per Iranian Research Institute for Electrical Engineeringفصلنامه مهندسی برق و مهندسی کامپيوتر ايران16823745168237452012-06102319articleH. Bankibabamir@kashanu.ac.ir1V. Ahmadi Sabetv.ahmadisabet@gmail.com2Software developers face the problem of adopting a suitable formal method to developing their software. We aim to determine capability level of formal methods in software specification and analysis in four steps. The first step introduces the criteria by which the formal methods assess. The second and third ones deal with categorizing sorts of software and formal methods based on their solution methods. The fourth step determines fitness of some typical formal methods to specification and analysis of each software category.http://ijece.org/Article/28028Software specification and verification Formal methods software categorization state based event basedper Iranian Research Institute for Electrical Engineeringفصلنامه مهندسی برق و مهندسی کامپيوتر ايران16823745168237452012-061022030articleZ. Ahmadieng_20042005@yahoo.com1 brnjkb@cc.iut.ac.ir2One of the important requirements of sensor networks is synchronization of the nodes. The importance of time in sensor networks causes the adversary tries to disturb time synchronization by altering and faking messages, delaying or replying them, compromising the nodes and sending false messages via them. Up to now, there is no method that is able to provide both synchronization and security needs of sensor networks simultaneously. In this paper, we suggest a method that is capable to provide precise synchronization, along with low communication and computational overhead, low convergence time and high security against internal and external attacks. Simulation and analytic results show the preference of our method compared to other available methods.http://ijece.org/Article/28029Wireless sensor network synchronization secure synchronization pulse delay authentication compromised nodeper Iranian Research Institute for Electrical Engineeringفصلنامه مهندسی برق و مهندسی کامپيوتر ايران16823745168237452012-061023139articleF. Sakifatemeh.saki@utdallas.edu1A. Tahmasbia.tahmasbi@utdallas.edu2Shahriar Baradaran Shokouhibshokouhi@iust.ac.ir3University of Science and TechnologyUniversity of Science and TechnologyFast and accurate classification of benign and malignant patterns in digital mammograms is of significant importance in the diagnosis of breast cancers. In this paper, we develop a new Computer-aided Diagnosis (CADx) system using a novel Opposition-based classifier to enhance the accuracy and shorten the training time of the classification of breast masses. We extract a group of Breast Imaging-Reporting and Data System (BI-RADS) features from preprocessed mammography images and feed them to a Multi-Layer Perceptron (MLP). The MLP is then trained using a new learning rule which we will refer to as the Opposite Weighted Back Propagation (OWBP) algorithm. We evaluate the performance of the system, in terms of classification accuracy, using a Receiver Operational Characteristics (ROC) curve. The proposed system yields an area under ROC curve (Az) of 0.924 and an accuracy of 92.86 %. Furthermore, the speed analysis results suggest that, with the same network topology, the convergence rate of the proposed OWBP algorithm is almost 4 times faster than that of the traditional Back Propagation (BP) algorithm.http://ijece.org/Article/28030BI-RADS CADx system feature extraction mammography images opposition-based classifierper Iranian Research Institute for Electrical Engineeringفصلنامه مهندسی برق و مهندسی کامپيوتر ايران16823745168237452012-061024046articleM. A. Saadatjoosaadatjoo@grad.kashanu.ac.ir1V. Derhamivderhami@yazduni.ac.ir2فاطمه سعادت جوfatemehsaadatjoo@gmail.com3Yazd UniversityUsing Information Technology techniques have been increased complication and dynamicity of supply-and-demand systems like auctions. In this paper, we introduce a novel method by applying Reinforcement Learning (RL) price offer as one of the robust methods of agent learning which can be used in interactive conditions with minimum level of information in auction and reverse auction. Negotiation as one of the challengeable and complicated behaviors is caused an agreement on price in auctions. The main aim of our method is maximizing seller’s and customer’s profits. We formulate seller and customer selection in form of two different RL problems. All of the RL parameters like states, actions, and reinforcement function are defined. Also, we describe an experimental method to compare with our proposed method for proving advantages of our method.http://ijece.org/Article/28031Reinforcement learning price offer seller and customer selection negotiationper Iranian Research Institute for Electrical Engineeringفصلنامه مهندسی برق و مهندسی کامپيوتر ايران16823745168237452012-061024754articleGh. A. Montazermontazer@modares.ac.ir1N. Rastegar Ramshesamane.rastegar@gmail.com2Alireza Askarzadeha.askarzadeh@kgut.ac.ir3Tarbiat Modares Universityدانشگاه تحصیلات تکمیلی صنعتی و فنّاوری پیشرفته کرمانMost of the time effective decisions in strategic situations such as competitive issues require a non-linear mapping between stimulus and response. Artificial neural networks can be an appropriate way for modeling and solving these kinds of problems. Prison Dilemma Game is a well-known game that is proposed in game theory. This paper tries to describe how using neural network, the iterated prisoner’s dilemma game can be modeled and analyzed. To do this a Grossberg Counter-Propagation Neural Network (GCP-NN) has been designed to play this game. Results show the capability of this method in complete modeling game. The results present the efficiency of the new method in comparison with the two conventional methods: Tit For Tat (TFT) strategy and Perceptron modeled game.http://ijece.org/Article/28032Prison dilemma game artificial neural network Grossberg counter propagation neural network TFT strategyper Iranian Research Institute for Electrical Engineeringفصلنامه مهندسی برق و مهندسی کامپيوتر ايران16823745168237452012-061025562articleB. Ghazanfaribe_ghazanfari@ieee.org1N. Mozayanimozayani@iust.ac.ir2M. R. Jahed Motlaghjahedmr@iust.ac.ir3University of Science and TechnologyExtracting bottlenecks improves considerably the speed of learning and the ability knowledge transferring in reinforcement learning. But, extracting bottlenecks is a challenge in reinforcement learning and it typically requires prior knowledge and designer’s help. This paper will propose a new method that extracts bottlenecks for reinforcement learning agent automatically. We have inspired of biological systems, behavioral analysts and routing animals and the agent works on the basis of its interacting to environment. The agent finds landmarks based in clustering and hierarchical object recognition. If these landmarks in actions space are close to each other, bottlenecks are extracted using the states between them. The Experimental results show a considerable improvement in the process of learning in comparison to some key methods in the literature.http://ijece.org/Article/28033Reinforcement learning object clustering hierarchical reinforcement learning temporally extended actions