JALIL SHIRAZI - Academia.edu (original) (raw)

Papers by JALIL SHIRAZI

In this paper, we proposed an improved edge detection algorithm based on fuzzy combination of mat... more In this paper, we proposed an improved edge detection algorithm based on fuzzy combination of mathematical morphology and wavelet transform. We used type-1 and type-2 fuzzy rules.The proposed method overcomes the limitation of wavelet based edge detection and mathematical morphology based edge detection in noisy images. Experimental results show superiority of the proposed method, as compared to the traditional Prewitt, wavelet based and morphology based edge detection methods. The proposed method is an effective edge detection method especially for noisy images and keeps clear and continuous edges.

International Journal of Electrical and Computer Engineering, 2011

In this paper, an improved edge detection algorithm based on fuzzy combination of mathematical mo... more In this paper, an improved edge detection algorithm based on fuzzy combination of mathematical morphology and wavelet transform is proposed. The combined method is proposed to overcome the limitation of wavelet based edge detection and mathematical morphology based edge detection in noisy images. Experimental results show superiority of the proposed method, as compared to the traditional Prewitt, wavelet based and morphology based edge detection methods. The proposed method is an effective edge detection method for noisy image and keeps clear and continuous edges. Keywords—Edge detection, Wavelet transform, Mathematical morphology, Fuzzy logic.

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2011

In this paper, in order to categorize ORL database face pictures, principle Component Analysis (P... more In this paper, in order to categorize ORL database face pictures, principle Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) methods by using Elman neural network and Support Vector Machine (SVM) categorization methods are used. Elman network as a recurrent neural network is proposed for modeling storage systems and also it is used for reviewing the effect of using PCA numbers on system categorization precision rate and database pictures categorization time. Categorization stages are conducted with various components numbers and the obtained results of both Elman neural network categorization and support vector machine are compared. In optimum manner 97.41% recognition accuracy is obtained. Keywords—Face recognition, Principal Component Analysis, Kernel Principal Component Analysis, Neural network, Support Vector Machine.

Majlesi Journal of Electrical Engineering, 2017

In this paper a low-noise amplifier with 0 . 6 V supply voltage, low power consumption, and impro... more In this paper a low-noise amplifier with 0 . 6 V supply voltage, low power consumption, and improved linearity at= 5 GHz is introduced in 0 . 18 µ m CMOS technology. By using a feed-forward structure and a multi-gated configuration in the proposed circuit, linearity of the circuit is significantly improved, while only 122 µ W more power is consumed compared to conventional folded cascode structure, and the other circuit parameters are similar. In addition, the Volterra series is used for nonlinear analysis and to evaluate the linearity improvement of the proposed circuit. There is also a noteworthy superiority over compared published works in the figure of merit. The suggested low-noise amplifier (LNA) at 1 . 28 mW DC power consumption provides 9 . 6 dB gain and a noise figure of 3 . 24 dB. It is achieved whilst the third order interception point has been improved by 10 dB and equals 0 . 0 dBm. In the operating frequency the circuit displays satisfactory input and output impedance m...

Mechatronic equipments such as a head positioning system of hard disks have been required to prov... more Mechatronic equipments such as a head positioning system of hard disks have been required to provide fast and accurate positioning. To achieve these requirements, a mode switching control (MSC), which encompasses such diverse structures and functions of the controller is switching to that was used extensively. To achieve to a desired position in this matter, the model a controller parameters are assessed by some evolutionary algorithms like genetic, patter search and simulated annealing. The obtained parameters show that the values of these algorithms have good effect on their output. In this paper, the best algorithm, could be proper is introduced.

In the present article the speech recognition is performed on 61 English phones extracted from TI... more In the present article the speech recognition is performed on 61 English phones extracted from TIMIT database. For this reason the speech signal of each phone is divided into 20 millisecond frames and for each frame, the MFCC coefficients, their first and second derivatives, energy of the frame, as well as its first derivative were extracted as 41 features of the vector frame and by the use of the support vector machines, the frame classification into English phonetics is performed. In order to improve the results the sinusoidal Lifter and Independent Component Analysis (ICA) are applied on feature vectors. According to the results of the study, there have been 4.93% error rate for the test data which presents a significant improvement compared with the recent researches in this area and demonstrate the high performance of the features and algorithms used in the article.

