Focused on the issue that Point-Of-Interest (POI) recommendation has low recommendation accuracy and efficiency, with deep analysis of the influence of social factors and geographical factors in POI recommendation, a POI recommendation algorithm combining location influence was presented. Firstly, in order to solve the sparseness of sign-in data, the 2-degree friends were introduced into the collaborative filtering algorithm to construct a social influence model, and the social influence of the 2-degree friends on the users were obtained by calculating experience and friend similarity. Secondly, by deep consideration of the influence of geographical factors on POI, a location influence model was constructed based on the analysis of social networks. The users' influences were discovered through the PageRank algorithm, and the location influences were calculated by the POI sign-in frequency, obtaining overall geographical preference. Moreover, kernel density estimation method was used to model the users' sign-in behaviors and obtain the personalized geographical features. Finally, the social model and the geographic model were combined to improve the recommendation accuracy, and the recommendation efficiency was improved by constructing the candidate POI recommendation set. Experiments on Gowalla and Yelp sign-in datasets show that the proposed algorithm can quickly recommend POIs for users, and has high accuracy and recall rate than Location Recommendation with Temporal effects (LRT) algorithm and iGSLR (Personalized Geo-Social Location Recommendation) algorithm.

In the era of big data, personalized recommendation system is an effective means of information filtering. One of the main factors that affect the prediction accuracy is data sparsity. Slope One online rating prediction algorithm uses simple linear regression model to solve data sparisity problem, which is easy to implement and has quick score rating, but its training stage needs to be offline because of high time and space consumption when generating differences between items. To solve above problems, a simplified Slope One algorithm was proposed, which simplified the most time-consuming procedure in Slope One algorithm when generating items' rating difference in the training stage by using each item's historical average rating to get the rating difference. The simplified algorithm reduces the time and space complexity of the algorithm, which can effectively improve the utilization rate of the rating data and has better adaptability to sparse data. In the experiments, rating records in Movielens data set were ordered by timestamps then divided into the training set and test set. The experimental results show that the accuracy of the proposed simplified Slope One algorithm is closely approximated to the original Slope One algorithm, but the time and space complexity are lower than that of Slope One, it means that the simplified Slope One algorithm is more suitable for large-scale recommendation system applications with rapid growth of data.

Concerning the limited influence scope and high time complexity of existing influence maximization algorithms in social networks, a k-core filtered algorithm based on independent cascade model was proposed. Firstly, an existing influence maximization algorithm was introduced, its rank of nodes does not depend on the entire network. Secondly, pre-training was carried out to find the value of k which has the best optimization effect on existing algorithms but has no relation with the number of selected seeds. Finally, the nodes and edges that do not belong to the k-core subgraph were filtered by computing the k-core of the graph, then the existing influence maximization algorithms were applied on the k-core subgraph, thus reducing computational complexity. Several experiments were conducted on datasets with different scale to prove that the k-core filtered algorithm has different optimization effects on different influence maximization algorithms. After combined with k-core filtered algorithm, compared with the original Prefix excluding Maximum Influence Arborescence (PMIA) algorithm, the influence range is increased by 13.89% and the execution time is reduced by as much as 8.34%; compared with the original Core Covering Algorithm (CCA), the influence range has no obvious difference and the execution time is reduced by as much as 28.5%; compared with the original OutDegree algorithm, the influence range is increased by 21.81% and the execution time is reduced by as much as 26.96%; compared with the original Random algorithm, the influence range is increased by 71.99% and the execution time is reduced by as much as 24.21%. Furthermore, a new influence maximization algorithm named GIMS (General Influence Maximization in Social network) was proposed. Compared with PIMA and Influence Rank Influence Estimation (IRIE), it has wider influence range while still keeping execution time at second level. When it was combined with k-core filtered algorithm, the influence range and execution time do not have significant change. The experimiental results show that k-core filtered algorithm can effectively increase the influence ranges of existing algorithms and reduce their execution times; in addition, the proposed GIMS algorithm has wider influence range and better efficiency, and it is more robust.

Aiming at the pilot contamination problem in massive Multiple-Input Multiple-Out (MIMO) systems, a dynamic pilot allocation scheme based on graph coloring was proposed. To allocate pilot more reasonably and mitigate pilot contamination, firstly, an edge-weighted interference graph based on cooperation among cells was constructed to describe the strength of pilot contamination among multi-cell users, whereby two users in different cells were connected by a weighted edge. Then, based on the traditional graph coloring theory, pilot resources were allocated preferentially to users who were heavily polluted by the characteristics of different weighted edge for connected users. The theoretical analysis and simulation results show that, compared with existing distributed pilot allocation scheme, the proposed pilot allocation scheme can reduce the inter-cell interference and enhance the uplink achievable sum rate by considering pilot reuse of all cells and centralized pilot allocation mechanism based on graph coloring.

