http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
ICA-based blind MIMO OFDM Receiver with Low-complexity by using Stone BSS
Mahdi Khosravy,Mohammad Reza Alsharif,Hai Lin,Katsumi Yamashita 대한전자공학회 2009 ITC-CSCC :International Technical Conference on Ci Vol.2009 No.7
In order to reduce the complexity of the Blind ICA-based MIMO-OFDM receiver an algorithm of employing blind source separation (BSS) methods has been proposed. The proposed algorithm exploits high performance of kullback leibler ICA as well as low complexity of Stone BSS. Stone BSS reduces the number of iteration required for convergence of KL ICA by initializing the separator matrix. The complexity of KL ICA has been reduced even more by using a NlogN kernel entropy estimation method. The numerical evaluation demonstrates the significant reduction in complexity of the blind MIMO OFDM receiver. In order to reduce the complexity of the Blind ICA-based MIMO-OFDM receiver an algorithm of employing blind source separation (BSS) methods has been proposed. The proposed algorithm exploits high performance of kullback leibler ICA as well as low complexity of Stone BSS. Stone BSS reduces the number of iteration required for convergence of KL ICA by initializing the separator matrix. The complexity of KL ICA has been reduced even more by using a NlogN kernel entropy estimation method. The numerical evaluation demonstrates the significant reduction in complexity of the blind MIMO OFDM receiver.
Image Enhancement Using Splitting α-Rooting Method in Wavelet Domain
Foisal Hossain,Mohammad Reza Alsharif 대한전자공학회 2008 ITC-CSCC :International Technical Conference on Ci Vol.2008 No.7
This paper will present an enhancement technique based upon splitting α-rooting method in wavelet domain. Wavelets transform concentrate most of the energy in the approximation coefficient. In splitting signal, a twodimensional image is represented uniquely by a set of onedimensional signal, which carries the spectral information of the image at frequency points of specific sets. Using splitting α-rooting method in the approximation coefficient of wavelet transform, the image enhancement procedure can be reduced to processing splitting signals and the process requires only a few spectral components of the image. A measure of enhancement based on contrast measure with respect to transform will be used as a tool for evaluating the performance of the proposed enhancement technique and for finding optimal values for variables contained in the enhancement. The algorithm’s performance will be compared quantitatively to classical histogram equalization and splitting α-rooting method using the aforementioned measure of enhancement.
A Probabilistic Short-length Linear Predictability Approach to Blind Source Separation
Mahdi Khosravy,Mohammad Reza Alsharif,Katsumi Yamashita 대한전자공학회 2008 ITC-CSCC :International Technical Conference on Ci Vol.2008 No.7
A merit function based on short length linear predictability of signal in an objective probabilistic algorithm is defined and used for blind source separation (BSS) of linear mixtures of signals. In BSS literatures, it has been conjectured that linear mixture of statistically independent source signals will result in a set of signals which each of them has less predictability than (or equal to) that of any of component source signals. We have used this property to extract source signals by finding an un-mixing matrix that maximizes the proposed merit function of predictability for each recovered signal. This method which is called Probabilistic Short-length Linear Predictability BSS (PSLP-BSS), its performance has been driven with many tests performed with mixtures of different kinds (speech, audio, image, constructed mathematical signals like saw tooth and sinusoidal). In all cases, correlation between each of source signals and each of extracted signals shows near-perfect performance of the method. The proposed BSS doesnt require any assumption regarding the probability density function of source signals. It has been demonstrated that PSLP-BSS can separate signal mixtures in which each mixture is a linear combination of source signals with gaussian, super-gaussian and sub-gaussian probability density functions. However, the method is adapted to temporal structure of recovered signals. Since, the un-mixing matrix that is concluded by proposed merit function can be obtained as the solution to a generalized eigenvalue routine, signals can be extracted simultaneously using the fast eigen value.
A Consideration of Noise Cancellation by using PCA-ICA Method with Delay Estimation
Toshiaki Yokoda,Mohammad Reza Alsharif,Mahdi Khosravy 대한전자공학회 2008 ITC-CSCC :International Technical Conference on Ci Vol.2008 No.7
The noise cancellation technologies are useful for speech recognition and other applications. There are some kind of methods for cancellation of background noise. In this paper, The desired signals are separated from background noise by using proposed PCA-ICA method (Principal Component Analysis, Independent Component Analysis). The proposed PCA-ICA method requires several number of observed signals that is, the same as the number of sources. The noise signal can be removed in the same way as BSS (Blind Source Separation). We have done experiments (two-observation one-source one-noise, with delay) and evaluated the results.
Web Application for discovering Association Rules in Social Welfare Data Base
Carlos Enrique Gutierrez,Mohammad Reza Alsharif 대한전자공학회 2008 ITC-CSCC :International Technical Conference on Ci Vol.2008 No.7
The current algorithms for fiding association rules are mainly batch processes. Several efforts are carried out to improve the algorithm’s performance and response’s speed. Besides that the dynamic and quick search of knowledge is becoming a necessity in the traditional Data Mining techniques. In this paper we explain step by step our web implementation of a fast asociation rules’ retrieval system in order to provide useful information to take decisions. Our system is based on the creation of temporary tables and the use of Structured Query Language “SQL” that allow a good exploitation of the database engine’s advantages. We present a simple web interface where the user chooses the attributes on which the mining algorithm will be executed.
Development Map for Latin America and the Caribbean using Self-Organizing Map
Carlos Enrique Gutierrez,Sonam Tshering,Alsharif Mohammad Reza 대한전자공학회 2009 ITC-CSCC :International Technical Conference on Ci Vol.2009 No.7
In the last years, countries like China and India stood out worldwide through their quick growth and developing processes. In Latin America and the Caribbean (LAC region) countries such as Brazil and Mexico are projected as the next region to grow up. It is very interesting to see how is the developing-evolution of the 26 LAC-countries. Using a Self Organizing Map (SOM) we could see the development history for each country by analyzing, after being a SOM fed by certain indexes, what unit is activated for a certain country-year. Also, it is possible to detect different relations among the countries, grouping them in categories. Our work seeks to generate an understandable development-map of the LAC region that shows countries’ grow or retrocession. To achieve it, a database from the InterAmerican Development Bank (IDB) with 11 annual development-indexes is used to feed a 2-dimensional Kohonen’s network. The generated map could be seen as a development-picture where the countries do not have geographical relationships, but similar data characteristics.