In view of the poor real-time response capability of traditional OnLine Analytical Processing (OLAP) when processing big data, how to accelerate computation of data cubes based on Spark was investigated, and a memory-based distributed computing framework was put forward. To improve parallelism degree and performance of Bottom-Up Construction (BUC), a novel algorithm for computation of data cubes was designed based on Spark and BUC, referred to as BUCPark (BUC on Spark). Moreover, to avoid the expansion of iterative data cube in memory, BUCPark was fruther improved to LBUCPark (Layered BUC on Spark) which could take full advantage of reused and shared memory mechanism. The experimental results show that LBUCpark outperforms BUC and BUCPark algorithms in terms of computing performace, and it is capable of computing data cube efficiently in big data era.

Focusing on the routing selection of end-to-end key agreement in Quantum Key Distribution (QKD) network, an optimal routing selection algorithm of end-to-end key agreement based on the Dijkstra algorithm was designed. Firstly, the unavailable links in the QKD networks were eliminated based on the strategy of choosing the available paths. Secondly, based on the strategy of choosing the shortest paths, the Dijkstra algorithm was improved to find out all the shortest paths with the least key consumption. Finally, according to the strategy of choosing the optimal path, the optimal path with the highest network service efficiency was selected from the shortest paths. The analysis results show that, the proposed algorithm solves the problems such as the optimal path is not unique, the best path is not the shortest, the optimal path is not optimal, and so on.The proposed algorithm can reduce the key consumption of end-to-end key agreement in QKD network, and improve the efficiency of network services.

On account of the features that the information in microblogging is enormous and the microbloggers' interests change over time, a personalized microblogging recommendation model based on Weighted Dynamic Degree of Interest (WDDI) was proposed. WDDI model considered the microblogging retweet features and the time factor of tweets, studied the tweets of microbloggers by exploiting the microblog topic model Retweet-Latent Dirichlet Allocation (RT-LDA) and built the individual dynamic interest model. Then WDDI got user's group dynamic interest by the similarity and the interacted frequency between users and their followee. Combining the user's individual interest and the group interest, the weighted dynamic degree of interest model was built. By ranking the new tweets that the user received in descending order by the degree of interest, the dynamic personalized microblogging recommendation was achieved. The experimental results show that WDDI is able to reflect the users' dynamic interest more precisely than the traditional models.

The high speed of the information propagation exacerbates the diffusion of rumors or other network pollutions in the microblogging. As the size of microbloggers and information of sub-networks in microblogging is enormous, the study of the propagation mechanism of microblogging pollution and pollution detection becomes very significant. According to the rumor spreading model for the microblogging established on the basis of influence of users, in this paper, ant colony algorithm was used to search for the rumor spreading route. Based on the data obtained from Twitter and Sina microblogging, the feasibility of the model was verified by comparison and analysis. The results show that: with the search of the affected individual, this model narrows down the pollution detection range, and improves the efficiency and accuracy of pollution management in microblogging.

The Bayesian anti-spam filter has strong classification capacity and high accuracy, but the mail training and learning at early stage consume mass system and network resources and affect system efficiency. A MapReduce-based Bayesian anti-spam filtering mechanism was proposed, which first improved the traditional Bayesian filtering technique, and then optimized the mail training and learning by taking advantage of mass data processing of MapReduce. The experimental results show that, compared with the traditional Bayesian filtering technique, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms, the MapReduce-based Bayesian anti-spam filtering mechanism performs better in recall, precision and accuracy, reduces the cost of mail learning and classifying and improves the system efficiency.