In order to solve the problems of copyright registration, rampant piracy and copyright disputes faced by digital intellectual property under Internet ecology, a Digital Copyright Identifier (DCI) control model of digital works without trusted third party was proposed. Firstly, the Peer-to-Peer (P2P) architecture based on the concept of de-centralization of blockchain was constructed. The blockchain replaced the traditional database as the core of storage mechanism. Through the creation of transactions, construction of blocks, legitimacy validation and link of blocks a digital work blockchain transaction information storage structure was built, guaranteeing the copyright information not be tampered and traceable. Secondly, the digital distribution protocol based on smart contract was proposed, three types of contracts include copyright registration, inquiry and transfer were designed, and the transactions were generated by automatically executing the preset instructions to ensure the transparency and high efficiency of models. Theoretical analysis and simulation show that the probability of forged block attack is close to zero in the digital work blockchain network, compared with the traditional copyright authentication mechanism based on trusted third party, the model has better architectural security. The experimental results show that the model simplifies the threshold of digital copyright registration, enhances the authority of copyright certification and has better real-time and robustness.

To solve the coverage and capacity optimization problem of Self-Organizing Network (SON) in the 3rd Generation Partnership Project (3GPP), an active antenna down-tilt angle optimization method based on Particle Swarm Optimization (PSO) algorithm was proposed. First, the number of User Equipments (UE) served by evolved Node B (eNB) was determined, and the Reference Signal Received Power (RSRP) and position measured from the UE were obtained. Second, the Spectral Efficiency (SE) was regarded as the fitness function which defined by optimization goals. Then, down-tilt angle optimization was regarded as multidimensional optimization problem, and antenna down-tilt angle was regarded as the set of particles to resolve the optimal value by the PSO algorithm. Finally, the capacity and coverage self-optimization of Long Term Evolution (LTE) networks was achieved by adjusting down-tilt angle independently. By simulations, different objective functions made different optimization results. When the average spectrum efficiency was set as the optimization goal, the spectral efficiency of traditional golden section algorithm increased by 12.9% than primary settings, the spectral efficiency of PSO was increased by 22.5%. When the weighted average spectral efficiency was set as the optimization goal, the spectral efficiency of golden section algorithm was not significantly improved but that of PSO was increased by 19.3% for edge users. The experimental results show that the proposed method improves cell throughput and system performance.

The existing detection approaches for fake plate vehicles have high cost and low efficiency. A new parallel detection approach, called TP-Finder, was proposed based on historical Automatic Number Plate Recognition (ANPR) dataset. To effectively handle the data skew problem emerged in the parallel processing of large-scale dataset, a new data partition strategy based on the idea of integer partition was implemented, which obviously improved the performance of fake plate vehicle detection. Besides, a prototype system for recognizing fake plate vehicles was developed based on the TP-Finder approach, and it could exactly present historical trajectories of all suspicious fake plate vehicles. Finally, the performance of TP-Finder approach was verified on a real ANPR dataset from a city. The experimental results prove that the partition strategy of TP-Finder can achieve a maximum of 20% performance improvement compared with the default MapReduce partition strategy.

Aiming at false segmentation of small regions and high computational complexity in traditional color image segmentation algorithm, a hierarchical method of color image segmentation based on rough set and HIS (Hue-Saturation-Intensity) space was proposed. Firstly, for the reason that the singularities in HSI space are the achromatic pixels in RGB space, the achromatic regions of RGB space were segmented and labeled in order to remove the singularities from the original image. Secondly, the original image was converted from RGB space to HSI space. In intensity component, in view of spatial neighbor information and regional distribution difference, the original histogram was weighted by homogeneity function with changing thresholds and gradience. The weighted and original histograms were respectively used as the upper and lower approximation sets of rough set. The new roughness function was defined and applied to image segmentation. Then the different regions obtained in the previous stage were segmented according to the histogram in hue component. Finally, the homogeneous regions were merged in RGB space in order to avoid over-segmentation. Compared with the method based on rough set proposed by Mushrif etc. (MUSHRIF M M, RAY A K. Color image segmentation: rough-set theoretic approach. Pattern Recognition Letters, 2008, 29(4): 483-493), the proposed method can segment small regions easily, avoid the false segmentation caused by the correlation between RGB color components, and the executing speed is 5-8 times faster. The experimental results show the proposed method yields better segmentation, and it is efficient and robust to noise.

