Tehrān, Iran
Tehrān, Iran

Time filter

Source Type

Samimi H.,ICT Research Institute
Wireless Personal Communications | Year: 2016

In this paper, we consider a free-space optical communication system using subcarrier intensity modulation (SIM) with general-order rectangular quadrature amplitude modulation (QAM) and operating over Gamma–Gamma turbulence channels subjected to pointing errors. We derive novel, exact closed-form expression for the average symbol error probability of the considered system in terms of the Fox H function. Using the derived analytical results, we investigate the combined effects of turbulence-induced fading and misalignment-induced fading on the performance of the SIM-QAM FOS communication system. Numerical and computer simulation results are presented in order to verify the accuracy of the proposed mathematical analysis. © 2016 Springer Science+Business Media New York

Darabi A.,ICT Research Institute | Baroud G.,Université de Sherbrooke
2015 2nd International Conference on Pattern Recognition and Image Analysis, IPRIA 2015 | Year: 2015

Trabecular bone consists of a network of tiny strands and plates. Micro-structural features of trabecular bone include thickness, relative volume, spacing and connectivity. The accurate evaluation of these features is of significant interest in the assessment of the mechanical and transport properties of bone. Extracting these features from μCT and μMRI images is difficult and measurements vary substantially according to image processing technique used. In this paper, we propose a fuzzy distance transform (FDT) method to measure trabecular bone thickness based on Min-Max operations and using an additive weighting term. Due to the employed fuzzy Min-Max operations along with the additive weighing term, the FDT method is performed in integer number space to consequently produce a computationally fast, robust and efficient use of memory method with taking into account the gray level of pixels. This method has been used to measure the trabecular thickness of bone samples with different bone volume fractions (BVF). Additionally, its performance was studied considering parameters such as image resolution, object rotation, noise and running time. The algorithm has proven to be very robust, precise and faster. © 2015 IEEE.

Zarei M.,Islamic Azad University at Tehran | Rahmani A.M.,Islamic Azad University at Tehran | Samimi H.,ICT Research Institute
Wireless Networks | Year: 2016

Speed variation is one of the main challenges in deriving the connectivity related predictions in mobile ad-hoc networks, especially in vehicular ad hoc networks (VANETs). In such a dynamic network, a piece of information can be rapidly propagated through dedicated short-range communication, or can be carried by vehicles when multihop connectivity is unavailable. This paper proposes a novel analytical model that carefully computes the connectivity distance for a single direction of a free-flow highway. The proposed model adopts a time-varying vehicular speed assumption and mathematically models the mobility of vehicles inside connectivity. According to the dynamic movability scenario, a novel and accurate closed form formula is proposed for probability density function of connectivity. Moreover, using vehicular spatial distribution, joint Poisson distribution of vehicles in a multilane highway and tail probability of the expected number of vehicles inside single lane in a multilane highway are mathematically investigated. The accuracy of analytical results is verified by simulation. The concluded results provide helpful insights towards designing new applications and improving performance of existing applications on VANETs. © 2016 Springer Science+Business Media New York

Asadi N.,ICT Research Institute | Badie K.,ICT Research Institute | Mahmoudi M.T.,ICT Research Institute
2016 2nd International Conference on Web Research, ICWR 2016 | Year: 2016

Scientific papers are continually increasing on the web and it is mandatory for the researchers to grasp on some powerful tools which are helpful in an efficient process of large amounts of data. Zone identification is a Natural Language Processing application which is to classify the sentences of scientific papers into a fixed set of zone categories. In this paper, we will propose an algorithm to identify some categories of zones in scientific papers. Regarding this, we make use of some significant lexical and syntactical features of the sentences standing for these categories in a particular way. In this respect, a sequence of sentences has been used. Experimental results show that these features are capable enough to identify the desired categories in a reasonable manner. © 2016 IEEE.

Moin M.-S.,ICT Research Institute | Sepas-Moghaddam A.,Islamic Azad University at Qazvin
Signal, Image and Video Processing | Year: 2013

JPEG compression standard is widely used for reducing the volume of images that are stored or transmitted via networks. In biometrics datasets, facial images are usually stored in JPEG compressed format and should be fully decompressed to be used in a face recognition system. Recently, in order to reduce the computational complexity of JPEG decompression step, face recognition in compressed domain is considered as an emerging topic in face recognition systems. In this paper, a novel coefficient selection method based on face segmentation has been proposed for selecting a limited number of zigzag scanned quantized coefficients in JPEG compressed domain, which led to an improvement in recognition accuracy and a reduction in computational complexity of the face recognition system. In the proposed method, different low frequency coefficients based on the importance of the regions of a face have been selected for recognition process. The experiments were conducted on FERET and FEI face databases, and PCA and ICA methods have been utilized to extract the features of the selected coefficients. Different criteria including recognition accuracy and time complexity metrics were employed in order to evaluate the performance of the proposed method, and the results have been compared with those of the state-of-the art methods. The results show the superiority of the proposed approach, in terms of recognition ranks, discriminatory power and time complexity aspects. © 2013, Springer-Verlag London.

