This study focuses on using an artificial neural network (ANN) based model for predicting the performance of high strength concrete (HSC) beams strengthened with surface mounted FRP laminates. Eight input parameters such as geometrical properties of the beam and mechanical properties of FRP laminates were considered for this study. Back propagation network with Lavenberg-Marquardt algorithm has...

The paper demonstrates performance enhancement using selective cloning on evolutionary neural network over the conventional genetic algorithm and neural back propagation algorithm for data classification. Introduction of selective cloning improves the convergence rate of the genetic algorithm without compromising on the classification errors. The selective cloning is tested on five data sets. T...

—Regarding to the problems of low rate of convergence and fault saturation for neural network classifier based on the algorithm of error back propagation during the signal recognition, bee colony algorithm is applied in this paper so as to extract combined feature module of signal and suggest three different algorithms including algorithm with rapidly support, super self-adaption error back pr...

The convergence time for training back propagation neural network for image compression is slow as compared to other traditional image compression techniques. This article proposes a pre-processing technique i.e. Pre-processed Back propagation neural image compression (PBN) with an enhancement in performance measures like better convergence time with respect to decoded picture quality and compr...

Bankruptcy prediction is one of the major business classification problems. The main purpose of this study is to investigate Kohonen self-organizing feature map in term of performance accuracy in the area of bankruptcy prediction.  A sample of 108 firms listed in Tehran Stock Exchange is used for the study. Our results confirm that Kohonen network is a robust model for predicting bankruptcy in ...

a back propagation artificial neural network (bpann) is a well-known learning algorithmpredicated on a gradient descent method that minimizes the square error involving the networkoutput and the goal of output values. in this study, 261 gps/leveling and 8869 gravity intensityvalues of iran were selected, then the geoid with three methods “ellipsoidal stokes integral”,“bpann”, and “collocation” ...

This paper explores the potential of extreme learning machine based supervised classification algorithm for land cover classification. In comparison to a backpropagation neural network, which requires setting of several user-defined parameters and may produce local minima, extreme learning machine require setting of one parameter and produce a unique solution. ETM+ multispectral data set (Engla...

Focused on the issue that conventional remote sensing image classification methods have run into the bottlenecks in accuracy, a new remote sensing image classification method inspired by deep learning is proposed, which is based on Stacked Denoising Autoencoder. First, the deep network model is built through the stacked layers of Denoising Autoencoder. Then, with noised input, the unsupervised ...