مجله رایانش نرم و فناوری اطلاعات
سال پنجم شماره 2 (تابستان 1395)

This paper presents a new approach for modeling the normal behaviors and detecting the abnormal behaviors. The approach consists of several main steps. First, using a detection method, the foreground and background regions are separated. Then, the busy-idle rates are defined as the behavioral features and, based on these features, a behavioral model is extracted for each pixel block. In the following, spectral clustering is used to classify the normal behaviors on the condition that a set of normal data is provided. In the classification process, the pixel blocks with similar behaviors are grouped together. A behavioral model is defined for each group of the blocks with similar behaviors. The behavioral model adopted in this paper is Hidden Markov Model. The results of the obtained classification and normal behaviors are used to detect the abnormal behaviors; i.e., based on the normal-behavior model for each cluster, if the observation sequence probability given by the normalbehavior model is lower than the threshold level, the pixel block is identified as the region in which the abnormal behaviors happened. The experimental results obtained from video data confirm the efficiency, accuracy, and speed of the approach adopted in this paper.

Energy constraint in wireless sensor networks, have been made the packets routing with essential issues. In event based applications, the inherent constraint of these networks and large packet traffics affects the networks lifetime. Hence, the energy of sensor nodes near the sink node will be exhusted and the duty of WSNs will be affected with this problem. Network coding scheme with encoding and decoding of data packets, have improved the throughput, reduces the average end-to-end delays and resilient the networks against the fails. In this paper, we proposes a routing algorithm using network coding scheme. For selecting appropriate routing paths, the proposed scheme considers the link quality and residual energy of neighbor nodes. Simulation results show that the proposed scheme increases the network reliability and decreases the energy consumption in comparing with other relate scheme.

There are several ways for bandwidth allocation for users acting based on policy of network administrators in computer networks. Due to the diversity of users and so amount of bandwidth usage per user, providing suitable bandwidth rate to meet their needs in various situations play an important role in terms of performance and implementation of bandwidth management systems. In this paper, we propose a dynamic and balanced approach, called normal weight allocation for determining amount of bandwidth for each user taking into account the importance of user in caomparision with other online concurrent users. In this regard, to obtain a user weight as the importance of user, we apply Fuzzy AHP technique for eliciting indecisive expert ideas. Ease of implementation and taking the advantage of maximal usage of available bandwidth are the features of the proposed approach.

In recent years, due to the use of data warehouses, the subject of materialized view maintanance is important. For quick access to data, data warehouses collect the necessary data from various sources and stored them to form of materialized views. This leads to increased speed of responding to queries. When the data changes over different resources, the materialized views should be updated that leads to the subject of view maintanence. At this time, algorithms are presented in order to view maintanance with optimized cost. The algorithm presented in this paper is the combining of a mathematical method with Cultural meta-heuristic algorithm that leads to reduce search time and optimizes the cost of access to data in data warehouses. Cultural algorithm uses a reasonable belief space, including several incremental view maintenance relations. The best response obtained at the end of every generation is stored in the space called the belief space. The tests showe that Cultural algorithm is faster to maintain incremental views compared to previous methods and algorithms like bacterial and bees and learning tlbo algorithm.

The powerfulness and effectiveness of the optimization methods are motivations of the researchers to use them in complex engineering problems. In this paper, the performance of the three optimization algorithms based on swarm intelligence ( IPO, PSO) and evolutionary technique (GA) for calculation the channel's widths of the transistors were evaluated compared with each others. The fitness functions are defined in order to the better integration and to improve the power consumption and delay of Level Shifter circuit (LS) with changing the voltage level of 0.4 to 3 volts using 0.35-um CMOS technology .Simulation results for the sample circuit show that it reach a power consumption of 0.222pW and a delay value of 9.113ns with PSO algorithm, a power consumption of 0.39 nW and delay value of 3.741 ns with IPO algorithm, and values of 0.235 nW and 3.711 ns whit GA algorithm. In addition to a dramatic improvement in power and delay, minimum of channel's widths also were obtained. All implementations of paper were performed in MATLAB and HSPICE.

Peer to peer network is a set of self-adaptive and identic nodes that cooperate together without the central coordinator. Mobile peer to peer network is caused from the implementation of peer to peer network over mobile Ad-hoc networks’ platform. The distributed structure of these networks reinforces the resource searching. The requests in these networks are often propagated randomly and broadcast. Thus, designing a self- adavptive mechanism that sends the request intentionally to the network is crucial, to be able to discover the demanded source of the request with the maximum amount of success rate and minimum amount of energy and traffic load. In this research is presented solution with the aim of improving serach on the mobile peer to peer network. Learning automata are adaptive decision making units which run in random environments that learn the optimal action through repeated interaction with its environment.In the proposed algorithm, each node having a message sends a search request to some more useful neighbors. Correspondingly the best route from the source node will transmit the requested resource. Moreover Because of saving result in neighbourse cache table, Neighbourse experince are effective in future forwards. The simulation results of the proposed algorithm and comparison with the “Gossiping Load Balancing alghorithm” algorithm and “Imporoved Adaptive Probablitistic Search”, show that avoiding selecting random neighbors for forward request and considering the history of each node using the results stored in cache tables, reduce energy consumption, the number of sended and droped network packets , and the networkload. Since, due to the influence of neighboring nodes in proceeding, the request message is sent to the neighbors who have been more successful in previous searches, the success rate of the network also increases.

3D urban reconstruction with access to geometric and visual information is used by many organizations. In this regard, using stereo panorama as an image-based method is attended by many manufacturers and users of the urban maps because of the simplicity and providing real visibility. In this paper, a new stereo panorama system based on stereo cameras (that is patented) is presented and three-dimensional reconstruction of urban environments using the system is expressed. Moreover in this article, the process of registration between the stereo panoramic images at different stations is also described to cover whole area. Finally, geometric and visual reconstruction of part of a street was evaluated by the mentioned stereo panorama system. The results of the reconstruction of the environment revealed that unlike most stereo panorama systems in which access to geometric information is sometimes difficult, in the proposed method, in addition to providing a visual space of the environment, geometric measurements is easily possible and achieving the desired accuracy that is needed in urban projects (large map with scale of 1:1000) is possible.