Because of the complexity of human language, text sentiment classification algorithms mostly have the problem of excessively huge vocabulary due to redundancy. Deep Belief Network (DBN) can solve this problem by learning useful information in the input corpus and its hidden layers. However, DBN is a time-consuming and computationally expensive algorithm for large applications. Aiming at this problem, a semi-supervised sentiment classification algorithm called text sentiment classification algorithm based on Feature Selection and Deep Belief Network (FSDBN) was proposed. Firstly, the feature selection methods including Document Frequency (DF), Information Gain (IG), CHI-square statistics (CHI) and Mutual Information (MI) were used to filter out some irrelevant features to reduce the complexity of vocabulary. Then, the results of feature selection were input into DBN to make the learning phase of DBN more efficient. The proposed algorithm was applied to Chinese and Uygur language. The experimental results on hotel review dataset show that the accuracy of FSDBN is 1.6% higher than that of DBN and the training time of FSDBN halves that of DBN.

Since the early Mild Cognitive Impairment (MCI) is very likely to be undiagnosed by the assessment of medical diagnostic cognitive scale, a multimodal network fusion method for the aided diagnosis and classification of MCI was proposed. The complex network analysis method based on graph theory has been widely used in the field of neuroimaging, but different effects of brain diseases on the network topology of the brain would be conducted by using imaging technologies based different modals. Firstly, the Diffusion Tensor Imaging (DTI) and resting-state functional Magnetic Resonance Imaging (rs-fMRI) data were used to construct the fusion network of brain function and structure connection. Then, the topological properties of the fusion network were analyzed by One-way ANalysis of VAriance (ANOVA), and the attributes with significant difference were selected as the classification features. Finally, the one way cross validation of Support Vector Machines (SVM) was used for the classification of healthy group and MCI group, and the accuracy was estimated. The experimental results show that, the classification result accuracy of the proposed method reaches 94.44%, which is significantly higher than that of single modal data method. Many brain regions, such as cingulate gyrus, superior temporal gyrus and parts of the frontal and parietal lobes, of the MCI patients diagnosed by the proposed method show significant differences, which is basically consistent with the existing research results.

Since there are many troubles such as large quantity, uneven quality and poor credibility in getting helpful information and making effective decision for stakeholders, and the existing research work on credibility assessment mainly considers the sources of reviews and the support of reviews in form of votes, an assessment method on review credibility from perspective of intrinsic quality was proposed. That is, the credibility assessment of reviews was realized by integrating the ratings of reviewers, the support degree of reviews and the consistency in reviews, etc. Firstly, the pre-processing of review data was completed based on rule and method libraries. Then, the feature recognition and the feature value extraction and standardization were completed based on product feature library, generic dictionary, sentiment dictionary and method library. Finally, the credibility assessment of reviews was completed based on the established models. The experimental results verify the feasibility of this method, and it can be applied to assess the credibility of product reviews automatically on other e-commerce platforms.

Since information extraction algorithm for Web pages lacks generality and information of title, release-time and source in news Web page, a new information extraction algorithm was proposed to resolve those problems. Firstly, HTML code of Web page was parsed to text sets combined with line number and text; then, extractor began to search boundary of news content from line which the longest sentence belonged to due to the characteristic that the longest sentence belongs to the content of news with an extremely high probability. Meanwhile, the longest common string algorithm was used to extract title, the regular expression and line number were used to extract release-time, and the presentation characteristics of source and line number were used to extract source. Finally, a data set was built to conduct a comparison experiment with an open-source software named newsPaper in accuracy of extraction. Experimental results show that newsExtractor outperforms newsPaper in average accuracy of content, title, release-time and source, it has strong generality and robustness.

In view of the problem that data for Named Data Networking (NDN) cache is replaced efficiently, a new replacement policy that considered popularity and request cost of data was proposed in this paper. It dynamically allocated proportion of popularity factor and request cost factor according to the interval time between the two requests of the same data. Therefore, nodes would cache data with high popularity and request cost. Users could get data from local node when requesting data next time, so it could reduce the response time of data request and reduce link congestion. The simulation results show that the proposed replacement policy can efficiently improve the in-network hit rate, reduce the delay and distance for users to fetch data.

With the increasing energy consumption in current data centers, many emerging energy-saving mechanisms have been proposed to reduce the energy consumption, but most of these methods assume data center is in a homogeneous environment. However, most of current data centers are heterogeneous as different types of servers are purchased at different time in reality. An energy-efficient method named Primary Virtual Machine Allocation Policy (PVMAP) was proposed, with the performance/power introduced as a parameter to indicate the energy efficiency of each server. The server of high energy efficiency would be fully utilized with high priority in the dynamic Virtual Machine (VM) consolidation. Also the consolidation process would try to minimize the VM migrations and running hosts in the end. The simulation results demonstrate that the PVMAP can guarantee the energy conservation and Quality of Service (QoS) at the same time, and it has better stability and extensibility.

Dynamic tree rendering plays an important role in the natural scenery simulation. In this paper, by using Cook-Torrance lighting model and pre-computed translucency texture, rendering scattering and translucency of the leaf were implemented. Using the polynomial fitted from tapered circular beam model expression and length correct method, the speed of calculation deform was boosted. By introducing the hierarchical branches texture with index, branches deform could be calculated in Graphic Processing Unit (GPU). Using pre-compaction and GPU helps to balance the reality and real-time in the simulation. The experiments show that the proposed method can render the dynamic tree scene vividly and rapidly.

Traditional solutions deal with following-car interference and adjacent-lane interference in Electronic Toll Collection (ETC) system separately, and are of low efficiency and high cost. In order to solve this problem, a solution based on information fusion, which can deal with these two problems together, was proposed. This method used the vehicle information collected by an ETC system as known information and chose the features of the vehicle image to verify whether the vehicle information came from the car in question. Then D-S evidence theory was adopted to fuse the results of verification and make a final decision whether it was the right car to be charged. An improved method for D-S evidence theory was proposed to ensure its validity when the results of consistency verification conflicted with each other. The experimental results show that this method can highly reliably detect illegal vehicles and solve both following-car interference and adjacent lane interference problems in ETC system.