During the present paper a number of cardiovascular patients were classified using features of ce... more During the present paper a number of cardiovascular patients were classified using features of cepstral coefficients based on national standards. Heart sounds include a healthy heart and fourth unhealthy heart, The data used in this paper was obtained from Michigan university website. After the separation of the heart murmurs from each heart sound, the cepstral coefficients based on Mel scale for each class was calculated as feature vectors and method support vector machine was used for the classification of the diseases. The diagnostic accuracy was %100. The results indicated the accuracy, reliability, and high performance capacity in method design.

International Journal of Scientific Engineering and Technology

–Normalized cross correlation is one of the practical methods for comparing the similarity of the... more –Normalized cross correlation is one of the practical methods for comparing the similarity of the two images.This paper presents a new method to detect objects in the picture based on normalized cross correlation. In this method,the reference image is segmented usingcolor segmentation based on K-means clustering method and various objects in the reference image are extracted.Then, the similarity between pattern binary image and objects binary images, extracted from reference image,is examined using normalized correlation. If rotated desired patterns exist in the reference image, it will be recognized with this method.

Proceedings of the International Conference on Signal Processing and Multimedia Applications

In this paper, a new feature set for audio classification is presented and evaluated based on sin... more In this paper, a new feature set for audio classification is presented and evaluated based on sinusoidal modeling of audio signals. Variance of the birth-death frequencies in sinusoidal model of signal, as a measure of harmony, is used and compared to typical features as the input into an audio classifier. The performance of this sinusoidal model feature is evaluated through classification of audio to speech and music using both the GMM and the SVM classifiers. Classification results show that the proposed feature is quite successful in speech/music classification. Experimental comparisons with popular features for audio classification, such as HZCRR and LSTER, are presented and discussed. By using a set of three features, we achieved 96.83% accuracy, in one-sec segment based audio classification.

–Normalized cross correlation is one of the practical methods for comparing the similarity of the... more –Normalized cross correlation is one of the practical methods for comparing the similarity of the two images.This paper presents a new method to detect objects in the picture based on normalized cross correlation. In this method,the reference image is segmented usingcolor segmentation based on K-means clustering method and various objects in the reference image are extracted.Then, the similarity between pattern binary image and objects binary images, extracted from reference image,is examined using normalized correlation. If rotated desired patterns exist in the reference image, it will be recognized with this method.

Journal of Electrical and Electronic Engineering, 2015

Aircraft systems are inherently unstable systems. The equations governing the motion of an aircra... more Aircraft systems are inherently unstable systems. The equations governing the motion of an aircraft are a very complicated set of six non-linear coupled differential equations. The linearized equation around the operating point is simulated in simulink MATLAB software. Also, the linear part of the system of nonlinear equations is simulated in simulink MATLAB software. In this study, combinations of PD controllers with fuzzy controller in a unity feedback system has been employed. This paper gives a comparison between the two types of FLC type-1 and type-2 in order to show the great effect of the new type of FLCs in reducing overshoot of the step response and improving the robustness of the system.

Lecture Notes in Computer Science, 2005

A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolat... more A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolated words. The network dimension is 10*15 cells with a hexagonal topology and it is trained using 300 Farsi words. As input vectors for learning, speech spectrum and energy of signal are used. The weight vectors of the cells are then fine tuned using supervised learning vector

Journal of Electrical and Electronic Engineering, Nov 18, 2014

Aircraft systems are inherently unstable systems. The equations governing the motion of an aircra... more Aircraft systems are inherently unstable systems. The equations governing the motion of an aircraft are a very complicated set of six non-linear coupled differential equations. The linearized equation around the operating point is simulated in simulink MATLAB software. Also, the linear part of the system of nonlinear equations is simulated in simulink MATLAB software. In this study, combinations of PD controllers with fuzzy controller in a unity feedback system has been employed. This paper gives a comparison between the two types of FLC type-1 and type-2 in order to show the great effect of the new type of FLCs in reducing overshoot of the step response and improving the robustness of the system.

In this paper, a new feature set for audio classification is presented and evaluated based on sin... more In this paper, a new feature set for audio classification is presented and evaluated based on sinusoidal modeling of audio signals. Variance of the birth-death frequencies in sinusoidal model of signal, as a measure of harmony, is used and compared to typical features as the input into an audio classifier. The performance of this sinusoidal model feature is evaluated through classification of audio to speech and music using both the GMM and the SVM classifiers. Classification results show that the proposed feature is quite successful in speech/music classification. Experimental comparisons with popular features for audio classification, such as HZCRR and LSTER, are presented and discussed. By using a set of three features, we achieved 96.83% accuracy, in one-sec segment based audio classification.

