Applied Mechanics and Materials Vols. 347-350

Abstract: Economic Dispatch (ED) is one of the optimization issues for improving the economic benefit of power plants. According to the framework of Mind Evolutionary Algorithm, we proposed a new developed Dynamic Mind Evolutionary Algorithm (DMEA) to solve the ED problem. Specifically, the economic model in power plants was built firstly. Secondly, an individual evaluation function is presented. Thirdly, simplex method was used to search the extreme value of each sub-group. Then, sub-groups are separated at the step similartaxis operator, while the sub-groups with the same extreme value are assembled at the step dissimilation operator, so that the extreme value of each local space can be found efficiently. Ultimately, it can avoid repeated search for the same space due to the record of the searched area. Including DMEA, three different methods were compared under the same illustration. The simulation results demonstrate the effect of DMEA.

Abstract: Under the background of global ocean development, artificial intelligence has increasing importance which urges the improvement of traditional research and exploration methods. Marine applications of artificial intelligence have been further practiced and expanded by Shanghai World Expo, which reflect in at least three major areas: firstly, the foundations of technical thought kernel, network expansion and intelligent navigation are laid in Maritime Internet of Things; secondly, in the field of far-reaching sea exploration, unmanned probe (deep-sea robot) relied on artificial intelligence technology has gradually become a major force in international competition; thirdly, as an ocean information and management comprehensive integration platform, digital ocean is applied to crack ocean information solitary island, jumbled information and other difficult problems through cooperation development, function integration and affinity services, enhancing the public ocean consciousness.

Abstract: Text sentiment analysis is a new branch of computational linguistics which is widely concerned. In this paper, we present an approach to determine polarity of sentiment word based on context of sentence. We first change the context of sentence to semantic pattern vector, calculate the between different sentences, then compare sentences context indirectly by comparing similarity of their pattern vector, next we annotate polarity of sentiment word according to comparing result. Experiment shows that when the context of two sentences have high similarity, it is likely to have high precision in recognizing polarity of sentiment word. Our study shows it's feasible to use semantic pattern vector in representing context and judging polarity of sentiment words.

Abstract: Feature selection has become the focus of research areas of applications with high dimensional data. Nonnegative matrix factorization (NMF) is a good method for dimensionality reduction but it cant select the optimal feature subset for its a feature extraction method. In this paper, a two-step strategy method based on improved NMF is proposed.The first step is to get the basis of each catagory in the dataset by NMF. Added constrains can guarantee these basises are sparse and mostly distinguish from each other which can contribute to classfication. An auxiliary function is used to prove the algorithm convergent.The classic ReliefF algorithm is used to weight each feature by all the basis vectors and choose the optimal feature subset in the second step.The experimental results revealed that the proposed method can select a representive and relevant feature subset which is effective in improving the performance of the classifier.

Abstract: This paper mainly analyzes the current problems existing in oral English teaching with application of multimedia technology and network-based environment on base of constructive learning theory as well as current reform situation. By providing diverse effective strategies, both scientific application of multimedia technology and oral English teaching quality could be achieved to its best.

Abstract: This paper discussed several methods to maximize the sum of the data rate. After the analysis of the graphic algorithm, we found the difficulty of the determination of the variables. To solve the problem, we propose a new idea to operate the variable and proved it to be efficient in the simulation results.

Abstract: Along with the coming of information age, many websites use its formidable resources and popularity, provides day by day the service of specialized and convenient to its member group. The members online rent DVD, became the website management administrative personnel the issue of concern. How to having the data carries on the analysis processing, is solves this problem the key. The article through building the mathematical model, has solved this problem using the data mining technique very well.

Abstract: Collaborative filtering is regarded as the most prevailing techniques for recommendation system. Slope one is a family of algorithms used for collaborative filtering. It is the simplest form of non-trivial item-based collaborative filtering based on ratings. But all the family of use CF algorithms ignores one important problem: ratings produced at different times are weighted equally. It means that they cant catch users different attitudes at different time. So in this paper, we present a new algorithm, which could assign different weights for items at different time. Finally, we experimentally evaluate our approach and compare it to the original Slope One. The experiment shows that the new slope one algorithms can improve the precision

Abstract: An approach of sentiment classification for online comments based on intuitionistic fuzzy reasoning is presented on the basis of the analysis of characteristics of sentiment classification. The approach employs membership function, non-membership function and hesitant function to depict uncertainties of features, quantitatively, by sample training, as well as sentiment expressions influenced by adverbs of degree, conjunctions and negative words are considered. Then the semantic orientation of a text is synthesized on the level of phrases, sentences and texts in sequence by means of aggregations of intuitionistic fuzzy information of features. The presented approach obtains high precision and recall when test using public corpus

Abstract: Nowadays, context-aware applications have become a hot research field. However, many context-aware applications dont fully connect to the characteristics of the Internet and the developed applications are limited by the platform, thus, the cross-platform deployment cant achieve. This paper presents a mechanism which can shield the difference among terminal operating systems andgather, store, and interpret the context information on the same smart terminal,based on the research achievements about the arithmetic of context-aware and the design of the cross-platform and context-aware middleware. To some extents, this frame can not only lessen the developers workload and avoid duplication of effort, but also speed up the applications development time and reduce the power consumption of mobile terminal.