نشریه محاسبات نرم
سال هشتم شماره 1 (پیاپی 15، بهار و تابستان 1398)

Protecting the information access pattern, which means preventing the disclosure of data and structural details of databases, is very important in working with data, especially in the cases of outsourced databases and databases with Internet access. The protection of the information access pattern indicates that mere data confidentiality is not sufficient and the privacy of queries and accesses must also be ensured. This is because by observing userschr('39') queries, attackers can extract the relationships between the queries and obtain a knowledge of the database to decrypt details of the database structure. In this paper, for the outsourcing model, the storing methods that are appropriate for providing confidentiality and protecting the access pattern are described. Finally, a segmentation-based approach is presented to protect the access pattern for outsourced data. Compared to previous methods, experiment results indicate our proposed method provides an acceptable level of preventing the information disclosure as well as not imposing large overhead of storing, computation, and communication.

In this paper, a hybrid multi-objective algorithm consisting of features of genetic and firefly algorithms is presented. The algorithm starts with a set of fireflies (particles) that are randomly distributed in the solution space; these particles converge to the optimal solution of the problem during the evolutionary stages. Then, a local search plan is presented and implemented for searching solution neighbors to improve the quality of global solutions. This part of the algorithm is used to search sparsely populated areas for finding the dominant solutions. To improve the algorithm, for each firefly some changes have been made on the criteria of determining the global optimal solution and doing local optimal solution; this leads to more uniformity of the Pareto curve and error reduction, as the experimental results show. The proposed algorithm is an extension of a basic algorithm.

In power systems, reconfiguration is one of the simplest and most low-cost methods to reach many goals such as self-healing, reliability improvement, and power loss reduction, without including any additional components. Regarding the expansion of distribution networks, communications become more complicate and the number of parameters increases, which makes the reconfiguration problem infeasible using mathematical models. Therefore, using intelligent algorithms become candidate solutions. On the other hand, analysis of opened and closed switches should be without error and should be done in line with the network constraints like, tolerable current flow of each branch, permissible voltage of the busbars, and the line power flow. Therefore, among evolutionary algorithms, an algorithm with enough accuracy and convergence speed is used. In this study, the performance of binary bat, dragonfly, genetic, and PSO (Particle Swarm Optimization) algorithms is compared in the network reconfiguration IEEE 16-bus and 33-bus test systems with the aim of reaching a topology with the minimum loss in power and the maximum reliability. The results show that binary bat algorithm has the best performance among other algorithms.

With the rapid growth of smart device and Internet of things applications, the volume of communication and data in networks have increased. Due to the network lag and massive demands, centralized and traditional cloud computing architecture are not accountable to the high userschr('39') demands and not proper for execution of delay-sensitive and real time applications. To resolve these challenges, we propose a Virtual Mobile Fog Computing-based architecture through creating a layer between the smart phone applications and the cloud. Data storing and processing and secured communication are performed in this layer in the separate nodes that are independent of the cloud. Each of these nodes is implemented virtually on a single server. We presented a marker-based add-on reality with dynamic 3D display in Android smart systems and evaluated its functionality in a cloud-based and proposed architectures through 4G and Wi-Fi Internet networks. The evaluation results show the optimal performance of the proposed architecture in both communication networks. Moreover, they show the execution of high-volume 3D models using Wi-Fi in a Mobile Fog architecture is fast and convenient for real time applications.

A sensor network consists of a large number of sensor nodes that are distributed in a large geographic environment to collect data. Localization is one of the key issues in wireless sensor network researches because it is important to determine the location of an event. On the other side, finding the location of a wireless sensor node by the Global Positioning System (GPS) is not appropriate due to some limitations on sensor nodes such as price and physical size. In some localization approaches, sensor nodes specify their position with the help of anchor nodes, which have pre-configured positions. Due to error, low accuracy of distance detection method, and, most importantly, and the multi-hop distance of the sensor nodes from the anchors, the obtained position may not be accurate. In this paper, a distributed Particle Swarm Optimization (PSO) algorithm is proposed to estimate the position of the sensor nodes using anchors. In the proposed approach, the average hop length and the number of hops between a sensor node and the anchors are used to determine the estimated positions. The simulation results, as well as the comparison of the proposed algorithm to others, in terms of the average localization error, indicate that our approach leads to more accurate localization.

Heart is one of the most important members of the body, and heart disease is the major cause of death in the world and Iran. This is why the early/on time diagnosis is one of the significant basics for preventing and reducing deaths of this disease. So far, many studies have been done on heart disease with the aim of prediction, diagnosis, and treatment. However, most of them have been mostly focused on the prediction of heart disease. The purpose of this study is to develop models for heart disease diagnosis using machine learning, neural network, and deep learning algorithms. The models have been developed using the Cleveland heart disease dataset from University of California Irvine (UCI) repository. After complete data processing, including outlier detection, normalization, discretization, feature selection and feature extraction, the dataset is transformed into two normalized data and discretized data, according to the nature of the algorithms. Moreover, in constructing models of machine learning and neural networks, two randomized searches with cross-validation and grid search with Talos scan approaches are used for model tuning. Among evaluated models, including decision tree algorithms, random forest, support vector machine (SVM) and XGBoost, the highest accuracy is 92.9% using SVM, and among neural network models, multilayer perceptron (MLP) has resulted in the highest accuracy of 94.6%.