Because the air quality in different regions of the city are correlated with each other in both time and space, the traditional deep learning model structure is relatively simple, and it is difficult to model from the perspectives of time and space. Aiming at this problem, a Spatio Temporal Air Quality Index (STAQI) model that can simultaneously extract the complex spatial and temporal relationships between air qualities was proposed for air quality prediction. The model was composed of local components and global components, which were used to describe the influences of local pollutant concentration and air quality states of adjacent sites on the air quality prediction of target site, and the prediction results were obtained by using the weighted fusion component output. In the global component, the graph convolutional network was used to improve the input part of the gated recurrent unit network, so as to extract the spatial characteristics of the input data. Finally, STAQI model was compared with various baseline models and variant models. Among them, the Root Mean Square Error (RMSE) of STAQI model is decreased by about 19% and 16% respectively compared with those of the gated recurrent unit model and the global component variant model. The results show that STAQI model has the best prediction performance for any time window, and the prediction results of different target sites verify the strong generalization ability of the model.

The community structure in complex networks can help people recognize basic structure and functions of network. Aiming at the problems of low accuracy and high complexity of most community division algorithms, a community division algorithm based on similarity of common neighbor nodes was proposed. Firstly, a similarity model was proposed in order to calculate the similarity between nodes. In the model, the accuracy of similarity measurement was improved by calculating the tested node pairs and their neighbor nodes together. Secondly, local influence values of nodes were calculated, objectively showing the importances of nodes in the network. Thirdly, the nodes were hierarchically clustered according to the similarity and local influence values of nodes, and preliminary division of network community structure was completed. Finally, the preliminary divided sub-communities were clustered until the optimal modularity value was obtained. The simulation results show that compared with the new Community Detection Algorithm based on Local Similarity (CDALS), the proposed algorithm has the accuuracy improved by 14%, which proves that the proposed algorithm can divide the community structure of complex networks accurately and effectively.

Aiming at the inaccuracy of traditional abnormal flow detection model in the industrial control system, an abnormal flow detection model based on Convolutional Neural Network (CNN) was proposed. The proposed model was based on CNN algorithm and consisted of a convolutional layer, a full connection layer, a dropout layer and an output layer. Firstly, the actual collected network flow characteristic values were scaled to a range corresponding to the grayscale pixel values, and the network flow grayscale map was generated. Secondly, the generated network traffic grayscale image was put into the designed convolutional neural network structure for training and model tuning. Finally, the trained model was used to the abnormal flow detection of the industrial control network. The experimental results show that the proposed model has a recognition accuracy of 97.88%, which is 5 percentage points higher than that of Back Propagation (BP) neural network with the existing highest accuracy.

Aiming at the problem of tracking instability of the Lucas-Kanade (LK) algorithm for the complex situation of moving target deformation, fog and haze, high-speed, uneven illumination and partial occlusion in traffic monitoring, a tracking algorithm based on multi-resolution LK optical flow algorithm and Speed Up Robust Features (SURF) was proposed. The problem tracking failure for large-scale motion between frames of same pixel point in the traditional LK algorithm was solved by the proposed method, and the SURF scale invariant feature transformation algorithm was combined, feature points for optical flow tracking were extracted, and an adaptive template real-time update strategy was developed; the amount of optical flow calculation was reduced while enhancing the resistance ability of moving targets against complex environments. The experimental results show that the feature points matching of the new method is accurate and fast, which has strong adaptability and it is stable in the complicated traffic environment.

Collaborative filtering algorithm is the most widely used algorithm in personalized recommendation system. Focusing on the problem of date sparseness and poor scalability, a new clustering recommendation algorithm based on user interest and social trust was proposed. Firstly, according to user rating information, the algorithm divided users into different categories by clustering technology, and set up a user neighbor set based on interest. In order to improve the accuracy of the calculation of interest similarity, the modified cosine formula was used to eliminate the difference of user scoring criteria. Then, the trust mechanism is introduced to measure implicit trust value among users by defining the direct trust calculation method and indirect trust calculation method, converted a social network to a trust network, and set up a user neighbor set based on trust. Finally, this algorithm combined the predictive value of two neighbor sets to generate recommendations for users by weighting method. The simulation experiment was carried out to test the performance on Douban dataset, found suitable value of α and k. Compared with collaborative filtering algorithm based on users and recommendation algorithm based on trust, the Mean Absolute Error (MAE) decreased by 6.7%, precision, recall and F1 increased by 25%,40% and 37%. The proposed algorithm can effectively improve the quality of recommendation system.

Based on open source softwares of Computer Haptics, visualizAtion and Interactive in 3D (CHAI 3D) and Open Graphic Library (OpenGL), a virtual surgical system was designed for reduction of maxillary fracture. The virtual simulation scenario was constructed with real patients' CT data. A geomagic force feedback device was used to manipulate the virtual 3D models and output haptic feedback. On the basis of the original single finger-proxy algorithm, a multi-proxy collision algorithm was proposed to solve the problem that the tools might stab into the virtual organs during the simulation. In the virtual surgical system, the operator could use the force feedback device to choose, move and rotate the virtual skull model to simulate the movement and placement in real operation. The proposed system can be used to train medical students and for preoperative planning of complicated surgeries.

To overcome the salient extraction results cannot preserve edge and enrich the inner details when extracting image salient region, a new multi-scale extraction approach based on frequency domain was proposed. In order to remove redundant information and get the innovation, the image was Fourier-transformed to get the spectral residual on multiple resolutions. Then normalization processing was applied to obtain the final saliency image. The simulation results show that the proposed method has good visual effect, which can keep the edges of salient region and highlight the whole significant target uniformly at the same time. The area under Receiver Operating Characteristic (ROC) curve of these results also has satisfied performance.

To reduce the calculation complexity of the Joint Probabilistic Data Association (JPDA) joint-association events, due to multiple targets' tracks aggregation, an improved JPDA algorithm, clustering by Meanshift algorithm and optimizing confirmation matrix by Bhattacharya coefficients,was proposed.The clustering center was created by Meanshift algorithm. Then the tracking gate was obtained by calculating Mahalanobis distance between the clustering center and targets' prediction observation. The Bhattacharya likelihood matrix which was as a basis for low probability events was created, consequently the computing complexity of JPDA joint-association events which was related to low probability events was reduced. The experimental results show that the new method is superior to the conventional JPDA both in computational complexity and precision of estimation for multiple targets' tracks aggregation.

In order to improve the low energy utilization efficiency of IEEE 802.11 in wireless mesh network, a modified low energy consumption MAC protocol, Power Control and Collision Avoidance (PCCA) was proposed. Two core algorithms — Dynamic Power Control Algorithm (DPCA) and Collision Avoidance Algorithm (CAA) were introduced into IEEE 802.11 to reduce energy consumption. DPCA can reduce energy transmission consumption by carefully computing the best transmission power through information collected at receiving node; CAA can make advantage of neighborhoods' communication states table to make the potential collisions nodes into sleep state to save energy. The simulation experiment shows that, the PCCA protocol can save about 20% transmission energy at most.