): Association of Information & Communication Technology of Iran 6 19 2015 6 1 Using a Hybrid PSO-GA Method for Capacitor Placement in Distribution Systems 1 10 FA Mohammad Hadi Varahram Amir Mohammadi In this paper, we have proposed a new algorithm which combines PSO and GA in such a way that the new algorithm is more effective and efficient.The particle swarm optimization (PSO) algorithm has shown rapid convergence during the initial stages of a global search but around global optimum, the search process will become very slow. On the other hand, genetic algorithm is very sensitive to the initial population. In fact, the random nature of the GA operators makes the algorithm sensitive to the initial population. This dependence to the initial population is in such a manner that the algorithm may not converge if the initial population is not well selected. This new algorithm can perform faster and does not depend on initial population and can find optimal solutions with acceptable accuracy. Optimal capacitor placement and sizing have been found using this hybrid PSO-GA algorithm. We have also found the optimal place and size of capacitors using GA and PSO separately and compared the results.

): Association of Information & Communication Technology of Iran 6 19 2015 6 1 A Hybrid Neural Network Ensemble Model for Credit Risk Assessment 11 28 FA sha'ban Elahi Tarbiat Modares University ahmad ghodselahi Tarbiat Modares University Hamidreza Naji Shahid Beheshti University Banking is a specific industry that deals with capital and risk for making profit. Credit risk as the most important risk, is an active research domain in financial risk management studies. In this paper a hybrid model for credit risk assessment which applies ensemble learning for credit granting decisions is designed. Combining clustering and classification techniques resulted in system improvement. The German bank real dataset was used for neural network training. The proposed model implemented as credit risk evaluation multi agent system and the results showed the proposed model has higher accuracy, better performance and lesser cost in applicant classification when compared with other credit risk evaluation methods.

): Association of Information & Communication Technology of Iran 6 19 2015 6 1 Analysis of the current situation ICT in rural areas of the country (using the Delphi Method) 29 40 FA Mohsen heidary Hassan Sedighi Nowadays, information and communication technology as a central management tool and has been running world. The development of information and communication technology in a rural community needs accurate planning can facilitate rural development. In our country size of the country,s population and 40 percent of the rural population, especially in rural economic development role in national development and village lack access to facilities and urban services, which are necessary for the effective and appropriate strategies for the development and use of rural conditions of our ICT services. The main purpose of this study was to investigate the difficulties and challenges of the current status of ICTin rural area of the country. The Delphi technique has been used for this purpose. The study group consisted of 30 members expert in agricultural development, rural planning, information technology and is well aware of rural ICT. Based on results, the general problems of rural ICT development in the country are five categories, there are problems of infrastructure, education, support, social and cultural policies and planning. With regard ti the most difficult problems in the development of ICT infrastructure and rural education in the country , Therefore, policymakers and rural development is expected to overcome the problems of rural ICT infrastructure in the country to tale the necessary steps. The villagers are familiar with computers and internet courses will be held in the villages. 

): Association of Information & Communication Technology of Iran 6 19 2015 6 1 A study on visual cryptography and providing a proposed method for color images cryptography 41 58 FA Naghmeh Mohamadi khajeh nasir toosi university of technology shahriyar mohammadi khajeh nasir toosi university of technology Visual cryptography is a method that makes use of the characteristics of human vision and it requires neither the knowledge of cryptography nor the complex calculations. This method was first proposed by Naor and Shamir, its implementation is simple, it has been extended to an secrect sharing (k, n) in which n shares are made from the image and they are distributed among n participants. Moreover, the image can be retrieved with k shares and their assembling onto each other however, the image is not retrievable with k-1 shares. Colors are represented using a combination of reflected lights from objects in the subtractive model. A wide range of colors is made with the mixture of cyan (C), magenta (M) and yellow (Y) and the combination of blue (B), red (R) and green (G) results in black in this model and also, the combination of these colors with white creates the same colors. This paper presents a visual cryptography proposal for colored images that divides a colored image into some shares after converting it to halftone images based on white and black visual cryptography and their rules are in accordance with the subtractive model of colors.

): Association of Information & Communication Technology of Iran 6 19 2015 6 1 Applying genetic algorithm for automatic service identification based on quality metrics 59 78 FA Saeed Parsa Iran University of Science and Technology Masoud Bagheri Imam Hossien University Jan Mohammad Rajabi Imam Hossien University Ali Akbar Azizkhani Imam Hossien University Service-oriented architecture improves the stability and operational capability of software systems for passive defense measures. Automatic identification of services using quality of service measures ensures the successful deployment of service-oriented architecture and is great importance to speed up software development life cycle. Little attention to non-functional requirements, no considerations for concurrent effects of business activities and entities and non-automated ranking of candidate services are the major issues with current approaches. The approach proposed in this paper considers both the business processes and entities, simultaneously to detect services. Applying a genetic algorithm, candidate services are identified based on quality metrics i.e. granularity, coupling, cohesion and convergence. These metrics are obtained from breaking goals to requirements of level. The TOPSIS method is applied to rank the candidate services. The illustrated case study is shown that high quality services can be identified automatically with minimal software developer’s interventions.