - Numerical Solution of The First-Order Evolution Equations by Radial Basis Function
  Sara Hosseini
  ‎In this work‎, ‎we consider the nonlinear first-order evolution‎ ‎equations‎: ‎$u_t=f(x,t,u,u_x,u_{xx})$ for $0<t<\infty$‎, ‎subject‎ ‎to initial condition $u(x,0)=g(x)$‎, ‎where $u$ is a function of‎ ‎$ أکثر

  ‎In this work‎, ‎we consider the nonlinear first-order evolution‎ ‎equations‎: ‎$u_t=f(x,t,u,u_x,u_{xx})$ for $0<t<\infty$‎, ‎subject‎ ‎to initial condition $u(x,0)=g(x)$‎, ‎where $u$ is a function of‎ ‎$x$ and $t$ and $f$ is a known analytic function‎. ‎The purpose of‎ ‎this paper is to introduce the method of RBF to existing method‎ ‎in solving nonlinear first-order evolution equations and also the‎ ‎method is implemented in four numerical examples‎. ‎The results‎ ‎reveal that the technique is very effective and simple. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  25 - Using Chebyshev polynomial’s zeros as point grid for numerical solution of nonlinear PDEs by differential quadrature- based radial basis functions
  Majid Erfanian Sajad Kosari
  Radial Basis Functions (RBFs) have been found to be widely successful for the interpolation of scattered data over the last several decades. The numerical solution of nonlinear Partial Differential Equations (PDEs) plays a prominent role in numerical weather forecasting أکثر

  Radial Basis Functions (RBFs) have been found to be widely successful for the interpolation of scattered data over the last several decades. The numerical solution of nonlinear Partial Differential Equations (PDEs) plays a prominent role in numerical weather forecasting, and many other areas of physics, engineering, and biology. In this paper, Differential Quadrature (DQ) method- based RBFs are applied to find the numerical solution of the linear and nonlinear PDEs. The multiquadric (MQ) RBFs as basis function will introduce and applied to discretize PDEs. Differential quadrature will introduce briefly and then we obtain the numerical solution of the PDEs. DQ is a numerical method for approximate and discretized partial derivatives of solution function. The key idea in DQ method is that any derivatives of unknown solution function at a mesh point can be approximated by weighted linear sum of all the functional values along a mesh line. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  26 - Approximation of a Fuzzy Function by Using Radial Basis Functions Interpolation
  Reza Firouzdor Majid Amirfakhrian
  In the present paper, Radial Basis Function interpolations are applied to approximate a fuzzy function $\tilde{f}:\R\rightarrow \mathcal{F}(\R)$, on a discrete point set $X=\{x_1,x_2,\ldots,x_n\}$, by a fuzzy-valued function $\tilde{S}$. RBFs are based on linear combina أکثر

  In the present paper, Radial Basis Function interpolations are applied to approximate a fuzzy function $\tilde{f}:\R\rightarrow \mathcal{F}(\R)$, on a discrete point set $X=\{x_1,x_2,\ldots,x_n\}$, by a fuzzy-valued function $\tilde{S}$. RBFs are based on linear combinations of terms which include a single univariate function. Applying RBF to approximate a fuzzy function, a linear system will be obtained which by defining coefficient vector, target function will be approximated. Finally for showing the efficiency of the method we give some numerical examples. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  27 - Numerical Solution of The Parabolic Equations by Variational Iteration Method and Radial Basis Functions
  Sara Hosseini
  ‎In this work‎, ‎we consider the parabolic equation‎: ‎$u_t-u_{xx}=0$‎. ‎The purpose of this paper is to introduce the method of‎ ‎variational iteration method and radial basis functions for‎ ‎solving this equation‎. ‎ أکثر

  ‎In this work‎, ‎we consider the parabolic equation‎: ‎$u_t-u_{xx}=0$‎. ‎The purpose of this paper is to introduce the method of‎ ‎variational iteration method and radial basis functions for‎ ‎solving this equation‎. ‎Also, the method is implemented to three‎ ‎numerical examples‎. ‎The results reveal‎ ‎that the technique is very effective and simple. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  28 - Determination of a Source Term in an Inverse Heat Conduction Problem by Radial Basis Functions
  Muhammad Arghand
  In this paper, we propose a technique for determining a source term in an inverse heat conduction problem (IHCP) using Radial Basis Functions (RBFs). Because of being very suitable instruments, the RBFs have been applied for solving Partial Dierential Equations (PDEs) أکثر