Mohtaj S.,ICT Research Institute | Asghari H.,ICT Research Institute | Zarrabi V.,ICT Research Institute
CEUR Workshop Proceedings | Year: 2015

In this paper, we describe an approach to create monolingual English plagiarism detection corpus for the task of text alignment corpus construction in PAN 2015 competition. We propose two different obfuscation methods to fragment obfuscation for creating the cases of plagiarism. The first method is an artificial obfuscation which consists of variety of obfuscation strategies such as synonym substitution, random change of order, POS preserving change of order and addition/deletion. The second obfuscation method is a simulated obfusca-tion, in which the SemEval dataset is used for creating the cases of plagiarism by using pairs of sentences with their similarity scores.

Safdari R.,Islamic Azad University at Qazvin | Moin M.-S.,ICT Research Institute
2016 Artificial Intelligence and Robotics, IRANOPEN 2016 | Year: 2016

In recent years, the recognition of Farsi handwritten digits is drawing increasing attention. Feature extraction is a very important stage in handwritten digit recognition systems. Recently deep feature learning got promising results in English handwritten digit recognition, though there are very few papers in this area for Farsi handwritten digits. The contribution of this paper is to propose a new framework utilizing a two layer sparse autoencoder for feature learning directly from data and using the learned weights for feature extraction. In the classification stage of our proposed framework Softmax regression is applied. This recognition method is applied to Farsi handwritten digits in the HODA dataset. The experimental results support our claim that use of deep feature learning as feature extraction stage improves the performance compared with conventional methods. © 2016 IEEE.

Elyasi I.,Islamic Azad University at Tehran | Pourmina M.A.,Islamic Azad University at Tehran | Moin M.-S.,ICT Research Institute
Measurement: Journal of the International Measurement Confederation | Year: 2016

Ultrasound imaging suffers from severe artifacts caused by speckle noise. The paper introduces an algorithm for speckle noise reduction in breast cancer ultrasound images. Based on wavelet analysis and filtering, we employed a combination of homogeneity filtering and modified bayes shrink methods to remove noise while keeping the sharpness of important features. First, we replace pixel intensity by the mean of homogenous neighborhood and then, the threshold value of modified bayes shrink is employed to distinguish homogenous regions from regions with speckle noise obtained from homogeneity filtering. The proposed algorithm is called Homogeneity Modified Bayes Shrink (HMBS). A comparative study with other despeckling methods, using quantitative indices, showed the superiority of the proposed method over those methods. © 2016 Elsevier Ltd. All rights reserved.

Kahyaei S.,Islamic Azad University at Qazvin | Moin M.-S.,ICT Research Institute
2016 4th International Conference on Control, Instrumentation, and Automation, ICCIA 2016 | Year: 2016

Fingerprint recognition is a type of physiological biometrics. In this paper, a system is proposed for fingerprints matching. The proposed system contains three phases. In the first phase, which is preprocessing, background removal and contrast enhancement are performed. In the second phase, a series of features are extracted from the fingerprint patches using pseudo-Zernike moments. Finally, in the third phase, which is the recognition phase, the fingerprint matching is done using the Euclidean distance between the input samples and the stored templates. The proposed system is invariant to the size, translation and rotation of fingerprints, and is accurate and fast. The proposed system has been evaluated on two data sets of FVC 2004 and FVC 2006. It can be observed that the proposed method is more accurate than similar methods. © 2016 IEEE.

Mahmoudi M.T.,ICT Research Institute | Badie K.,ICT Research Institute | Valipour M.,Jundi Shapour University of Technology
Proceedings of 2015 International Conference on Interactive Collaborative Learning, ICL 2015 | Year: 2015

Educational contents and their corresponding construction methods have had an enormous change from traditional to electronic, and recently to multimedia and augmented reality based (AR-based) formats. Along with content edutainment trend, interaction and learning performance of audiences seem to have been improved. To validate this assumption, besides AR-based content construction, an appropriate pedagogical method should be applied, as well. According to the above mentioned point, in this paper, we try to demonstrate that a content superimposed by animation, sound, 3D images, etc. as exemplars of augmented reality, has the potential to improve/upgrade learner's learning performance. Within this context, students' learning style was first modeled through using the method of Felder-Silverman, and two types of content; one traditional and the other AR-based, were subsequently submitted to the test population. Students' learning performance was then assessed using T-Test. Experimental results indicate that, in contrast with traditional contents, AR-based content has the potential to exhibit promising characteristics in learning performance of those who interact with it. © 2015 IEEE.

Loading ICT Research Institute collaborators
Loading ICT Research Institute collaborators