Pitch frequency is the fundamental frequency of a speech signal. It is one of the most important ... more Pitch frequency is the fundamental frequency of a speech signal. It is one of the most important parameters for speech signal processing. The simulated results on Keele pitch reference database show that the performance of the proposed wavelet transform based pitch detection algorithm is obviously better than the original AMDF and its improvements based algorithms

Mechatronic equipments such as a head positioning system of hard disks have been required to prov... more Mechatronic equipments such as a head positioning system of hard disks have been required to provide fast and accurate positioning. To achieve these requirements, a mode switching control (MSC), which encompasses such diverse structures and functions of the controller is switching to that was used extensively. To achieve to a desired position in this matter, the model a controller parameters are assessed by some evolutionary algorithms like genetic, patter search and simulated annealing. The obtained parameters show that the values of these algorithms have good effect on their output. In this paper, the best algorithm, could be proper is introduced.

Int. Conference on Artificial Neural Networks, 2005

A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolat... more A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolated words. The network dimension is 10*15 cells with a hexagonal topology and it is trained using 300 Farsi words. As input vectors for learning, speech spectrum and energy of signal are used. The weight vectors of the cells are then fine tuned using supervised learning vector

2008 IEEE International Conference on Multimedia and Expo, 2008

... Jalil Shirazi1, Shahrokh Ghaemmaghami 2, Farbod Razzazi3 1. Islamic Azad University, Gonabad ... more ... Jalil Shirazi1, Shahrokh Ghaemmaghami 2, Farbod Razzazi3 1. Islamic Azad University, Gonabad Branch, Iran, 2. Sharif University of Technology, Iran 3. Islamic Azad University, Science and Research Branch, Iran J_shirazi@iau-gonabad.ac.ir, ghaemmag@sharif.edu, razzazi ...

TENCON 2008 - 2008 IEEE Region 10 Conference, 2008

ABSTRACT

Multimedia Tools and Applications, 2010

ABSTRACT

In this paper, we proposed an improved edge detection algorithm based on fuzzy combination of mat... more In this paper, we proposed an improved edge detection algorithm based on fuzzy combination of mathematical morphology and wavelet transform. We used type-1 and type-2 fuzzy rules.The proposed method overcomes the limitation of wavelet based edge detection and mathematical morphology based edge detection in noisy images. Experimental results show superiority of the proposed method, as compared to the traditional Prewitt, wavelet based and morphology based edge detection methods. The proposed method is an effective edge detection method especially for noisy images and keeps clear and continuous edges.

International Journal of Electrical and Computer Engineering, 2011

In this paper, an improved edge detection algorithm based on fuzzy combination of mathematical mo... more In this paper, an improved edge detection algorithm based on fuzzy combination of mathematical morphology and wavelet transform is proposed. The combined method is proposed to overcome the limitation of wavelet based edge detection and mathematical morphology based edge detection in noisy images. Experimental results show superiority of the proposed method, as compared to the traditional Prewitt, wavelet based and morphology based edge detection methods. The proposed method is an effective edge detection method for noisy image and keeps clear and continuous edges. Keywords—Edge detection, Wavelet transform, Mathematical morphology, Fuzzy logic.

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2011

In this paper, in order to categorize ORL database face pictures, principle Component Analysis (P... more In this paper, in order to categorize ORL database face pictures, principle Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) methods by using Elman neural network and Support Vector Machine (SVM) categorization methods are used. Elman network as a recurrent neural network is proposed for modeling storage systems and also it is used for reviewing the effect of using PCA numbers on system categorization precision rate and database pictures categorization time. Categorization stages are conducted with various components numbers and the obtained results of both Elman neural network categorization and support vector machine are compared. In optimum manner 97.41% recognition accuracy is obtained. Keywords—Face recognition, Principal Component Analysis, Kernel Principal Component Analysis, Neural network, Support Vector Machine.