  In this paper, we propose a technique for determining a source term in an inverse heat conduction problem (IHCP) using Radial Basis Functions (RBFs). Because of being very suitable instruments, the RBFs have been applied for solving Partial Dierential Equations (PDEs) by some researchers. In the current study, a stable meshless method will be pro- posed for solving an (IHCP). The other advantage of the method is that can be applied to the problems with various types of boundary conditions. The results of numerical experiments are presented and compared with analytical solutions. The results demonstrate the reliability and efficiency of the proposed scheme. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  29 - Using Radial Basis Functions for Numerical Solving Two-Dimensional Voltrra Linear Functional Integral Equations
  reza Firouzdor Neda Khaksary Atousa Emady
  This article is an attempt to obtain the numerical solution of functional linear Voltrra two-dimensional integral equations using Radial Basis Function (RBF) interpolation which isbased on linear composition of terms. By using RBF in functional integral equation, rst a أکثر

  This article is an attempt to obtain the numerical solution of functional linear Voltrra two-dimensional integral equations using Radial Basis Function (RBF) interpolation which isbased on linear composition of terms. By using RBF in functional integral equation, rst alinear system 􀀀C = G will be achieved; then the coecients vector is dened, and nally thetarget function will be approximated. In the end, the validity of the method is shown by anumber of examples. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  30 - THE COMPARISON OF EFFICIENT RADIAL BASIS FUNCTIONS COLLOCATION METHODS FOR NUMERICAL SOLUTION OF THE PARABOLIC PDE’S
  S. S. Mirshojaei S. Fayazzadeh
  In this paper, we apply the compare the collocation methods of meshfree RBF over differential equation containing partial derivation of one dimension time dependent with a compound boundary nonlocal condition.

  In this paper, we apply the compare the collocation methods of meshfree RBF over differential equation containing partial derivation of one dimension time dependent with a compound boundary nonlocal condition. تفاصيل المقالة
• حرية الوصول المقاله
  • صفحة الملخص
  • نص كامل
  
  31 - Modeling of Groundwater Resources Heavy Metals Concentration Using Soft Computing Methods: Application of Different Types of Artificial Neural Networks
  Meysam Alizamir Soheil Sobhanardakani Lobat Taghavi
  10.22034/jchr.2017.544179
  Nowadays, groundwater resources play a vital role as a source of drinking water in arid and semiarid regions and forecasting of pollutants content in these resources is very important. Therefore, this study aimed to compare two soft computing methods for modeling Cd, Pb أکثر

  Nowadays, groundwater resources play a vital role as a source of drinking water in arid and semiarid regions and forecasting of pollutants content in these resources is very important. Therefore, this study aimed to compare two soft computing methods for modeling Cd, Pb and Zn concentration in groundwater resources of Asadabad Plain, Western Iran. The relative accuracy of several soft computing models, namely multi-layer perceptron (MLP) and radial basis function (RBF) for forecasting of heavy metals concentration have been investigated. In addition, Levenberg-Marquardt, gradient descent and conjugate gradient training algorithms were utilized for the MLP models. The ANN models for this study were developed using MATLAB R 2014 Software program. The MLP performs better than the other models for heavy metals concentration estimation. The simulation results revealed that MLP model was able to model heavy metals concentration in groundwater resources favorably. It generally is effectively utilized in environmental applications and in the water quality estimations. In addition, out of three algorithms, Levenberg-Marquardt was better than the others were. This study proposed soft computing modeling techniques for the prediction and estimation of heavy metals concentration in groundwater resources of Asadabad Plain. Based on collected data from the plain, MLP and RBF models were developed for each heavy metal. MLP can be utilized effectively in applications of prediction of heavy metals concentration in groundwater resources of Asadabad Plain. تفاصيل المقالة