این سایت در حال حاضر پشتیبانی نمی شود و امکان دارد داده های نشریات بروز نباشند
Iranian Journal of Electrical and Electronic Engineering، جلد ۱۳، شماره ۱، صفحات ۰-۰
عنوان فارسی
چکیده فارسی مقاله
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی Training Radial Basis Function Neural Network using Stochastic Fractal Search Algorithm to Classify Sonar Dataset
چکیده انگلیسی مقاله Radial Basis Function Neural Networks (RBF NNs) are one of the most applicable NNs in the classification of real targets. Using of recursive methods and gradient descent for training RBF NNs, improper classification accuracy, failing to local minimum and low-convergence speed are defections of this type of network. To overcome defections, heuristic and meta-heuristic algorithms have been popularized to training RBF networkRadial Basis Function Neural Networks (RBF NNs) are one of the most applicable NNs in the classification of real targets. Despite the use of recursive methods and gradient descent for training RBF NNs, classification improper accuracy, failing to local minimum and low-convergence speed are defects of this type of network. In order to overcome these defects, heuristic and meta-heuristic algorithms have been conventional to training RBF network in the recent years. This study uses Stochastic Fractal Search Algorithm (SFSA) for training RBF NNs. The particles in the new algorithm explore the search space more efficiently by using the diffusion property, which is observed regularly in arbitrary fractals. To assess the performance of the proposed classifier, this network will be evaluated with the two benchmark datasets and a high-dimensional practical dataset (i.e., sonar). Results indicate that new classifier classifies sonar dataset six percent better than the best algorithm and its convergence speed is better than the other algorithms. Also has better performance than classic benchmark algorithms about all datasets. in the recent years. This study uses Stochastic Fractal Search Algorithm (SFSA) for training RBF NNs. The particles in the new algorithm explore the search space more efficiently by using the diffusion property, which is seen regularly in arbitrary fractals. To assess the performance of the proposed classifier, this network will be evaluated with the two benchmark datasets and a high-dimensional practical dataset (i.e., sonar). Results indicate that new classifier indicates better performance than classic benchmark algorithms and classifies sonar dataset six percent better than the best algorithm and its convergence speed is better than the other algorithms.
کلیدواژه‌های انگلیسی مقاله
نویسندگان مقاله محمدرضا موسوی | m r mosavi
narmak, tehran 16846-13114, iran


m خویشه | m. khishe
narmak, tehran 16846-13114, iran


y حاتم خانی | y hatam khani
department of electrical engineering, university of imam khomeini marine sciences, noshahr, iran


m شعبانی | m. shabani
department of physics, university of hormozgan, bandar abbas, iran.

سازمان اصلی تایید شده: دانشگاه هرمزگان (Hormozgan university)

نشانی اینترنتی http://ijeee.iust.ac.ir/browse.php?a_code=A-10-78-17&slc_lang=en&sid=en
فایل مقاله فایلی برای مقاله ذخیره نشده است
کد مقاله (doi)
زبان مقاله منتشر شده en
موضوعات مقاله منتشر شده 5-Signal Processing
نوع مقاله منتشر شده Research Paper
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات