mostafa mofarreh-bonab | Shahid Beheshti University (original) (raw)

Uploads

Papers by mostafa mofarreh-bonab

International Journal of Computer Applications, 2015

Principal Component Analysis (PCA) is an efficient method for compressing high dimensional databa... more Principal Component Analysis (PCA) is an efficient method for compressing high dimensional databases [1]. For image compression, it is called Hotelling or KL transform. The central idea of PCA is to reduce the dimensionality of a data set in which there are a large number of interrelated variables. [2] This reduction is achieved by transforming to a new set of variables, the principal components, which are uncorrelated, and which are ordered so that the first few retain most of the variation present in all of the original variables. Computation of the principal components reduces to the solution of an Eigen value-Eigen vector problem for a positive-semi definite symmetric matrix [2]. In spite of ordinary applications which utilize the PCA method for dataset compression, in this paper, a new method is introduced to compress a single image in RGB color space using the correlations between three Red, Green and Blue color domains.

6th International Symposium on Telecommunications (IST), 2012

ABSTRACT In Wireless Sensor Networks (WSNs), the received data from nodes are useful only when ac... more ABSTRACT In Wireless Sensor Networks (WSNs), the received data from nodes are useful only when accurate information about their locations is available. Many localization methods use some nodes that their locations are known by manual or by means of positioning systems such as GPS. These nodes are known as anchor or beacon nodes. In those applications of WSNs in which localization is very important, such as robotic land mine detection, battle field surveillance, etc., the anchor nodes may be attacked by unauthorized accesses in hostile environments and as a result, the localization system may face perturbation. Therefore, in recent literatures some secure localization methods have been introduced. Gradient descent is a low complex, secure and time efficient approach that marks some anchor nodes as attacked ones by using special algorithms and prunes them, then determines the position of sensors using the remaining anchor nodes. In this paper, it is shown that pruning these anchor nodes may cause to localization error increase. In other words, it is shown that in non-coordinated attacks, using the information sent by attacked anchor nodes can improve the localization accuracy. The simulation results show that by utilizing this technique, we can decrease the localization error up to 15%.

Communications on Applied Electronics, 2015

Besides ever increasing digital world, the importance of information security aspects becomes inc... more Besides ever increasing digital world, the importance of information security aspects becomes increasingly clear day by day. Several solutions are introduced to provide the required security for various applications and encryption is one of these solutions [2]. In image encryption, conventional algorithms encounter some kinds of complexity due to high amount of data that should be processed. In this paper, a new method is introduced for image encryption using PCA method. This algorithm is more advantageous especially in applications that integrity of database is more important, such as a prison and the prisoner's photo database. In such cases, the security system should provide two major requirements:1) avoid changing an image in the database and 2) hiding real images from unauthorized access. The simulation results show that the mentioned method is capable to manage these two requirements properly.

ICCKE 2013, 2013

ABSTRACT In many applications of Wireless Sensor Networks (WSNs) such as monitoring applications ... more ABSTRACT In many applications of Wireless Sensor Networks (WSNs) such as monitoring applications or routing, localization is one of the important issues that affect directly the network quality of operation. Secure localization in WSNs needs to detect malicious nodes and exclude them in order to avoid deception by attackers. Accurate and appropriate methods that are usually iterative algorithms such as gradient descent, least median square (LMdS) and voting based secure localization have been introduced in the recent literature. Gradient descent based secure localization has better performance in terms of convergence speed and accuracy while have the minimum complexity compared to the other methods, however, still more convergence speed is needed for real-time applications. In this paper, a new gradient based method has been introduced which has higher convergence speed among all existing algorithms and the probability of fault for this algorithm is less than other algorithms. The other advantage of the proposed method is its low complexity in comparison to the other methods and its capability to be implemented in hardware. Simulation results show that the introduced algorithm's convergence speed is about 10 times more than the gradient descent algorithm with same localization error.

International Journal of …, Jan 1, 2012

In this paper, a new PCA based method for video compression is introduced. This method extracts t... more In this paper, a new PCA based method for video compression is introduced. This method extracts the features of video frames and process them adaptively based on required accuracy. This idea improves the quality of compression effectively. In this paper, we focused on the fact that video is a composition of sequential and correlated frames, so we can apply the PCA to these high correlated frames. Most of other video compression methods use DCT transform to compression. DCT causes to large damage in the edges of frames which plays fundamental role in quality of video. Our method in this paper doesn't reduce the bandwidth of frequency response, so the edges of frames don't fade.