Majlesi Journal of Electrical Engineering, 2017

In this paper a low-noise amplifier with 0 . 6 V supply voltage, low power consumption, and impro... more In this paper a low-noise amplifier with 0 . 6 V supply voltage, low power consumption, and improved linearity at= 5 GHz is introduced in 0 . 18 µ m CMOS technology. By using a feed-forward structure and a multi-gated configuration in the proposed circuit, linearity of the circuit is significantly improved, while only 122 µ W more power is consumed compared to conventional folded cascode structure, and the other circuit parameters are similar. In addition, the Volterra series is used for nonlinear analysis and to evaluate the linearity improvement of the proposed circuit. There is also a noteworthy superiority over compared published works in the figure of merit. The suggested low-noise amplifier (LNA) at 1 . 28 mW DC power consumption provides 9 . 6 dB gain and a noise figure of 3 . 24 dB. It is achieved whilst the third order interception point has been improved by 10 dB and equals 0 . 0 dBm. In the operating frequency the circuit displays satisfactory input and output impedance m...

Mechatronic equipments such as a head positioning system of hard disks have been required to prov... more Mechatronic equipments such as a head positioning system of hard disks have been required to provide fast and accurate positioning. To achieve these requirements, a mode switching control (MSC), which encompasses such diverse structures and functions of the controller is switching to that was used extensively. To achieve to a desired position in this matter, the model a controller parameters are assessed by some evolutionary algorithms like genetic, patter search and simulated annealing. The obtained parameters show that the values of these algorithms have good effect on their output. In this paper, the best algorithm, could be proper is introduced.

In the present article the speech recognition is performed on 61 English phones extracted from TI... more In the present article the speech recognition is performed on 61 English phones extracted from TIMIT database. For this reason the speech signal of each phone is divided into 20 millisecond frames and for each frame, the MFCC coefficients, their first and second derivatives, energy of the frame, as well as its first derivative were extracted as 41 features of the vector frame and by the use of the support vector machines, the frame classification into English phonetics is performed. In order to improve the results the sinusoidal Lifter and Independent Component Analysis (ICA) are applied on feature vectors. According to the results of the study, there have been 4.93% error rate for the test data which presents a significant improvement compared with the recent researches in this area and demonstrate the high performance of the features and algorithms used in the article.

During the present paper a number of cardiovascular patients were classified using features of ce... more During the present paper a number of cardiovascular patients were classified using features of cepstral coefficients based on national standards. Heart sounds include a healthy heart and fourth unhealthy heart, The data used in this paper was obtained from Michigan university website. After the separation of the heart murmurs from each heart sound, the cepstral coefficients based on Mel scale for each class was calculated as feature vectors and method support vector machine was used for the classification of the diseases. The diagnostic accuracy was %100. The results indicated the accuracy, reliability, and high performance capacity in method design.

International Journal of Scientific Engineering and Technology

–Normalized cross correlation is one of the practical methods for comparing the similarity of the... more –Normalized cross correlation is one of the practical methods for comparing the similarity of the two images.This paper presents a new method to detect objects in the picture based on normalized cross correlation. In this method,the reference image is segmented usingcolor segmentation based on K-means clustering method and various objects in the reference image are extracted.Then, the similarity between pattern binary image and objects binary images, extracted from reference image,is examined using normalized correlation. If rotated desired patterns exist in the reference image, it will be recognized with this method.

Proceedings of the International Conference on Signal Processing and Multimedia Applications

In this paper, a new feature set for audio classification is presented and evaluated based on sin... more In this paper, a new feature set for audio classification is presented and evaluated based on sinusoidal modeling of audio signals. Variance of the birth-death frequencies in sinusoidal model of signal, as a measure of harmony, is used and compared to typical features as the input into an audio classifier. The performance of this sinusoidal model feature is evaluated through classification of audio to speech and music using both the GMM and the SVM classifiers. Classification results show that the proposed feature is quite successful in speech/music classification. Experimental comparisons with popular features for audio classification, such as HZCRR and LSTER, are presented and discussed. By using a set of three features, we achieved 96.83% accuracy, in one-sec segment based audio classification.

–Normalized cross correlation is one of the practical methods for comparing the similarity of the... more –Normalized cross correlation is one of the practical methods for comparing the similarity of the two images.This paper presents a new method to detect objects in the picture based on normalized cross correlation. In this method,the reference image is segmented usingcolor segmentation based on K-means clustering method and various objects in the reference image are extracted.Then, the similarity between pattern binary image and objects binary images, extracted from reference image,is examined using normalized correlation. If rotated desired patterns exist in the reference image, it will be recognized with this method.

