Advanced Materials Research Vols. 546-547

Abstract: This paper reports a new architecture of intelligent question answering system based on the analysis of answering systems’ advantages and disadvantages. According to the design of ARIANE system, it develops the machine translation system for problem extraction. In the machine translation system design, analysis, and intelligent syntax has been difficult to solve. For the syntax analysis and word construction problems in intelligent segmentation, this paper adopts semantic network partition to solve it, It is partition in some level of association, can batter handle the issue to focus in semantic network partition. In this way, the user issues after word from the words library screening, a list of a series of related issues in descending order by degree of difficulty and returned to the user. Experimental analysis proves the usability of the improved algorithm.

Abstract: Character Segmentation is the key step for image text recognition. This paper presents a text tilt correction algorithm using tracked characteristics rectangle contour to extract angle, using line scan method based on the number of transitions to determine the character on the bottom. In order to meet the requirements of real-time and reliability, takes improved secondary single-character segmentation algorithm based on vertical projection method.

Abstract: According to the current e-government development, analysis of the characteristics of digital watermarking technology, a digital watermarking-based solutions for electronic seals to increase the security of electronic data.

Abstract: With the development of intelligent fault diagnosis technology, research on the application of multi-Agent theory in the remote fault diagnosis system is increasing. With avionic devices as the application background, the modeling of the remote intelligent fault diagnosis system (RIFDS) based on multi-Agent theory is researched, including the frame model, logical model and soft architecture. The key problems that need to be resolved for the realization of the system are also discussed.

Abstract: Zero Velocity Update (ZUPT) is an essential method of error control in Stapdown Inertial Navigation System (SINS), which is extensively used because of its cheapness and efficiency. ZUPT uses the output of velocity error of SINS when the carrier is parking, to update the errors of other items in SINS. This method can improve the position and direction precisions of SINS. Kalman filter is chosen as the method of ZUPT to correct the velocity and position errors in SINS in this article. The method of ZUPT based on Kalman filter is applied to the vehicle experiment. The results of the vehicle experiment indicate that the ZUPT based on Kalman filter is efficient and powerful in error control, and the Kalman filter designed based on SINS is proper.

Abstract: Visualization simulation can reflect the dynamic characters of object studied lively. Satellite Tool Kit (STK), developed by Analytical Graphics Inc., is a software used for 3D simulation and analysis. It has the characteristics of powerful model library, 3D effects and sound and rapid development. This paper discusses the application mode of STK/Connect, and proposes a method that a third-part program controls the STK scenario through STK/Connect to build a 3D visualization simulation system. A case is given to prove the feasibility of the solution.

Abstract: Show the definition of Ad Hoc network attack cluster, and propose a new method of DDoS attacks for Ad Hoc Networks, which can accurately attack the target node, demonstrate no redundant aggressive behavior compared with the traditional attack and reduce the detection rate of aggressive behavior. Use NS2 simulation platform to build Ad Hoc network simulation scenarios with dynamic topology, and simulate DDoS attacks in this environment; The simulation results show that the new DDoS attack method can effectively reduce the communication ability of the Ad Hoc network, and increasing the attack node density will strengthen the attack effect.

Abstract: It proposes the model and learning algorithm of Quantum Counter Propagation Neural Network and applies which in hyperspectral data classification as well. On one hand, introducing quantum theory into the structure or training process of Counter Propagation Neural Network with regard to improving structure and capacity of Classical Neural Network, enhancing learning and generalization ability of it. On the other hand, establishing a new topological structure and training algorithm of Quantum Counter Propagation Neural Network by the means of quoting the thought, concept and principles of quantum theory directly. To complete the experiment of hyperspectral data classification with three ways and the result shows that effects of Quantum Counter Propagation Neural Network is superior to the traditional classification.

Abstract: In order to promote the application and development of machine vision, The paper introduces the components of a machine vision system、common lighting technique and machine vision process. And the key technical problems are also briefly discussed in the application. A reference idea for application program of testing the quality of the machine parts is offered.

Abstract: According to the characteristics of college training and requirements of the society for talents, the decision support system of college training is designed in this paper. Targeted at graduates’ employment, a data warehouse for college students is set up and online analytical processing and data mining are conducted so as to find out the key factors that affect graduates to find a job. The experimental results are in line with the reality, which shows that decision support system of college training is a powerful auxiliary decision-making tool.