2nd World Conference on Information …, Jan 1, 2011

Face images could be projected onto a feature space that the variation among them can be expresse... more Face images could be projected onto a feature space that the variation among them can be expressed better. The face space is defined by the ldquoeigenfacesrdquo, which are the eigenvectors of the faces set; they do not necessarily correspond to the isolated features such as eyes, ears, and noses. Using eigenfaces decreases the huge amount of the required memory to

International Journal of Computer Applications, 2015

Principal Component Analysis (PCA) is an efficient method for compressing high dimensional databa... more Principal Component Analysis (PCA) is an efficient method for compressing high dimensional databases [1]. For image compression, it is called Hotelling or KL transform. The central idea of PCA is to reduce the dimensionality of a data set in which there are a large number of interrelated variables. [2] This reduction is achieved by transforming to a new set of variables, the principal components, which are uncorrelated, and which are ordered so that the first few retain most of the variation present in all of the original variables. Computation of the principal components reduces to the solution of an Eigen value-Eigen vector problem for a positive-semi definite symmetric matrix [2]. In spite of ordinary applications which utilize the PCA method for dataset compression, in this paper, a new method is introduced to compress a single image in RGB color space using the correlations between three Red, Green and Blue color domains.

6th International Symposium on Telecommunications (IST), 2012

ABSTRACT In Wireless Sensor Networks (WSNs), the received data from nodes are useful only when ac... more ABSTRACT In Wireless Sensor Networks (WSNs), the received data from nodes are useful only when accurate information about their locations is available. Many localization methods use some nodes that their locations are known by manual or by means of positioning systems such as GPS. These nodes are known as anchor or beacon nodes. In those applications of WSNs in which localization is very important, such as robotic land mine detection, battle field surveillance, etc., the anchor nodes may be attacked by unauthorized accesses in hostile environments and as a result, the localization system may face perturbation. Therefore, in recent literatures some secure localization methods have been introduced. Gradient descent is a low complex, secure and time efficient approach that marks some anchor nodes as attacked ones by using special algorithms and prunes them, then determines the position of sensors using the remaining anchor nodes. In this paper, it is shown that pruning these anchor nodes may cause to localization error increase. In other words, it is shown that in non-coordinated attacks, using the information sent by attacked anchor nodes can improve the localization accuracy. The simulation results show that by utilizing this technique, we can decrease the localization error up to 15%.

Communications on Applied Electronics, 2015

Besides ever increasing digital world, the importance of information security aspects becomes inc... more Besides ever increasing digital world, the importance of information security aspects becomes increasingly clear day by day. Several solutions are introduced to provide the required security for various applications and encryption is one of these solutions [2]. In image encryption, conventional algorithms encounter some kinds of complexity due to high amount of data that should be processed. In this paper, a new method is introduced for image encryption using PCA method. This algorithm is more advantageous especially in applications that integrity of database is more important, such as a prison and the prisoner's photo database. In such cases, the security system should provide two major requirements:1) avoid changing an image in the database and 2) hiding real images from unauthorized access. The simulation results show that the mentioned method is capable to manage these two requirements properly.

ICCKE 2013, 2013

ABSTRACT In many applications of Wireless Sensor Networks (WSNs) such as monitoring applications ... more ABSTRACT In many applications of Wireless Sensor Networks (WSNs) such as monitoring applications or routing, localization is one of the important issues that affect directly the network quality of operation. Secure localization in WSNs needs to detect malicious nodes and exclude them in order to avoid deception by attackers. Accurate and appropriate methods that are usually iterative algorithms such as gradient descent, least median square (LMdS) and voting based secure localization have been introduced in the recent literature. Gradient descent based secure localization has better performance in terms of convergence speed and accuracy while have the minimum complexity compared to the other methods, however, still more convergence speed is needed for real-time applications. In this paper, a new gradient based method has been introduced which has higher convergence speed among all existing algorithms and the probability of fault for this algorithm is less than other algorithms. The other advantage of the proposed method is its low complexity in comparison to the other methods and its capability to be implemented in hardware. Simulation results show that the introduced algorithm's convergence speed is about 10 times more than the gradient descent algorithm with same localization error.

International Journal of …, Jan 1, 2012

In this paper, a new PCA based method for video compression is introduced. This method extracts t... more In this paper, a new PCA based method for video compression is introduced. This method extracts the features of video frames and process them adaptively based on required accuracy. This idea improves the quality of compression effectively. In this paper, we focused on the fact that video is a composition of sequential and correlated frames, so we can apply the PCA to these high correlated frames. Most of other video compression methods use DCT transform to compression. DCT causes to large damage in the edges of frames which plays fundamental role in quality of video. Our method in this paper doesn't reduce the bandwidth of frequency response, so the edges of frames don't fade.

2nd World Conference on Information …, Jan 1, 2011

Face images could be projected onto a feature space that the variation among them can be expresse... more Face images could be projected onto a feature space that the variation among them can be expressed better. The face space is defined by the ldquoeigenfacesrdquo, which are the eigenvectors of the faces set; they do not necessarily correspond to the isolated features such as eyes, ears, and noses. Using eigenfaces decreases the huge amount of the required memory to