List of Articles
-
Open Access Article
1 - Search Space Reduction in Fingerprint Recognition Based on Block Orientation Field
S. Helfroush H. GhassemianClassification is the first essential step in every automatic fingerprint recognition system. Regarding to the time and expense of recognition process, it has the benefit of search space reduction. Conventional classification methods are based on visible fingerprint cla MoreClassification is the first essential step in every automatic fingerprint recognition system. Regarding to the time and expense of recognition process, it has the benefit of search space reduction. Conventional classification methods are based on visible fingerprint classes. However, due to small number of these classes and nonuniform distribution of fingerprints among them, continuous classification scheme has been addressed. In this method, a similarity criterion is defined and a degree of likeness is assigned to the similarity of input fingerprint and each fingerprint in database. According to similarity criterion, matching of input fingerprint is begun first with the image in database that is more similar to input fingerprint. In this paper, a new similarity measuring method is proposed and used for continuous classification of fingerprints. The method is based on block orientation field. It is translation and rotation invariant and does not need core point existence and detection. Experimental results on FVC2000 database demonstrate the effectiveness of the proposed algorithm in search space reduction compared with the other methods. Manuscript profile -
Open Access Article
2 - CDF (2,2) Wavelet Lossy Image Compression on CPLD
A. A. Lotfi-Neyestanak Mohammad Mohaghegh Hazrati Mohammad Mohaghegh Hazrati N. AhmidiThis paper presents a hardware implementation of CDF(2,2) wavelet image compressor. The design demonstrates that high quality circuit implementation is possible through the use of suitable data organization (partitioned approach) and algorithm-to-architecture mappings ( MoreThis paper presents a hardware implementation of CDF(2,2) wavelet image compressor. The design demonstrates that high quality circuit implementation is possible through the use of suitable data organization (partitioned approach) and algorithm-to-architecture mappings (parallel-ism or pipelining). A VHDL code for CDF(2,2) was developed to satisfy our objective. Then it was synthesized in Foundation 5.1 software and downloaded to CPLD XC9572 by a JTAG ByteBlaster cable. The original image was transmitted through serial port. The AVR’s ATmega8535 was used to implement serial protocol to and back from the CPLD. The main goal is to reach a higher performance and throughput with a single CPLD. Details of the encoder design have been discussed and the results are presented. Manuscript profile -
Open Access Article
3 - Optimum Design and Fabrication of Pen-Shaped Antenna
Mohammad Khalaj-AmirhosseiniIn this paper, a pen-shaped antenna, called Vlasov antenna, is introduced. This antenna has a simple structure and can be constructed by creating a slant at the end of a circular waveguide. The main property of this antenna is its suitable radiation by excitation of som MoreIn this paper, a pen-shaped antenna, called Vlasov antenna, is introduced. This antenna has a simple structure and can be constructed by creating a slant at the end of a circular waveguide. The main property of this antenna is its suitable radiation by excitation of some modes such as TM01, which are symmetrical. The analysis of the antenna is done qualitatively and then the manner of its design is introduced. A pen-shaped antenna is designed in the X band and then is simulated, fabricated, and its performance is measured. Manuscript profile -
Open Access Article
4 - A New CMA Algorithm for Adaptive Array Systems with Rayleigh Channel Fading in the Mobile Communications Based on CDMA
E. Jedari Mohammad Hakkak M. KamareiIn this paper, we propose a time-varying multi-path vector channel model for the cellular CDMA-based communication system environment. A modified CMA to use in CDMA system environment is presented. We assume that the angular spread of each source to be large so that fad MoreIn this paper, we propose a time-varying multi-path vector channel model for the cellular CDMA-based communication system environment. A modified CMA to use in CDMA system environment is presented. We assume that the angular spread of each source to be large so that fading is non-coherent across the elements of the antenna array. The proposed modified CMA algorithm is more suitable in studying the convergence performance and the radiation patterns of uniform linear for tracking signal sources in CDMA mobile systems. Comparing the signal to noise ratio at the output of the algorithm of a uniform linear with the theoretical results proves the efficiency of the proposed algorithm. The BER performance with DBPSK modulation is also compared for CMA and VS-CMA algorithms in linear array. Manuscript profile -
Open Access Article
5 - Comparsion of Harmonic Propagation and Whack-a-mole Phenomena Compensation on Radial Distribution Feeder Using Parallel Active Power Filter with Constant and Controlled Gains
H. R. Ezzati A. Yazdian VarjaniIn order to damping harmonic propagation effect, the active power filters (APF) are installed on distribution systems. This installation also may cause harmonic oscillation effect named Whack-a-mole. In this paper using simulation results, the two mentioned effects are MoreIn order to damping harmonic propagation effect, the active power filters (APF) are installed on distribution systems. This installation also may cause harmonic oscillation effect named Whack-a-mole. In this paper using simulation results, the two mentioned effects are decreased efficiently for a ten-bus power radial distribution feeder for any nonlinear load connections (harmonic current or voltage source) by using constant gain Kv=1/Zc The characteristic impedance, Zc, is nondeterministic and variable, so the APF's gain should be controlled actively. In this paper the parallel active filter gain is designed such that by producing proper compensating current, the harmonic distortion on APF bus is controlled and the harmonic propagation and oscillation effects are prevented by keeping the harmonic distortion in an allowable interval. By adjusting APF gain, the effective compensation current will decrease and so the power loss and cost, the benefit of applying adjustable gain APF. Manuscript profile -
Open Access Article
6 - Multi-Objective Particle Swarm Classifier
Seyed-Hamid ZahiriA multi-objective particle swarm optimization (MOPSO) algorithm has been used to design a classifier which is able to optimize some important pattern recognition indices concurrently. These are Reliability, Score of recognition, and the number of hyperplanes. The propos MoreA multi-objective particle swarm optimization (MOPSO) algorithm has been used to design a classifier which is able to optimize some important pattern recognition indices concurrently. These are Reliability, Score of recognition, and the number of hyperplanes. The proposed classifier can efficiently approximate the decision hyperplanes for separating the different classes in the feature space and dose not have any over-fitting and over-learning problems. Other swarm intelligence based classifiers do not have the capability of simultaneous optimizing aforesaid indices and they also may suffer the over-fitting problem. The experimental results show that the proposed multi-objective classifier can estimate the optimum sets of hyperplanes by approximating the Pareto-front and provide the favorite user's setup for selecting aforesaid indices. Manuscript profile -
Open Access Article
7 - A New Ensemble Learning Method for Improvement of Classification Performance
S. H. Nabavi-Kerizi E. KabirThe combination of multiple classifiers is shown to be suitable for improving the performance of pattern recognition systems. Combining multiple classifiers is only effective if the individual classifiers are accurate and diverse. The methods have been proposed for dive MoreThe combination of multiple classifiers is shown to be suitable for improving the performance of pattern recognition systems. Combining multiple classifiers is only effective if the individual classifiers are accurate and diverse. The methods have been proposed for diversity creation can be classified into implicit and explicit methods. In this paper, we propose a new explicit method for diversity creation. Our method adds a new penalty term in learning algorithm of neural network ensembles. This term for each network is the product of its error and the sum of other networks errors. Experimental results on different data sets show that proposed method outperforms the independent training and the negative correlation learning methods. Manuscript profile