Advanced Materials Research Vols. 760-762

Abstract: As the customer reviews become more and more on the Internet, It would be significant if these reviews are summarized automatically. Sentiment classification aims at predicting the semantic orientation of customer reviews, positive and negative. In this paper, we gave out the framework of sentiment classification, and empirically studied the performance when used different features, term weighting methods and machine learning methods. The experimental results suggest that using binary occurrence to weight the features is more suitable when used Naïve Bayes, but when used the support vector machine, tfidf-c can get the best performance. Besides, we also find that the sentiment terms are not suitable as features when used the approaches based on machine learning methods.

Abstract: Due to the emergency plan format information characteristics is stronger and more easily to gain the complete content description, so this paper puts forward the recommendation algorithm of emergency plan based on content filtering. This paper proposes the characteristics model of emergency plan and the user's interest model and designs the flexible recommendation interface for user interactive, so we can get the recommend results.

Abstract: There are many thinking method, the thinking method of decomposition and combination is important and widely used. In the category of scholars, "decomposition and combination" belong to "analysis and synthesis". Developing software is a complex mental activity, so it requires the use of a variety of thinking method. Thinking method of decomposition and combination is the use of the most frequent in developing software. Content of thinking method of decomposition and combination is analyzed. Application of thinking method of decomposition and combination has been analyzed from four aspects. Four aspects are the development trend of software, the main content of the structured software development method, the main content of the object-oriented software development method, several commonly used software development tools.

Abstract: Aiming at detecting the moving targeting from video sequence, this paper proposes a mixed algorithm in video sequence based on the motion target detection. Combining the median filtering background modeling and the improved TemporalDifference method (MFTD) to detect the object which also use the self-adaptive threshold segmentation method to optimize moving object extraction, and at the same time, we introduce the gaussian filter and morphological filter to eliminate noise and improve the effect of moving region extraction. In practical engineering, the MFTD algorithm can extract the moving object regions accurately and effectively.

Abstract: In this paper, we believed that social tag is a new paradigm of resource organizing and sharing. It is a very suitable technology using in e-learning systems. We discussed with the learning process in the e-learning system based on social tags. We brought forward a new individual learning process model based on social tags. And we compared with the new learning process model and traditional process model. The new individual learning process model could improve the interaction between learners and between human and computers. The social tags could help the e-learning system build the learners preference model and knowledge model.

Abstract: Tag clouds are now very popular in websites because of its ability to recruit the activity of web users into effectively information retrieval. In recent years, although there are many researches on English tag clouds, few are known about Chinese tag clouds. In this paper, we investigated the layout of the Chinese tag cloud, and analyzed eight visual features of the Chinese tag cloud according to users browsing behavior. Our results could provide a theoretical reference for the tag cloud designers.

Abstract: In this article, according to WenShuHua and Zhangxueniang fractal model, we point out the deficiency. Based on the fractal theory and Zhang, Wens contact stiffness fractal model, this paper puts forward Gamma distribution of rough joint surface normal contact stiffness. This paper considers micro convex body for ellipsoid, contact area for elliptic. This is slightly convex body for sphere hypothesis is more close to the actual situation. At the same time by using statistics theory, considering the contact ellipse long, short axis a and b are greater than zero, the assumption of a and b to two-dimensional Gamma distribution, it is more suitable for engineering practice.

Abstract: Prediction is necessary to compensate system latency in real-time tracking radiotherapy for thoracic and abdominal cancers. The paper proposes a memory-based learning method to predict respiratory tumor motion. The method first stores the training data in memory and then finds relevant data to answer a particular query. By fitting relatively simple models to local patches instead of fitting one single global model, it is able to capture highly nonlinear and complex relations between the internal tumor motion and external surrogates accurately and immediately. Furthermore, due to the local nature of weighting functions, it is inherently robust to outliers in the training data.

Abstract: According to the problem that the intelligence is not high of the soccer robot, using the mechanical theory as a guide, making some mechanical analyses and calculations on the pressure and transmutation states of chip kick mechanics, and conducting optimal design too, then making the structure of chip kick mechanics more and more rationalization. Experiments show that the new soccer robot controller features a quick response and high servo rigidity, and provide a kind of method for improving and perfecting the soccer robot control system, at the same time, filling the needs of producing.

Abstract: In recent years, with the development of Internet of Things, a new challenge is posed on data access. Focusing on the database management problems of internet of things, a design method of database system for Internet of Things was proposed by means of DPT and P2P point cloud. An example of Internet of Things for medical health system verifies the method can solve the problem of database management of Internet of Things to a certain extent and provide technical support for Internet of Things combining distributed processing technology, network technology, and middleware technology.