Ahar Branch,Islamic Azad University, Ahar,Iran
Journal of Artificial Intelligence in Electrical Engineering
2345-4652
3
10
2014
09
01
Implementation of VlSI Based Image Compression Approach on Reconfigurable Computing System - A Survey
1
7
EN
Shahin
Shafei
shahin_shafei@yahoo.com
Image data require huge amounts of disk space and large bandwidths for transmission. Hence, imagecompression is necessary to reduce the amount of data required to represent a digital image. Thereforean efficient technique for image compression is highly pushed to demand. Although, lots of compressiontechniques are available, but the technique which is faster, memory efficient and simple, surely hits theuser requirements. In this paper, the image compression, need of compression, its principles, how imagedata can be compressed, and the image compression techniques are reviewed and discussed. Also,wavelet-based image compression algorithm using Discrete Wavelet Transform (DWT) based on B-splinefactorization technique is discussed in detail. Based on the review, some general ideas to choose the bestcompression algorithm for an image are recommended. Finally, applications and future scopes of imagecompression techniques are discussed considering its development on FPGA systems.
Image compression,Discrete wavelet transform,Decomposed lifting algorithm (DLA),Huffman-coding
http://jaiee.iau-ahar.ac.ir/article_514431.html
http://jaiee.iau-ahar.ac.ir/article_514431_f0ce29e7b5eebb7bd762602bea812e9a.pdf
Ahar Branch,Islamic Azad University, Ahar,Iran
Journal of Artificial Intelligence in Electrical Engineering
2345-4652
3
10
2014
09
01
Reinforcement Learning Based PID Control of Wind Energy Conversion Systems
8
15
EN
Mohammad Esmaeil
akbari
m-akbari@iau-ahar.ac.ir
Noradin
Ghadimi
noradin.1364@gmail.com
In this paper an adaptive PID controller for Wind Energy Conversion Systems (WECS) has been developed. Theadaptation technique applied to this controller is based on Reinforcement Learning (RL) theory. Nonlinearcharacteristics of wind variations as plant input, wind turbine structure and generator operational behaviordemand for high quality adaptive controller to ensure both robust stability and safe performance. Thus, areinforcement learning algorithm is used for online tuning of PID coefficients in order to enhance closed loopsystem performance. In this study, at start the proposed controller is applied to two pure mathematical plants,and then the closed loop WECS behavior is discussed in the presence of a major disturbance.
Adaptive Control,WECS,reinforcement learning
http://jaiee.iau-ahar.ac.ir/article_514432.html
http://jaiee.iau-ahar.ac.ir/article_514432_fe4a9b1ce870b521c462bf74d3e2e596.pdf
Ahar Branch,Islamic Azad University, Ahar,Iran
Journal of Artificial Intelligence in Electrical Engineering
2345-4652
3
10
2014
09
01
Training Set of Data Bin for Small Black Pixels Neighborhood Recognition of Each Boundary
16
19
EN
Roya
Abdollahi
roya.abdollahi6666@yahoo.com
We first describe how to “fuzzify” the estimated binary columns to create a [0,1]-valued column. Werefer to this [0,1] -valued column as the soft segmentation column of the noisy spectrogram column.Similarly to the collection of soft segmentation columns as the soft segmentation image, or simply asthe soft segmentation. The band-dependent posterior probability that the hard segmentation columnvalue of pixel is 1, given that bin and the binary values in the neighborhood configuration of the pixelare equal. Symbolically, each pixel of the soft segmentation column is set to the soft segmentationcolumn value of the pixel in a row was set to zero.
http://jaiee.iau-ahar.ac.ir/article_514433.html
http://jaiee.iau-ahar.ac.ir/article_514433_3556cd5188d360081946e825ad3ea21d.pdf
Ahar Branch,Islamic Azad University, Ahar,Iran
Journal of Artificial Intelligence in Electrical Engineering
2345-4652
3
10
2014
09
01
Fuel Cell Voltage Control for Load Variations Using Neural Networks
20
23
EN
Zolekh
Teadadi
sh.teadadi@gmail.com
Hassan
Changiziyan
In the near future the use of distributed generation systems will play a big role in the production ofelectrical energy. One of the most common types of DG technologies , fuel cells , which can be connectedto the national grid by power electronic converters or work alone Studies the dynamic behavior andstability of the power grid is of crucial importance. These studies need to know the exact model of dynamicelements. In this paper, a new method based on a neural network algorithm for controlling the fuel cellvoltage is provided. The effects of load change the output voltage characteristic of the fuel cell unit ischecked Simulations in MATLAB / SIMULINK. The results show that the prosecution is conducted in anappropriate manner Voltage Stabilization time.
Fuel cell,Dynamic Behavior,Neural networks,hydrogen,neural network controller
http://jaiee.iau-ahar.ac.ir/article_514434.html
http://jaiee.iau-ahar.ac.ir/article_514434_9897a9ce118d79a55582a25f4a68b3b1.pdf
Ahar Branch,Islamic Azad University, Ahar,Iran
Journal of Artificial Intelligence in Electrical Engineering
2345-4652
3
10
2014
09
01
Load Frequency Control in Two Area Power System Using Sliding Mode Control
24
36
EN
Milad
Babakhani Qazijahan
babakhani.milad@yahoo.com
In this article, the sliding mode control of frequency load control of power systems is studied. The study areaconsists of a system of water and heat. First, a mathematical model of the proposed system disturbances ismade and then sliding control mode for frequency load control is provided. By the system simulation andsliding mode control, it can be shown that the damping of oscillations is well led.
frequency Load control,Sliding mode control,dual zone system
http://jaiee.iau-ahar.ac.ir/article_514435.html
http://jaiee.iau-ahar.ac.ir/article_514435_e3385c15cf4d3d2f1d12004bcf4eb733.pdf
Ahar Branch,Islamic Azad University, Ahar,Iran
Journal of Artificial Intelligence in Electrical Engineering
2345-4652
3
10
2014
09
01
Neural Networks in Electric Load Forecasting:A Comprehensive Survey
37
50
EN
Vahid
Mansouri
vahidmansouri2010@gmail.com
Mohammad Esmaeil
akbari
Review and classification of electric load forecasting (LF) techniques based on artificial neuralnetworks (ANN) is presented. A basic ANNs architectures used in LF reviewed. A wide range of ANNoriented applications for forecasting are given in the literature. These are classified into five groups:(1) ANNs in short-term LF, (2) ANNs in mid-term LF, (3) ANNs in long-term LF, (4) Hybrid ANNs inLF, (5) ANNs in Special applications of LF. The major research articles for each category are brieflydescribed and the related literature reviewed. Conclusions are made on future research directions.
Artificial Neural Networks (ANNs),Load Forecasting(LF),Short Term LF,Mid Term
LF,Long Term LF,Peak LF,Unit Commitment(UC)
http://jaiee.iau-ahar.ac.ir/article_514436.html
http://jaiee.iau-ahar.ac.ir/article_514436_40c94157e14d3cf7890e1d964fdf1bf9.pdf