Applied Mechanics and Materials Vols. 631-632

Abstract: With the rapid development of Internet and occurrence of social media services, many users are becoming the creators of social information. However, the normal manual work can't deal with a large number of subjective messages. As a new kind of social media service, micro blog has been widely accepted and can be used for sentiment analysis. This paper compared performances of three machine learning methods on sentiment analysis of Chinese micro blog. We also proposed an improved feature selection method that increases the accuracy of classification. Experiment results show that SVM is closed to Naïve Bayes and they are better than logistic regression in most cases.

Abstract: Supervised methods of sentiment orientation analysis have got more and more attention for which don’t require labeled corpus and can be applied to different domains. However, traditional methods mostly consider single words which ignore the dependencies between the words of each other. To solve the problem, this paper presents an unsupervised method for sentiment orientation analysis on micro-blog based on dependency parsing and HDP model. Firstly, this method uses dependency parsing to filter the words in the corpus. Secondly, the HDP model is used to mine the implicit topics in the document. Then, a sentiment dictionary is used to calculate the sentiment distributions of the topics. Finally, the sentiment orientation of the whole micro-blog is obtained on the basis of the sentiment distributions of the topics. The experimental results show that the proposed method can effectively identify the sentiment orientation of micro-blog.

Abstract: As a convenient and popular social network platform, microblogging has become an important medium for people’s information exchange. The development of microblogging network can be regarded as a growth of complex network, and dissemination of information in microblogging network shows strong regularity. In the face of big scale of users, the appraisal of user influence become an important index to measures the value of a user. How to recognize user influence becomes a hot topic in microblogging research. In this paper, we proposed a method named InformationRank to evaluate user influence, which based on measure the information of node betweenness centrality in the network. Then, we analyze and compare the efficiency of this method with PageRank algorithm and Hits algorithm. The experimental results indicate that InformationRank algorithm is effective in a large scale network.

Abstract: The requirement for minimized risk is that, in the premise of balanced capacity of each member, make the lowest cost of whole manufacture and distribution network through the optimal production task allocation scheme. This paper analyzes the forming mechanism of order processing risk in the horizontal type of virtual enterprise alliance. Moreover, a minimized order distribution risk the model is proposed, and the model is computed by immune algorithm. Afterwards, the feasibility of model and algorithm are verified by a real example.

Abstract: The reality is that PHM is mostly a matter of the analytic method and process of building tailored and hybrid functional DSS to meet various requirements in field of maintenance and logistics support, not only creating models and algorithms in black box which is philosophical basis of so many PHM universal platforms, especially in the concept and design stage of systems. Some issues under discussions are presented firstly. Then, the critical cases analysis method is described, and the demonstration on the different level of specialized vehicle health management system is shown as human-computer interfaces. Lastly, the preliminary design approach to implement PHM system is presented. In addition, potential difficult points in practice are investigated for R&D of PHM.

Abstract: In this paper, it discussed multi-attribute decision making (MADM) problems in which the information about attribute weights is incomplete and decision-making information is characterized by interval-valued intuitionistic fuzzy number (IVIFNs), decision-making method is proposed based on the satisfaction. First, we define positive and negative ideal point of the comprehensive attribute values and satisfaction function, and make use of satisfaction function to establish a multi-objective optimization model, apply this model to determine the attribute weight vector, calculate the comprehensive attribute values, rank the alternatives according to the score function and precise function of the comprehensive attribute values. Finally, the examples are given to show that the method is reasonable and effective.

Abstract: Ammunitions stored in war fields have lifespans that are related to the single base propellants, as Nitrocellulose (NC), the main component of propelling gunpowder, decomposes naturally into an unstable substance, similar to other nitric acid esters. Decomposition is inevitable; however a decomposition product (NO₂, NO₃, and HNO₃) and tranquillizer DPA (Diphenylamine), which have high reactivity, can be added to a propellant to restrain the induction of automatic catalysis by a decomposition product. The decay rate of the tranquillizer is also affected by the production rate of the decomposition product of NC. Thus, as the storage period of single base propellants lengthens, the reduction rate of the tranquillizer content increases. This paper presents a new methodology based on data mining and regression analysis for estimating the shelf-life of single base propellants using data from the ASRP to 105mm HE (KM1 and M1).

Abstract: Import is an effective way to absorb technology spillovers. This paper firstly uses cointegration theory to analyze the technology spillover effect of import in the Yangtze Delta Region. The results show that import plays an important role in technological progress in the Yangtze Delta Region. Finally, this paper points out the policy implications of the above findings.

Abstract: Hubei Provincial Party Committee and Provincial Government attach great importance to the construction of Wuhan shipping center. In this background, the paper analyzed the concept of hinterland of shipping center. We use triangular fuzzy number model to calculate the factors that influenced the attractiveness between shipping center and its hinterland. Finally we get the indicator system of factors of attractiveness between shipping center and its hinterland.

Abstract: As the backbone of the national science and technology development, intellectual property management of scientific research project has become one of the most important links in the intellectual property’s protection and management in China. With the policy deconstruction and reconstruction method, the critical steps of the intellectual property management have been isolated from the policy documents and combined back together to build the whole process system of intellectual property management in scientific research project. Three elements of a system, participators, process and productions, have been identified and reasonably reconstructed to build the system.