Keywords : Neural Networks


Scansion Text Written in English language and Recognized Printed English Character using Bidirectional Associative Memory Network

Aseel W. Ali

AL-Rafidain Journal of Computer Sciences and Mathematics, 2013, Volume 10, Issue 2, Pages 81-94
DOI: 10.33899/csmj.2013.163487

The fact that English language is a universal language, so it is necessary to propose  a computerized  ways to recognize the texts written in English language, which will simplifies the reading  of any text, treat it, and deal with it in a least possible time.
            The BAM (Bidirectional Associative Memory) network was used to recognize the printed English letters, because it process the small size images of letters in an easy way, also BAM is working in two ways (forward and backward) and store the weights without any amendment, therefore BAM is considered as one of the networks of education controller (Supervised learning).
The recognition of the printed English text was done using the network BAM, while the printed English text was entered to the computer using the scanner, also BAM network used to recognize the letters that have some noise and after training; it gives successful results of recognition about 84.6%.
  The aim of this research is to segment and recognize the printed English text, wither it is clear or it have some noise, Matlab R2008a language is used to accomplish this work.
 

Extraction and Recognition of Color Feature in true Color Images Using Neural Network Based on Colored Histogram Technique

Orjuwan M.A. Aljawadi

AL-Rafidain Journal of Computer Sciences and Mathematics, 2012, Volume 9, Issue 2, Pages 167-181
DOI: 10.33899/csmj.2012.163709

In this research, a neural network using backpropagation (BPNN) algorithm was trained and learned to work as the cone cells in human eyes to recognize the three fundamental cells’ colors and hues, as the neural network showed good results in training and testing the color feature  it was trained and learned again to recognize two nature scenes images ; Red sunset and Blue sky images where both scenes images contain color interaction and different hues such as red-orange and blue-violet. The recognition process was based on color histogram technique in colored images which is a representation of the distribution of colors in an image by counting the number of pixels that have colors in each of a fixed list of color ranges, that span the image's color space , all possible colors in the image. The importance of this research is based on developing the ability of (BPNN) in images ‘objects recognition based on color feature that is very important feature in artificial intelligence and colored image processing fields from developing the systems of alarms robots in fire recognition , medical digenesis of tumors, certain pattern’s recognition in different segments of an image , face and eyes’ iris recognition as a part of security systems , it helps solve the problem of limitation of recognition process in neural networks in many fields.
 

Hybridization of Genetic Algorithm with Neural Networks to Cipher English Texts

Radwan Y. Al-Jawadi; Raid R. Al-Naima

AL-Rafidain Journal of Computer Sciences and Mathematics, 2010, Volume 7, Issue 3, Pages 77-90
DOI: 10.33899/csmj.2010.163928

This research aims in the first stage to built a cipher system using hybrid Genetic Algorithm with single layer Neural network to prevent any data attack during the transition process , where the ASCII of the letters are used as inputs to the network and the random numbers are used as outputs to the network , then the weights will be constructed after the network training .
In the second stage a decipher process is used to restore the ciphered data by using the inverse of the genetic neural network , where the inverse of weights is used as a key for the decryption process .
Stream cipher method is used to input the data in the network during the ciphering stage. This suggested technique attained 100% success.
All the ciphering and deciphering processes are built under MATLAB ver.(7) .
 

Pulmonary Tuberculosis Diagnosis Using Artificial Neural Networks

Karam Hatim Thanoon; Mohammed Abd-alraheem Hamdi

AL-Rafidain Journal of Computer Sciences and Mathematics, 2009, Volume 6, Issue 1, Pages 103-114
DOI: 10.33899/csmj.2009.163788

This research can detecting the Tuberculosis by using the artificial neural networks, the idea of this research is to design a system that receive the information of patient and give these information to Hamming and Maxnet network which doing the comparison between these information with constant values of human body that stored in network. The system is implemented about many humans (infected and not infected) which has been entered their information to the data base of system, and programmed the system by using visual basic 6.0 with Microsoft access software to build the data base.