Journal of Electrical and Electronic Engineering, 2015

Aircraft systems are inherently unstable systems. The equations governing the motion of an aircra... more Aircraft systems are inherently unstable systems. The equations governing the motion of an aircraft are a very complicated set of six non-linear coupled differential equations. The linearized equation around the operating point is simulated in simulink MATLAB software. Also, the linear part of the system of nonlinear equations is simulated in simulink MATLAB software. In this study, combinations of PD controllers with fuzzy controller in a unity feedback system has been employed. This paper gives a comparison between the two types of FLC type-1 and type-2 in order to show the great effect of the new type of FLCs in reducing overshoot of the step response and improving the robustness of the system.

Lecture Notes in Computer Science, 2005

A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolat... more A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolated words. The network dimension is 10*15 cells with a hexagonal topology and it is trained using 300 Farsi words. As input vectors for learning, speech spectrum and energy of signal are used. The weight vectors of the cells are then fine tuned using supervised learning vector

Journal of Electrical and Electronic Engineering, Nov 18, 2014

Aircraft systems are inherently unstable systems. The equations governing the motion of an aircra... more Aircraft systems are inherently unstable systems. The equations governing the motion of an aircraft are a very complicated set of six non-linear coupled differential equations. The linearized equation around the operating point is simulated in simulink MATLAB software. Also, the linear part of the system of nonlinear equations is simulated in simulink MATLAB software. In this study, combinations of PD controllers with fuzzy controller in a unity feedback system has been employed. This paper gives a comparison between the two types of FLC type-1 and type-2 in order to show the great effect of the new type of FLCs in reducing overshoot of the step response and improving the robustness of the system.

In this paper, a new feature set for audio classification is presented and evaluated based on sin... more In this paper, a new feature set for audio classification is presented and evaluated based on sinusoidal modeling of audio signals. Variance of the birth-death frequencies in sinusoidal model of signal, as a measure of harmony, is used and compared to typical features as the input into an audio classifier. The performance of this sinusoidal model feature is evaluated through classification of audio to speech and music using both the GMM and the SVM classifiers. Classification results show that the proposed feature is quite successful in speech/music classification. Experimental comparisons with popular features for audio classification, such as HZCRR and LSTER, are presented and discussed. By using a set of three features, we achieved 96.83% accuracy, in one-sec segment based audio classification.

Pitch frequency is the fundamental frequency of a speech signal. It is one of the most important ... more Pitch frequency is the fundamental frequency of a speech signal. It is one of the most important parameters for speech signal processing. The simulated results on Keele pitch reference database show that the performance of the proposed wavelet transform based pitch detection algorithm is obviously better than the original AMDF and its improvements based algorithms

Mechatronic equipments such as a head positioning system of hard disks have been required to prov... more Mechatronic equipments such as a head positioning system of hard disks have been required to provide fast and accurate positioning. To achieve these requirements, a mode switching control (MSC), which encompasses such diverse structures and functions of the controller is switching to that was used extensively. To achieve to a desired position in this matter, the model a controller parameters are assessed by some evolutionary algorithms like genetic, patter search and simulated annealing. The obtained parameters show that the values of these algorithms have good effect on their output. In this paper, the best algorithm, could be proper is introduced.

Int. Conference on Artificial Neural Networks, 2005

A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolat... more A modified 2-D Kohonen Self-Organizing (MSOM) neural network is used for recognizing Farsi isolated words. The network dimension is 10*15 cells with a hexagonal topology and it is trained using 300 Farsi words. As input vectors for learning, speech spectrum and energy of signal are used. The weight vectors of the cells are then fine tuned using supervised learning vector

2008 IEEE International Conference on Multimedia and Expo, 2008

... Jalil Shirazi1, Shahrokh Ghaemmaghami 2, Farbod Razzazi3 1. Islamic Azad University, Gonabad ... more ... Jalil Shirazi1, Shahrokh Ghaemmaghami 2, Farbod Razzazi3 1. Islamic Azad University, Gonabad Branch, Iran, 2. Sharif University of Technology, Iran 3. Islamic Azad University, Science and Research Branch, Iran J_shirazi@iau-gonabad.ac.ir, ghaemmag@sharif.edu, razzazi ...

TENCON 2008 - 2008 IEEE Region 10 Conference, 2008

ABSTRACT

Multimedia Tools and Applications, 2010

ABSTRACT