The forecasted concentration of PM2.5 forecasting model greatly deviate from the measured concentration. In order to solve this problem, the data (from February 2015 to July 2015), consisting of measured PM2.5 concentration, PM2.5 model (WRF-Chem) forecasted concentration and model forecasted data of 5 main meteorological factors, were provided by Shanghai Pudong Meteorological Bureau. Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) algorithm were combined to build rolling forecasting model of hourly PM2.5 concentration in 24 hours in advance. Meanwhile, the nighttime average concentration, daytime average concentration and daily average concentration during the upcoming day were forecasted by rolling model. Compared with Radical Basis Function Neural Network (RBFNN), Multiple Linear Regression (MLR) and WRF-Chem, the experimental results show that the proposed SVM model improves the forecasting accuracy of PM2.5 concentration one hour in advance (according with the results concluded from finished research), and can comparatively well forecast PM2.5 concentration in 24 hours in advance, and effectively forecast the nighttime average concentration, daytime average concentration and daily average concentration during the upcoming day. In addition, the proposed model has comparatively high forecasting accuracies of hourly PM2.5 concentration in 12 hours in advance and nighttime average concentration during the upcoming day.

According to the characteristics of traditional multivariate linear regression method for long processing time and limited memory, a parallel multivariate linear regression forecasting model was designed based on MapReduce for the time-series sample data. The model was composed of three MapReduce processes which were used to solve the eigenvector and standard orthogonal vector of cross product matrix composed by historical data, to forecast the future parameter of the eigenvalues and eigenvectors matrix, and to estimate the regression parameters in the next moment respectively. Experiments were designed and implemented to the validity effectiveness of the proposed parallel multivariate linear regression forecasting model. The experimental results show multivariate linear regression prediction model based on MapReduce has good speedup and scaleup, and suits for analysis and forecasting of large data.

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.

Reverse parsing unknown network protocol is of great significance in many network security applications. Most of the existing protocol reverse parsing methods can not handle the encryption protocol or get the semantic information of the protocol field. To solve this problem, a network protocol parsing technique based on dataflow analysis was proposed. According to the data flow recording tool developed on Pin platform, it could parse the network protocol with the aid of the dependence analysis based data flow tracking technology, as well as obtain the protocol format and semantic information of each protocol field. The experimental results show that the technique can parse out the protocol format correctly, especially for the encryption protocol, and extract the program behavior semantics of each protocol field.