In order to solve the problem of exponential increase of label space, an overlapping community discovery algorithm based on latent feature was proposed. Firstly, a generative model for network including overlapping communities was proposed. And based on the proposed generative model, an optimal object function was presented by maximizing the generative probability of the whole network, which was used to infer the latent features for each node in the network. Next, the network was induced into a bipartite graph, and the lower bound of feature number was analyzed, which was used to optimize the object function. The experiments show that, the proposed overlapping community discovering algorithm can improve the recall greatly while keeping the precision and execution efficiency unchanged, which indicates that the proposed algorithm is effective with the exponential increase of label space.

Aiming at improving the robustness in pre-processing and extracting features sufficiently for Synthetic Aperture Radar (SAR) images, an automatic target recognition algorithm for SAR images based on Deep Belief Network (DBN) was proposed. Firstly, a non-local means image despeckling algorithm was proposed based on Dual-Tree Complex Wavelet Transformation (DT-CWT); then combined with the estimation of the object azimuth, a robust process on original data was achieved; finally a multi-layer DBN was applied to extract the deeply abstract visual information as features to complete target recognition. The experiments were conducted on three Moving and Stationary Target Acquisition and Recognition (MSTAR) databases. The results show that the algorithm performs efficiently with high accuracy and robustness.

With regard to the advantages and disadvantages of image retrieval algorithm based on edge orientation autocorrelogram, a kind of image retrieval algorithm based on edge direction histogram correlation matching was proposed. Firstly, the salt and pepper noise in image was filtered by using an adaptive median filter, and then Sobel operator was used to extract image edge. After the edge orientation histogram was got through calculating the edge gradient amplitude and angle, the feature vector was constituted. Lastly, Spearman rank correlation coefficient was used to calculate the correlation coefficient between the feature vectors of images, as a measure of image similarity. Compared with the algorithm based on edge orientation autocorrelogram, the average precision and the recall rate of the new image retrieval algorithm increased by 10.5% and 9.7%. And the retrieval time consumption was also reduced by 7.5%. The experimental results verify the effectiveness of the proposed algorithm. The algorithm could be applied in medium to large image retrieval system to improve retrieval effect and raise the system speed.

In order to achieve the high efficiency in automatic train operation, on the basis of the analysis of the train at different stages of operation, taking parking as the key stage, analytic hierarchy process was used to get quantitative description of the importance between each performance indexes and evaluation function of parking controls comprehensive performance in this stage, then the fuzzy manipulation rules of the online control were got. The offline operation of train under the rules was simulated for several times, the different schemes in sub-regional division and start braking point selection were scored to get the parking manipulation scheme which performance indexes are the best. Finally the simulation system was designed based on VC++ platform, and it has verified that the practical effect of the train running under the control algorithm has good parking precision, comfort and time saving.

In order to improve the accuracy and reliability of cognitive radio spectrum sensing, an optimal linear cooperation spectrum sensing method based on Chaos Harmony Search (CHS) algorithm was proposed in this paper. This algorithm is based on the linear weighted cooperative spectrum sensing model with energy detection, using the optimization capability of Harmony Search (HS) and the traverse and randomness of chaotic system to find the optimal weight values and then improve the performances of spectrum sensing for cognitive radio networks. The simulation results show that the proposed algorithm has better optimal performance and convergence speed than the traditional HS algorithm. This CHS algorithm can obtain optimal weight values and improve the probability of detection in complex communications environment. Besides, cooperation spectrum sensing performance based on the proposed algorithm is better than the existing Modified Deflection Coefficient (MDC) method with the same false probability.

In order to improve the searching accuracy of motion estimation, a new algorithm called Directional Adaptive Sampling Search (DASS) algorithm was proposed. According to the information of matching error in search patterns, the algorithm adopts two sorts of triangle search patterns adaptively. The strategy of local sampling search was employed for the sake of big-motion vector. Early termination strategy was adopted in the procedure of DASS so as to further speed up the search. The experimental results show that the proposed algorithm not only ensures the speed but also improves the accuracy of search with Peak Signal-to-Noise Ratio (PSNR) degradation of only 0.28dB on average.

In action classification, methods of feature extraction were either simple with low accuracy, or complicated with poor real-time quality. To resolve this problem, firstly, Enhanced Gait Energy Image (EGEI) was derived from Gait Energy Image (GEI); secondly, high dimensional feature space of the action was reduced to lower dimensional space by Two-Dimensional Locality Preserving Projection (2DLPP); then Nearest-Neighbor (NN) classifier was adopted to distinguish different actions. EGEI could extract more obvious feature information than GEI; 2DLPP outperformed principal component analysis and locality preserving projections in dimensional reduction. It was tested on the Weizmann human action dataset. The experimental results show that the proposed algorithm is simple, achieves higher classification accuracy, and the average recognition ratio reaches 91.22%.