فهرست مطالب s. j. mirabedini

Today, with the increasing spread of science, the use of decision support systems can be of great help in the therapeutic policies of the Doctor. For this purpose, the use of artificial intelligence systems in predicting and diagnosing breast cancer, which is one of the most common cancers among women, is being considered. In this study, the process of diagnosis of breast cancer is done by using multistage weights in the MLP neural network in two layers. In the first layer, the three classifiers are trained simultaneously on the learning set data. Upon completion of the training, the output of the classifier of the first layer is accumulated together with the learning set data in the new sets. This set is given as an input to the second layer superconductor, and the supra-class mapping maps between the outputs of each of the ordinary classifiers of the first layer with the actual output classes. The three-layer structure of the first layer, as well as the second-layer supraclavicle, is a MLP neural network that optimizes the weights, effective properties and the size of the hidden layer simultaneously using an innovative genetic algorithm. In order to evaluate the accuracy of the proposed model, the Wisconsin database is used, which was created by the FNA test. Experiment results on the WBCD dataset the accuracy is 98.72% for the proposed method, which is relative to GAANN, CAFS algorithms provide better performance.

Cloud computing is one of the newest developments in information technology and has been widespread in the industry and different educational sectors over time. Cloud computing is not a new technology, but it is also a new method for providing services via the Internet. Cloud computing is a new concept as a storage of virtualized resources and it increases the efficiency, saves the hardware resources, and enhances the computing power. The load balancing is one of the main concerns in cloud computing space; and it can increase the speed, efficiency, customer satisfaction and reduce the response time in the case of proper performance. This paper also studies the problems of load balancing in cloud computing and introduces several load balancing algorithms. Finally, an algorithm is proposed and evaluated to improve the load balancing in cloud computing space. Our proposed algorithm utilizes the combination of fuzzy and min-max algorithms; and we have found that our algorithm has better performance than the non-fuzzy algorithm in most of the cases.

Any real world activity deals with a series of imprecise data. Managing this type of data using classic database systems leads to a tremendous loss of knowledge, and this issue necessitates the use of advanced database modeling techniques. Applying fuzzy theory and modeling to classic databases can be a basis for intelligent information processing. In recent years, XML has become a very important standard language and structure especially for exchanging and displaying web-based information. Many researches have been performed to assess and expand the XML and imprecise data literature, but many few have assessed the concept of imprecise data within XML. In this study, fuzzy logic is merged into XML concept to reach a suitable solution for object-oriented database queries. By combining SQL and XML we can provide an independent language and database for storing and retrieving queries. This paper examines the queries in two forms of simple and complex queries. In complex queries, the focus is more on conjunctive queries. These queries are then expressed with fuzzy XML tags. The results of this paper show that the proposed method is able to support fuzzy queries with hypertext markup language.

Agile enterprise architecture is developed in a process called enterprise architecture process. This process is complex and the architect can use a framework to regulate its structure and use a style to guide its behavior in order to control its complexity. In architecture, behavior precedes structure and with a structure, it is possible to have various behaviors. One of the factors with which, one can determine which one of these behaviors is more appropriate for agile enterprise architecture, is architecture performance assessment. A non-functional requirement in agile enterprise architecture is efficiency, and one of the system efficiency parameters is response time which has been used in this research. For this purpose, and in order to regulate and organize enterprise architecture descriptions, it is necessary to use a framework. DODAF, unlike Zachman framework which has six viewpoints, consists of three different viewpoints. Unified Modeling Language (UML), makes it possible that the products of this framework, be shown with a unified modelling symbol. The aim of this research is to provide a method to assess the efficiency of agile enterprise architecture to achieve a proper architecture. In this research, using Zachman-based frameworks, first, the characteristics of the desired enterprise are described using UML diagrams. In the following, these diagrams which are mainly behavioral and structural, are turned into official models. UML-related clichés which are usually placed as marginal graphics on UML diagrams will be used for this purpose. It will be possible to assess non-functional requirements on official models. In the proposed method, we will assess the efficiency of agile enterprise architecture in the design and pre-implementation phases. Research results show that with the provision of a model in the design phase, heavy implementation costs will be avoided.

The development of complex software systems Wants models that non-functional requirements evaluation of systems do in the development process, especially in the early stages. Architecture evaluation is done in different ways Hence need to have a way to integrate non-functional requirements. This Paper, MVC design pattern show in the form of framework based on extensible markup language for evaluating performance non-functional requirements. This framework is based on Petri nets that help can be it provided the MVC design pattern. The current study compared with RelatedWork provides Take advantage of Extensible Markup Language,   To address non-functional requirements and will be drawn an executable model of the application.