Information Technology

Rough Set Theory provides a formal framework for data mining. Feature Selection or Attribute Reduction is a preprocessing step in data mining, and it is very effective in reducing dimensionality, reducing irrelevant data, increasing learning accuracy and improving comprehensibility. The fuzzy-rough feature selection algorithm was used to handle the continuous real-valued data as well as to handle noisy data. It was implemented by standard fuzzification techniques enabling linguistic labels to be associated with attribute values. It also provides uncertainty modeling by allowing the possibility of the membership value to more than one fuzzy label. In this paper, we use an Improved Quickreduct algorithm by redefining the lower and upper approximations based on fuzzy set theory. The membership degrees of feature values to fuzzy sets are exploited in the process of dimensionality reduction. The experiments are carried out on public domain datasets available in UCI machine learning repository and real Tuberculosis data set.

The estimation accuracy has been focused in various formal estimation models in recent research initiatives. The formal estimation models were developed to measure lines of code and function points in the software projects but most of them failed to improve accuracy in estimation. The concept of reusability in software development in estimating effort using artificial neural network is focused in this paper. Incorporation of reusability metrics in COCOMO II may yield better results. In COCOMO II it is very difficult to find the values of size parameters. A new model called COREAN has been proposed in this paper for better effort estimation accuracy and reliability. The proposed model has focused on two components of COCOMO II. First, instead of using RUSE cost driver, three new reuse cost drivers are introduced. Second, In order to reduce the project cost, three cost drivers such as PEXE, AEXE, LTEX are combined into single cost driver Personnel Experience (PLEX). Finally, this proposed model accuracy is more improved with the help of Enhanced RPROP algorithm and simulated annealing optimization technique.

As the modernization of government is growing, E-Government is a grand new domain in recent years. More and more data is sent to databases system and large amounts of data are accumulated. Abundant knowledge exists in those Historical data. Meaning is to analyze those historical data and find useful knowledge and rules from the mass of data to provide better decision support and better adjustment guidance. The concept and steps of data mining is introduced in particular. When we use the E-Government system to process data, we need to choose what data is useful and what kind of new information we can get from the log file or from the database. Because of the special characters of knowledge, this paper presents an algorithm of the fuzzy data mining, and put great importance on the steps of the Fuzzy data mining.

At the of 20th Century and as well as in this present time ,discussion about technology and information technology has special in many scientific and research assemblies . In recent years in our country this issue has received special attention. One of the helpful application of IT is in educational areas. This present article investing acted this issue specially and it has investigated IT in all dimensions .This article expressed the history of information technology usage in training and investigated the application of information technology in training and educational areas as well as analyzed this technology besides students and teachers and examined the relationship between education and information technology and expressed aids of this technology in students training as well as examined children training by parents.

The paper is to lay special emphasis on study to design new management system into current information management in order to expand a method such as a library management information system. Studying data resources on hand and a new system model for information service management have been formed and realized, and at the same time problems of the hidden dangers of data redundancy get solved. The new system is called as a post-information management and the current system called as a pre-information management system. Whole information management system (IMS) consists of two systems, PrIMS and PoIMS. PoIMS is main foundations of statistics and analysis data. We offer a post-information management system which focuses on design system at data statistics and analysis with formulas. It is applied the retrieval combined models under multi-restrictive conditions and theories to the lending book rates in a library with PoIMS.

Mobile banking system plays a major role in mobile commerce. As wireless networks are existed, today new generation of electronic commerce applications are emerged and expanded, that are known as mobile commerce. In this field one of services that served in bank industry with cell phones is mobile banking. Although many studies have been conducted to assess users’ satisfaction with mobile applications, none has focused on ranking the effective alternatives. So the goal of this article is to extract the effective alternatives of user’s satisfaction and rank them with VIKOR. The research extract 42 alternatives based on Delone and McLean’s Revised Model and chooses 21 effective alternatives by expert’s ideas and then ranking them. VIKOR shows that data accuracy and security are ranked as first and second alternatives.

AbstractIn this work, a neural network with chaos activation function has been applied as a pseudo-random number generator (PRNG). Chaotic neural network (CNN) is used because of its noise like behaviour which is important for cryptanalyst to know about the hidden information as it is hard to predict. A suitable adaptive architecture was adopted to generate a binary number and the result was tested for randomness using National Institute of Standard Technology (NIST) randomness tests. Although the applications of CNN in cryptography have less effective than traditional implementations, this is because these systems need large numbers of digital logic or even a computer system. This work will focus on applications that can use the proposed system in an efficient way that minimize the system complexity.

Sensor networks have been widely employed in many real-time applications. One of the most obvious challenges appearing to threaten the successful deployment of sensor networks is privacy issues including source-location privacy which can not be adequately addressed by general security mechanisms. Focusing on this important kind of privacy, among many approaches proposed in literatures, self-adjusting phantom routing is a very successful one. But it still has some weaknesses. In this paper, we propose an improved version of it to enhance its performance. This method can decrease energy consumption and communication cost while increase the accuracy of the aggregate locations by minimizing their monitored areas.

The purpose of this study was to investigate the influence of intelligent classroom and deepen student's learning speed. This analytical method and the method of data collection tools and library resources, articles and scientific sites are used. The results showed that the use of multimedia content in a wide range of senses of the students involved in the teaching and learning process is deepening. In other words, in addition to increasing the performance of various classes of applications due to the use of audio-visual senses to help students learn. The system allows students to move beyond their curricula and more emphasis on thinking skills and deep learning students. The intelligent interaction between students and teachers of the school, more intelligent, and this can lead to a higher share successful experiences between them. So schools by creating platforms for intelligent classes can take advantage of this training method used.

As man has started using computers to track the work of machines, the flexibility with which the humans communicate and request information from the computers must increase. There arises a need for the computers to understand and process the ambiguous queries put forth by authorized persons. This has been accomplished in this paper by introducing soft computing in multi – modal systems. This architecture first uses vascular pattern recognition to identify whether the user is an authorized person or not by using the image of his blood vessels obtained by using near – infrared light. Then the architecture consists of six main components - a reasoner, a speech system, a vision system, a non intrusive neural network based gaze tracking system, an integration platform and an application interface, using which we can process speech, text, face images, gaze information and simulated gestures. Fuzzy and probabilistic techniques have been used in the reasoner to establish temporal relationships and learn interaction sequences. This architecture can be used in Process control and Instrumentation where the authorized users can query the values of some physical parameters (pressure, temperature etc). The ambiguities of these queries are resolved using gaze tracking. Example: Query (recognized by speech): show me this of that machine. (That machine is pointed using mouse) Ambiguity: this (physical parameter) - identified by where the user’s gaze is fixed on the screen. Final query: show parameterA of machineB.