Advanced Materials Research Vols. 718-720

Abstract: With the development of Internet and the sharp increase of the number of netizens, Network is becoming an important public platform for the public to express the opinion, Network public opinion is becoming the improtant base of decision making to the government and companies.Managing the public opinion information and timely discovering hot spots is essential to correctly guiding the public opinion trends, so the Network Public Opinion has become a hot point in this years.Because of the different demand, it is impossible for all the users to acquire the satisfied result.This paper describes an individulized prison Network Public Opinion algorithm based on information network to solve this problem expecially for the judicial authority.

Abstract: Electronic commerce recommendation system can effectively retain user, prevent users from erosion, and improve e-commerce system sales. BP neural network using iterative operation, solving the weights of the neural network and close values to corresponding network process of learning and memory, to join the hidden layer nodes of the optimization problem of adjustable parameters increase. Ontology learning is the use of machine learning and statistical techniques, with automatic or semi-automatic way, from the existing data resources and obtaining desired body. The paper presents building electronic commerce recommendation system based on ontology learning and BP neural network. Experimental results show that the proposed algorithm has high efficiency.

Abstract: Pv6 not only solves the problem of IP address deficient, also simplified the protocol header, and the success of the introduction of two new extension header AH and ESP. The Internet of things perceived terminal data format varied, unified management difficult operation, new business difficulty landing. The research of security Internet of things will mainly focus on the open web application security system, individual privacy protection mode of networking, security features, Internet safety laws formulation. The paper presents the novel application model of Internet of things based on IPv6 technology. Experimental results show that the proposed method has high efficiency.

Abstract: BP neural network is a multilayer feed-forward neural network, it achieved from input to output arbitrary nonlinear mapping, and weights are adjusted by using the back propagation learning algorithm. Intrusion detection systems using the learning ability of neural network to extract the network data profile, and it also can use the neural network has the ability of self-learning and parallel processing ability, through the construction of intelligent neural network classifier to identify abnormal, so as to achieve the purpose of detecting intrusion behavior. The paper proposes the development of intrusion detection system based on improved BP neural network. Experimental results show that the proposed algorithm has high efficiency.

Abstract: Network lifetime is a critical metric in the design of energy-constrained wireless sensor networks. In this paper, we consider the joint cross layer optimization of the physical layer, medium access control layer and routing layer to maximize network lifetime of a multi-sources and single-sink wireless sensor network with energy constraints. We focus on synchronous small-scale sensor network with interference-free link scheduling and practical MPSK link transmission scheme. As the network lifetime maximization problem is a constrained non-convex optimization problem that is difficult to be solved, and the particle swarm optimization algorithm is a good intelligent algorithm, we employ it to solve the problem mentioned above effectively in this paper. The penalty function technique is brought in to work out the constrained optimization problem by converting it to an unconstrained optimization problem. Simulation results show the effectiveness of the proposed algorithm in energy saving and network lifetime maximization, and the particle swarm optimization can solve the network lifetime maximization problem fast and efficiently.

Abstract: The e-commerce transaction security is the security of business activities in the public network, and its essence is based on computer network security, protect the business process to precede smoothly, the core content of the e-commerce information security. IPv6 network layer denial of service attacks, the fight against replay attacks, prevent data passive or active eavesdropping, to prevent data session stealing attacks and other functions, which greatly enhances the security of the network can be realized. The paper presents using IPv6 technology to construct network security system of electronic commerce. Experimental results show that the proposed method has high efficiency.

Abstract: Collaborative filtering process is based on the known users of the evaluation of target users to predict the target of interest, and then to the target users to recommend new items. This paper applies the fuzzy clustering technology used in the project of nearest neighbors and the users nearest neighbor search, reduces the project space and user space calculation dimension, to improve the traditional collaborative filtering algorithm scalability. The paper puts forward the novel model of collaborative filtering recommendation based on fuzzy clustering analysis. Compared with the traditional method of item similarity calculation is more accurate, the experiments show that the method improves the accuracy of recommendation.

Abstract: For the blank of the recommender system for chinese recipes, this paper uses OWLS-WSDL to build a semantic reasoning-based chinese recipe recommender system. This system through the tool of Protégé to establish the ontology of chinese recipes and then add rules for ontology reasoning. On this basis bring out a catering algorithm, using Euclidean distance and Jaccard to calculate the similarity between the dishes. According to the similarity as well as user preference, provides a quick means of siding dishes for users.

Abstract: In order to improve the stability of target tracking under occlusion conditions，on the basis of researching some target tracking algorithms, this paper presents an algorithm based on MCD correlation matching, which combines multi sub-templates matching and target movement prediction. Besides, for occlusion characteristics, corresponding template matching criterions and updating methods are put forward. Experimental results show that, comparing with the single template method which updating frame by frame, the proposed algorithm has a certain anti-occlusion ability with better stability and continuity of target tracking under occlusion conditions.

Abstract: The paper analyzes the theories of nuclear leakage accident information extraction based on 3S technology, and studying roundly the building process of GIS spatial and temporal databases; the contents of RS images collection and the function of GPS geography position information. In addition, information extraction and analysis methods both on spatial dimension and temporal dimension are summarized. The spatial distribution and trend of radiation leak after the nuclear accident are simulated by trend surface model. Calculation and mapping shows the variation of the radiation value with time using time series analysis model.