Nitrogen oxide （NOx） is one of the main pollutants in the regenerated flue gas of Fluid Catalytic Cracking （FCC） unit. Accurate prediction of NOx emission can effectively avoid the occurrence of pollution events in refinery enterprises. Because of the non-stationarity， nonlinearity and long-memory characteristics of pollutant emission data， a new hybrid model incorporating Ensemble Empirical Mode Decomposition （EEMD） and Long Short-Term Memory network （LSTM） was proposed to improve the prediction accuracy of pollutant emission concentration. The NOx emission concentration data was first decomposed into several Intrinsic Mode Functions （IMFs） and a residual by using the EEMD model. According to the correlation analysis between the IMF sub-sequences and the original data， the IMF sub-sequences with low correlation were eliminated， which could effectively reduce the noise in the original data. The IMFs could be divided into high and low frequency sequences， which were respectively trained in the LSTM networks with different depths. The final NOx concentration prediction results were reconstructed by the predicted results of each sub-sequences. Compared with the performance of LSTM in the NOx emission prediction of FCC unit， the Mean Square Error （MSE）， Mean Absolute Error （MAE） were reduced by 46.7%， 45.9%，and determination coefficient （R²） of EEMD-LSTM was improved by 43% respectively， which means the proposed model achieves higher prediction accuracy.

Moving object detection and static map reconstruction in the environment with complex dynamic background are prone to incomplete moving object detection. In order to solve the problem， a new moving object detection method with hybrid vision system assisted by point cloud segmentation was proposed. Firstly， the PassThrough+RANdom SAmple Consensus （RANSAC） method was proposed to overcome large-area wall interference， so as to realize the point cloud ground point recognition. Secondly， the non-ground point data were projected to the image as feature points， and their optical flow motion vectors and artificial motion vectors were estimated to detect the dynamic points. Then， the dynamic threshold strategy was used to perform Euclidean clustering to the point cloud. Finally， the results of dynamic point detection and point cloud segmentation were integrated to completely extract the moving objects. In addition， the Octomap tool was used to convert the point cloud map into a 3D grid map in order to complete the map construction. Through the experimental results and data analysis， it can be seen that the proposed method can effectively improve the integrity of moving object detection， and reconstruct a low-loss， highly-practical static grid map.

Concerning the influence of resident's psychological factors on travel mode choice in the actual travel, a travel mode choice model based on prospect theory was established and a choice method more according to human thinking habits was put forward. Considering psychological reference points of travel time and travel cost comprehensively, satisfied travel mode to resident was obtained. The influence of reference point on travel mode was analyzed by comparing changes of comprehensive prospect value under different reference points. Finally an example gave the application of this travel mode choice method. The experimental results show that residents in the minority whose expectation of travel time is lower prefer bus travel, although the comprehensive prospect value changes of taxi and private car are identical. More residents tend to use private car mode, which is consistent with the fact. The proposed method provides a new way to predict resident travel mode.

A parallel bi-level image sharpening methodology in Compute Unified Device Architecture (CUDA) circumstance was proposed especially for the improvements on fuzzy boundaries and poor quality when enlarging low resolution photos or images. A GPU-based parallel sharpening algorithm with two stages was designed and implemented. Firstly, the parallel linear interpolation algorism was repeatedly adopted by the calculation of non-edge region and the sharpening treatments of edge area. Secondly, an improved gradient method was utilized for the further optimized images. The jagged edges of the enlarged images were basically eliminated by the proposed method, making the images much more smooth, natural, and legible. The experimental results prove that the GPU-based parallel image sharpening algorithm is superior to the currently popular algorithms in calculation efficiency and image quality, and it can be applied in sharpening images and amplifying photos.

Traditional Collaborative Filter (CF) often suffers from the shortage of historic information. A transfer-Bagging algorithm based on hybrid classifiers was proposed for question recommendation. The main idea was that the recommendation and prediction problem were cast into the framework of transfer learning, then the users' demand for recommend questions were treated as target domain, while similar users who had applicable historic information were employed as auxiliary domain to help training target classifiers. The experimental results on both question recommendation platform and popular open datasets show that the accuracy of the proposed algorithm is 10%-20% higher than CF, and 5%-10% higher than single Bagging algorithm. The method solves cold start-up and sparse data problem in question recommendation field, and can be generalized into production recommendation on E-commerce platform.

As for the present research on the dissemination of Internet Public Opinion (IPO), some research use mathematic statistics or intelligent learning to analyze the growing or descending process of a topic related text, and some use cellular automata or Hidden Markov Model (HMM) to find the tendency propagation of the subject of IPO. However, all of them lack the analyses of the impacts of the subject attributes in IPO on its tendency propagation. Based on the systematic synergy of IPO space, the synergistic transition probability between states on whole cells space of discussed IPO was computed firstly, and then it was compared with a local state probability in 9 neighbors of a central cell to decide whether the state of central cell should be converted. After several iterative operations, the degree (magnetisability) which expressed the tendency propagation upon to "+" or "-" was obtained. Through observing the magnetisability-time variable curve, one can clearly handle its evolution. Therefore, a new model and an algorithm of extensive synergistic cellular automata model were presented. The simulation results show that the order-variable parameters of society adaptability can express the subject's group psychology, and it goes towards the majority opinion. Similarly, the order-variable parameters of preference fast make tendency propagation close to the direction of preference, i.e "+" or "-". The model is relatively closer to the real situation of dissemination of IPO.

Through analyzing the transition feature of object based on time sequence in the dynamic information system, trend concept lattice related to the object was proposed. According to the goal of extracting decision rules, two corresponding algorithms were put forward, the former was used for constructing lattice and the later was used for extracting decision rule based on the decision lattice which was generated by the former. Finally, the two algorithms were used in stock forecasting to verify the validity of them.

In this paper, a temperature monitoring and fire alarming system that made use of semantic network technologies was presented. The system was implemented with a context-aware computing framework that built upon an OSGi gateway. Environment temperature info was collected from 1-wire sensor networks and was stored and processed as a part of smart-home context. Customer rule based context reasoning can be done by the framework, and alarming services would be scheduled when it detected dangerous high temperature.

The complexity of Internet Key Exchange (IKE) protocol causes some potential security flaws. After the mechanism of IKE with signature was introduced, the two kinds of man-in-middle attack were analyzed. In order to protect the users' identities from being exposed to the outside, two solutions with some improvements were proposed. Finally the paper made a quantitative capability analysis on the whole.

The software design of Global Positioning System (GPS) vehicle terminal was discussed, which was based on General Packet Radio Service (GPRS) wireless communication, including the definition of communication protocol between vehicle terminal and monitor center, the design of efficient strategy of GPS information receiving and unpacking, and GPRS communication flow design. The work provides a useful reference for developing GPRS communication equipment and GPS location equipment.