Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : Back

OFDM Channel Estimation Based on Intelligent Systems

Ismail Mohammad Jaber; Hanan A. R. Akkar; Haraa Raheim Hatem

Engineering and Technology Journal, 2014, Volume 32, Issue 2, Pages 305-324

This work is dedicated to the study of reducing Bit Error Rate (BER) when transferring data in the system Orthogonal Frequency Division Multiplexing (OFDM) by estimating the carrier channel in different ways. The proposal design for Artificial Neural Network (ANN) is considered as a tool to improve performance BER and compared with the traditional method based on the use of the Least Square estimation algorithm (LS) to estimate the impulse response of frequency selective Rayleigh fading channel. A MATLAB 7.14 program is used in simulation.
The proposed method which integrates algorithm LS with ANN includes the following:
1. Training the neural network by Back-Propagation (BP) and using the trained neural network with algorithm (LS) to estimate the channel in different paths.
2. Using Resilient Back propagation algorithm (RProp)in the training of the neural network.
3. UsingLevenberg-Marquardt algorithm (LM) in the training of the neural network.
4.The comparison of results between the traditional method and the proposed method when taking BER = 0.001 at various tracks (one path, two path and three path) and showed that there profit of (1.5dB, 2dB, 2dB) between using the traditional method and the proposed method using RProp algorithm and a profit of (2dB,3dB, 2dB) using an algorithm LM. There is also comparison between the performance ofRProp algorithm and LMalgorithm and the results showed that the LM algorithm better thanRProp algorithm.

Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

Hanan A. R. Akkar; Samem Abass Salman

Engineering and Technology Journal, 2011, Volume 29, Issue 13, Pages 2739-2755

This work is devoted to compression Image Skin Diseases by using Discrete Wavelet Transform (DWT) and training Feed-Forward Neural Networks (FFNN) by using Particle Swarm Optimization(PSO) and compares it with Back-Propagation (BP) neural networks in terms of convergence rate and accuracy of results .The comparison between the two techniques will be mentioned. A MATLAB 6.5 program is used in simulation.
The structure Artificial Neural Network (ANN) of training image skin diseases is proposed as follows: 1- The proposed structure of NN that performs three compressions Images Skin training by BP algorithms with log sigmoid activation function, and three neurons in output layer.
2- The proposed structure of FFNN using PSO that performs three compressions Images Skin with hardlim activation function, and three neurons in output layer. The results obtained using PSO are compared to those obtained using BP. Learning iterations (602-4700 epoch), convergence time (1sec.- 100 sec.), number of initial
weights (1set - 75set), number of derivatives (0 - 38 derivatives) and accuracy (60% - 100%) are used as performance measurements. The obtained Mean Square Error (MSE) is 7 10 - to check the performance of algorithms. The results of the proposed neural networks performed indicate that PSO can be a superior training algorithm for
neural networks, which is consistent with other research in the area.

Intrusion Detection and Attack Classifier Based on Three Techniques: A Comparative Study

Adel Sabry Issa; Adnan Mohsin Abdulazeez Brifcani

Engineering and Technology Journal, 2011, Volume 29, Issue 2, Pages 386-412

Different soft-computing based methods have been proposed in recent years
for the development of intrusion detection systems. The purpose of this work is to
development, implement and evaluate an anomaly off-line based intrusion
detection system using three techniques; data mining association rules, decision
trees, and artificial neural network, then comparing among them to decide which
technique is better in its performance for intrusion detection system. Several
methods have been proposed to modify these techniques to improve the
classification process. For association rules, the majority vote classifier was
modified to build a new classifier that can recognize anomalies. With decision
trees, ID3 algorithm was modified to deal not only with discreet values, but also
to deal with numerical values. For neural networks, a back-propagation algorithm
has been used as the learning algorithm with different number of input patterns
(118, 51, and 41) to introduce the important knowledge about the intruder to the
neural networks. Different types of normalization methods were applied on the
input patterns to speed up the learning process. The full 10% KDD Cup 99 train
dataset and the full correct test dataset are used in this work. The results of the
proposed techniques show that there is an improvement in the performance
comparing to the standard techniques, furthermore the Percentage of Successful
Prediction (PSP) and Cost Per Test (CPT) of neural networks and decision trees
are better than association rules. On the other hand, the training time for neural
network takes longer time than the decision trees.