The data in internet social media has the characteristics of fast transmission, high user participation and complete coverage compared with traditional media under the background of the rise of various platforms on the internet.There are various topics that people pay attention to and publish comments in, and there may exist deeper and more fine-grained sub-topics in the related information of one topic. A survey of sub-topic detection based on internet social media, as a newly emerging and developing research field, was proposed. The method of obtaining topic and sub-topic information through social media and participating in the discussion is changing people’s lives in an all-round way. However, the technologies in this field are not mature at present, and the researches are still in the initial stage in China. Firstly, the development background and basic concept of the sub-topic detection in internet social media were described. Secondly, the sub-topic detection technologies were divided into seven categories, each of which was introduced, compared and summarized. Thirdly, the methods of sub-topic detection were divided into online and offline methods, and the two methods were compared, then the general technologies and the frequently used technologies of the two methods were listed. Finally, the current shortages and future development trends of this field were summarized.
A tampered image recognition system with better universality based on convolutional neural network of three-stream feature extraction was proposed to improve the recognition accuracy of three main tampering methods stitching, scaling and rotating, copying and pasting. Firstly, by comparing the similarity of feature sub-blocks according to image local color invariant feature, comparing the noise correlation coefficients of tampered region edges with noise correlation, and calculating the standard deviation contrast of sub-blocks based on image resampling trace, the features of the RGB stream, noise stream and signal stream of the image were extracted separately. Then, through multilinear pooling, combined with an improved piecewise AdaGrad gradient algorithm, the feature dimension reduction and parameter self-adaptive updating were realized. Finally, through network training and classification, three main image tampering methods of stitching, scaling and rotating, copying and pasting were identified and the corresponding tampered areas were located. In order to measure the performance of this model, experiments were carried out on VOC2007 and CIFAR-10 datasets. The experimental results of about 9 000 images show that the proposed model can accurately identify and locate the three tampering methods stitching, scaling and rotating, copying and pasting, and its recognition rates are 0.962,0.956 and 0.935 respectively. Compared with the two-stream feature extraction method in the latest literature, the model has the recognition rates increased by 1.050%, 2.137% and 2.860% respectively. The proposed three-stream model enriches the image feature extraction by convolutional neural network, improves the training performance and recognition accuracy of the network. Meanwhile, controlling the descent speed of parameter learning rate piecewisely by the improved gradient algorithm reduces the over-fitting and convergence oscillation, as well as increases the convergence speed, so as to realize the optimization design of the algorithm.
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.
To solve the gesture segmentation deviation problem under the interference of other skins and overlapping objects, a method of using depth data and skeleton tracking to segment gesture accurately was proposed. The minimum circumscribed circle, the average and the maximal inscribed circle of convexity defect, were combined to improve the detection of palm and the palm region's radius of various gesture. A fingertip candidate set was got through integrating the finger arc with convex hull, then real fingertips were obtained with three-step filtering. Six gestures have been tested in four transform cases, the recognition rate of flip, parallel, overlapping are all higher than 90% but the rate decreases obviously when tilting more than 70 degree and yawing more than 60 degree. The experimental results show that the accuracy of the proposed method is high in a variety of real scenes.
In order to manage the metadata of massive spatial data storage effectively, a distributed metadata server management structure based on consistent hashing was introduced, and on this basis, a metadata wheeled backup strategy was proposed in this paper, which stored Hash metadata node after excuting a consistent Hash algorithm according to the method of data backup, and it effectively alleviated the single point of metadata management and access bottleneck problems. Finally testing wheel backup strategy, it obtained the optimum number of metadata node backup solution. Compared with the single point of metadata servers, the proposed strategy improves the metadata safety, reduces the access delay, and improves the load balance of distributed metadata server combined with virtual nodes.
In this paper, to protect data integrity in data aggregation of Wireless Sensor Network (WSN), a secure and efficient data aggregation scheme was proposed, which was based on Dual-head Cluster Based Secure Aggregation (DCSA). By setting symmetric keys between nodes and using distributed authentication method, this scheme performed node authentication and aggregation simultaneously, as integrity-checking of child node was completed immediately in the process of aggregation. Also, by using the oversight features of red and black cluster head, this scheme could locate malicious nodes and enhance the capability of anti-collusion attack. The experimental results show that the proposed scheme ensures the same security level with DCSA, and this scheme is able to detect and discard erroneous data immediately. It improves the efficiency of integrity detection mechanism and it has lower network energy consumption.
Aiming at the problem that the performance of parallel computing cannot be improved by extending its scale under the constraint of fixed structure, a method of proportionally adjusting graph weights was proposed to handle such extension problem. The method firstly investigated the factors from architecture and parallel tasks which affected its scalability, and then modeled the architecture as well as parallel tasks by using weighted graph. Finally, it realized an extension in parallel computing by adjusting proportionally the weights of the vertices and edges in the graph model for parallel computing. The experimental results show that the proposed extension method can realize isospeed-efficiency extension for parallel computing under the constraint of fixed structure.