Motion blur has an extremely negative effect on video frame interpolation. In order to handle this problem, a novel blurred video frame interpolation method was proposed. Firstly, a multi-task fusion convolutional neural network was proposed, which consists of a deblurring module and a frame interpolation module. In the deblurring module, based on the deep Convolutional Neural Network (CNN) with stack of ResBlocks, motion blur removal of two input frames was implemented by extracting and learning the deep blur features. And the frame interpolation module was used to estimate voxel flow between two consecutive frames after blur removal, then the obtained voxel flow was used to guide the trilinear interpolation of the pixels to synthesize the intermediate frame. Secondly, a large blurred video simulation dataset was made, and a “first separate and then combine” “from coarse to fine” training strategy was proposed, experimental results show that this strategy promotes the effective convergence of the multi-task fusion network. Finally, compared with the simple combination of the state-of-the-art deblurring and frame interpolation algorithms, experimental metrics show that the intermediate frame synthesized by the proposed method has the peak-to-noise ratio increased by 1.41 dB, the structural similarity improved by 0.020, and the interpolation error decreased by 1.99， at least. Visual comparison and reconstructed sequences show that the proposed model performs good frame rate up conversion effect for blurred videos, in other words, two blurred consecutive frames can be reconstructed end-to-end to three sharp and visually smooth frames by the model.

Traditional feature selection methods have great limitations in the imbalanced text sentiment tendency classification, which are mainly reflected in the high feature dimension, the sparse characteristics, and the imbalanced feature distribution, making the reduction of classification accuracy. According to the distribution of emotional features of imbalanced texts, a Three-Way Decisions-Feature Selection algorithm (TWD-FS) was proposed for imbalanced text sentiment classification based on three-way decisions. In order to reduce the number of feature words and reduce the feature dimension, two supervised feature selection methods were combined, and the feature words selected were further filtered in order to make them satisfy the characteristics of the maximum between-class scatter degree and the minimum within-class scatter degree. In addition, the imbalance of sentiment features was decreased and the classification accuracy of minority sentiment was effectively improved by combining positive and negative sentiment features. The experimental results on COAE2013 Chinese microblog imbalanced datasets and other datasets show that the proposed feature selection algorithm TWD-FS can effectively improve the accuracy of imbalanced text sentiment classification.

Since methods based on linked list in existing microscopic traffic simulation systems are not efficient and scalable to process Nearest Neighbor (NN) queries, a variation of B+ tree based method was proposed to resolve these problems. This method combined ideas from NN queries in database with advantages of linked list. By maintaining indices of nearby vehicles of each vehicle in the local lane, the performance of NN queries in that lane could be largely improved. Under the assumption of randomly distribution of vehicles, a mathematical model was also proposed to optimize the parameter setting according to multiple parameters for lanes and the amount of vehicles. This model calculated the minimized average query length of each NN query to optimize the parameter setting. The results of theoretical analysis and simulations showed that in common traffic conditions including sparse, normal and congestion, the main indicator, namely the average simulation time cost of each vehicle, could be reduced by 64.2% and 12.8% compared with linked list and B+ tree respectively. The results prove that the proposed method is suitable for larges-cale microscopic traffic simulation systems.

With the rapid development of Internet, the traditional automatic abstraction algorithm cannot meet the needs of the green network. Different from the traditional automatic abstraction algorithm based on statistical learning, this paper proposed a new algorithm based on clear semantics. It made use of cloud data acquisition library of green network system based on behavior analysis and Wikipedia resources as the knowledge base to establish the concept of space, it performed semantic interpretation on these words. Finally, the experimental results prove that the proposed method can cover more information with fewer sentences compared with the traditional algorithm, thus it greatly shortens the time for the system to analyze and filter inappropriate content and enhances the quality of software services.