نشریه مهندسی برق و مهندسی کامپیوتر ایران
سال چهاردهم شماره 3 (پیاپی 40، پاییز 1395)

In this paper, a new method for resolution enhancement of single document images is presented. The proposed method is example based using an example set of low-resolution and high-resolution training patches. According to the Bayes rule, one function is considered as the likelihood or data-fidelity term that measures the fidelity of the output high-resolution to the input low-resolution image. As well, three other functions are considered as the regularization terms containing the prior knowledge about the desired high-resolution document image. Three priors which are fulfilled by the regularization terms are bimodality of document images, smoothness of background and text regions, and similarity to the patches in the example set. By minimizing these four energy functions through the iterative procedure of asynchronous sequential gradient descent, the HR image is reconstructed. Instead of synchronous minimization of the linear combination of these functions, they are minimized in order and according to the gradual changes in their values and in the updating HR image. Therefore, determining the coefficients of the linear combination, which are variable for input images, is no longer required. In the experimental results on twenty document images with different fonts, at different resolutions, and with different amounts of noise and blurriness, the proposed method achieves significant improvements in visual image quality and in reducing the computational complexity.

A desirable software application should be able to provide the quality attributes required by the system, as well as the functional requirements. Software architecture styles have a significant effect on the quality attributes of the designed software as well as its specification and decomposition.) The quantity evaluation and analysis of this effectiveness rate result in the selection of the most appropriate style for designing the architecture. In this paper, a method based on the Colored Petri Net is proposed to quantitatively evaluate three candidate attributes of the software architectural styles called the quality attributes, performance, reliability, and security in three candidate styles named shared-data, object-oriented, and pipe-and-filter software architectural styles. This method has not limitations of the previous-ones in evaluating the quality attributes. In this method, the candidate styles are firstly modeled by using the Colored Petri Net; then, considering the evaluation rules, CPN tools are used to analyze the networks and calculate the exact value of the candidate attributes. At the end, the best candidate style is chosen for implementation through ranking the styles in terms of the satisfaction level of the candidate quality attributes. To present a practical representation using the proposed methodology, the ATM system has been chosen as a case study.

Texture classification is one of the important branches of image processing. The main point of texture classification is feature extraction. Local Binary Pattern (LBP) is one of the important methods that are used for texture feature extraction. This method is widely used because it has simple implementation and extracts high discriminative features from textures. Most of previous LBP methods used uniform patterns and only one feature is extracted from non-uniform patterns. In this paper, by extending non-uniform patterns a new mapping technique is proposed that extracts more discriminative features from non-uniform patterns. So in spite of almost all of the previous LBP methods, the proposed method extracts more discriminative features from non-uniform patterns and increases the classification accuracy of textures.
The proposed method has all of the positive points of previous LBP variants. It is a rotation invariant and illumination invariant method and increase the classification accuracy. The implementation of proposed mapping on Outex dataset shows that proposed method can improve the accuracy of classifications significantly.

In this paper a weighted Fuzzy min-max classifier (WL-FMM) which is a type of fuzzy min-max neural network is described. This method is a quick supervised learning tool which capable to learn online and single pass through data. WL-FMM uses smaller size with higher weight to manipulate overlapped area. According to experimental results, proposed method has less time and space complexity rather than other FMM classifiers, and also user manual parameters has less effect on the results of proposed method.

An Ultra-Large-Scale (ULS) system is generally considered as a system-of-systems that have many crosscutting concerns. As the size of a system-of-systems grows, and interoperability demands between the sub-systems are increased, achieving more scalable and dynamic integration of sub-systems becomes a major challenge. In this integration, each sub-system has its own domain that may have independent policies. Over the last few years, the notion of Rich Services has emerged as a technique for facilitating integration of systems. In this paper, a Data-Centric Rich Services (DCRS) approach is proposed to improve the dynamicity, scalability, and security of Rich Services in a ULS system. In the proposed approach, a two-layer and data-centric middleware is presented to manage orchestration of Rich Services. The lower layer is a Data Distribution Service (DDS) middleware used for data-centric, publish-subscribe, real-time, and loosely-coupled communication among Rich Services. The upper layer is used for dynamic and secure configuration and reconfiguration of Rich Services. We also analyze the performance of our approach using simulation-based experiments.

Quantum-logic synthesis refers to generating a quantum circuit for a given arbitrary quantum gate according to a specific universal gate library implementable in quantum technologies. Previously, an approach called block-based quantum decomposition (BQD) has been proposed to synthesize quantum circuits by using a combination of two well-known quantum circuit synthesis methods, namely, quantum Shannon decomposition (QSD) and cosine-sine decomposition (CSD). In this paper, an improved block-based quantum decomposition (IBQD) is proposed. IBQD is a parametric approach and explores a larger space than CSD, QSD, and BQD to obtain best results for various synthesis cost metrics. IBQD cost functions for synthesis are calculated in terms of different synthesis cost metrics with respect to the parameters of the proposed approach. Furthermore, in order to find optimum results according to these functions, IBQD synthesis approach is defined as a constrained-optimization model. The results show that IBQD can lead to the minimum total gate cost among all the proposed approaches for the specific case of 4-qubit quantum circuit synthesis. Moreover, for the first time, the depth costs of the CSD, QSD, BQD, and IBQD synthesis approaches are evaluated and it is shown that IBQD makes a trade-off between the total gates and depth costs for the synthesized quantum circuits.

Insider attack is one of the most dangerous threats for the security of a critical infrastructure (CI). An insider attack occurs when an authorized operator misuses his/her permissions in order to perform malicious operations in the CI. Providing too many permissions for an operator may backfire when the operator abuses his/her privileges, either intentional or unintentional. Therefore, an access control model is required to provide necessary permissions in order to prevent malicious operations. In this paper, a hybrid access control model (HAC) has been proposed for CI applications which are monitored and controlled by a CIM (IEC-61970-301 common information model)-based supervisory control and data acquisition system. The proposed HAC is an extension of the mandatory and role-based access control models. In the proposed model, the permissions of an operator will be determined according to the predefined types of responsibilities, grid statuses, activation times of roles, security levels, and their periods of validity. A colored Petri-net is employed to simulate and illustrate the effectiveness of the proposed HAC.

Opinion mining deals with an analysis of user reviews for extracting their opinions, sentiments and demands in a specific area, which plays an important role in making major decisions in such areas. In general, opinion mining extracts user reviews at three levels of document, sentence and feature. Opinion mining at the feature level is taken into consideration more than the other two levels due to orientation analysis of different aspects of an area. In this paper, one method is introduced for a feature extraction. The recommended method consists of four main stages. First, opinion-mining lexicon for Persian is created. This lexicon is used to determine the orientation of users’ reviews. Second, the preprocessing stage includes unification of writing, tokenization, creating parts-of-speech tagging and syntactic dependency parsing for documents. Third, the extraction of features uses the method including dependency grammar based feature extraction. Fourth, the features and polarities of the word reviews extracted in the previous stage are modified and the final feature's polarity is determined. To assess the suggested techniques, a set of user reviews in both scopes of university and cell phone areas were collected and the results of the method were compared with frequency-based feature extraction method.