Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : Principal Component Analysis

An Efficient Approach Combining Genetic Algorithm and Neural Networks for Eigen Value Grads Method (EGM) In Wireless Mobile Communications

Mohammed Hussein Miry

Engineering and Technology Journal, 2011, Volume 29, Issue 13, Pages 2590-2600

The objective of this paper is combining Genetic Algorithm and Principal
Component Analysis (PCA) neural network for Eigenvalue Grads Method (EGM)
to estimate the number of sources in wireless mobile communications. The
Eigenvalue Grads Method (EGM) is a popular method for estimation the number
of sources impinging on an array of sensors, which is a problem of great interest in
wireless mobile communications. This paper proposed a new system to estimate
the number of sources by applying the output of genetic algorithm and PCA neural
network with Complex Generalized Hebbian algorithm (CGHA) to EGM
technique. In the proposed model, the initial weight and learning rate values for
CGHA neural network can be selected automatically by using Genetic algorithm.
The result of computer simulation for proposed system showed good response by
fast converge speed for neural network , efficiency and yield the correct number of
the sources. The important feature of new system is that, the PCA of covariance
matrix are calculated based on CGHA neural network instead of determining the
covariance matrix because computation of covariance matrix is time consuming.

Image Authentication Using PCA And BP Neural Network

Abbas Hussein Miry; Akel A. Alzaiez; Mohammed Hussein Miry

Engineering and Technology Journal, 2010, Volume 28, Issue 22, Pages 6536-6545

In this paper, a recognition system for image identification by using
principal component analysis (PCA) and back propagation (BP) Neural Network is proposed. The system consists of three steps. At the very outset some preprocessing are applied on the input image. Secondly image features are extracted by using PCA, which will be taken as the input to the Back-propagation Neural Network (BPN) in the third step and classification. Principal Component Analysis (PCA) is one of the most popular appearance-based methods used mainly for dimensionality reduction in compression and recognition problems, this will reduce
the size of training data which it entered to neural network. In our work, The proposed model is tested on a number of images with different value of learning rate. Experimental results demonstrate the proposed model is better, efficient and it reduces the ratio of the number of iteration training to half comparing with results of the Neural Network