Advanced Materials Research Vols. 219-220

Abstract: A neural network soft sensor based on fuzzy clustering is presented. The training data set is separated into several clusters with different centers, the number of fuzzy cluster is decided automatically, and the clustering centers are modified using an adaptive fuzzy clustering algorithm in the online stage. The proposed approach has been applied to the slab temperature estimation in a practical walking beam reheating furnace. Simulation results show that the approach is effective.

Abstract: A decision support system for flood warning has been developed for Jinan city. It is a web based distributed system that integrates GIS, databases and models. Urban Flood Simulation model is used as a real-time flood forecasting model. Mike Flood model is used to simulate pre-formulated flood scenarios for urban areas. The objective of the system is to simulate and forecast river and urban floods on the basis of real-time meteorological situation and rainfall available, and to serve as a tool for making decision.

Abstract: A Smart home control system based on S3C2440 and Windows CE was designed, which combined with 433MHz/315MHz wireless network and Wi-Fi module. The designed system can not only realize several local wireless controlling modes of the home appliances, but also implement remote control and monitoring via Web pages and telephone. Through the proper chip selection and circuit design, the penetration capability of the wireless signal was enhanced, the power dissipation and the cost of system were reduced. Moreover, with the humanized design of the software, the operation of system is more simple and convenient.

Abstract: When massive information brings people more channels to attain messages, there generates different types of new personalized recommendation systems. As the important sector for social development, tourism industry suffers the problem of information over-loading. In the construction of personalized recommender system mainly involves two problems: information acquisition and personalized recommender. This recommender system is able to form client’s databank after user’s login and assessment for various travel destination and products to support more accurate user’s information mining. The authors adopt improved hybrid recommender algorithm through combining collaborative filtering algorithm with content-based recommendation algorithm. The relationship of user and travel destination can be classified as the interested and disinterested. So it can predict the degree of new users’ enthusiasm towards different types of travel destination to realize personalized travel recommendation.

Abstract: Financial crisis reflects that the value of enterprise is the key to lead the development of the enterprise. Combining with the vacancy of the enterprise culture, insufficient innovation of the Enterprise culture, and ineffective measures of the enterprise culture construction, and so on, this paper comes up with some countermeasures such as the enterprise should correct understanding of the enterprise culture, strengthen the construction of enterprise’s learning organization, fully exert the entrepreneurial spirit of enterprise leaders so as to improve the competitiveness and the ability of dealing with the crisis.

Abstract: Vehicle routing problem (VRP) is the key to reducing the cost of logistics, and also an NP-hard problem. Ant colony algorithm is a very effective method to solve the VRP, but it is easy to fall into local optimum and has a long search time. In order to overcome its shortcomings, max-min ant colony algorithm is adopted in this paper, and its simulation system is designed in GUI of MATLAB7.0. The results show that the vehicle routing problem can well achieves the optimization of VRP by accessing the simulation data of database.

Abstract: In order to improve the efficiency and security of the authentication for Hierarchical Mobile IP protocol, we propose a novel authentication scheme, which introduced identity signature and digital envelope to authenticate the sender and receiver of the registration packet. Theoretically prove that the scheme is an effective mutual authentication scheme, and improve the security and resist security attacks.

Abstract: According to the fast increase of Information data and continuous enhancement of people’s requirement for analyze of information, it is more and more difficult to get requisite information to judgment and decision-making. For solving these problems, the design of an intelligent forecast system based on back propagation neural network is introduced. And the framework, data processing and arithmetic of the system are presented. By continuously running program debugging and optimization settings to modify the parameters, the predicted results and actual test results is to be closer.

Abstract: In this paper, we proposed a LW-PSO (PSO using a local world evolving model) by combining a local world evolving model with the “survival of the fittest” evolution mechanism. The concept of population structural entropy, a new diversity measure is defined and used to control the evolution process of the population topology of LW-PSO so the balance between the exploration and exploitation can be preserved during the population evolution. The experimental results show that LW-PSO can outperform the standard PSO with the lbest topology and the gbest topology especially in the multimodal problems and the extra time cost is negligible.

Abstract: As a new business model, e-commerce has great prospects for development. Meanwhile, such an e-business model has put forward higher requirements for the management level and the technology of transmitting information, and the construction of security system is particularly important. How to create a safe and convenient application environment for e-commerce, and providing adequate protection of information are the issues concerned by companies and users. Firstly, this thesis puts forward the existing safety risks of e-commerce in China. Then, their causes are analyzed. Finally, the relevant conclusions are drawn from the perspective of technology, legal, security management and network morality.