The traditional multi-path load balancing algorithms cannot effectively perceive the running state of the network, cannot comprehensively consider the real-time transmission states of the links and most of them lack adaptability. In order to solve these problems, a Software Defined Network(SDN) adaptive multi-path Load Balancing Algorithm based on Spider Monkey Optimization(SMO-LBA) was proposed based on the idea of centralized control and whole network control of SDN. Firstly, the perceptul ability of data center network was used to obtain the multi-path real-time link state information. Then, based on the global exploration and local exploitation ability of spider monkey optimization algorithm, the link idle rate was used as the adaptability value of each path, and the paths were dynamically evaluated and updated by introducing the adaptive weight. Finally, the path with the lowest link occupancy rate in data center network was determined as the optimal forwarding path. The fat tree topology was selected to carry out the simulation experiment on Mininet platform. Experimental results show that SMO-LBA can improve the throughput and average link utilization of data center network, and realize the adaptive load balancing of the network.

User relevance measure is the foundation and core of heterogeneous information network research. The existing user relevance measure methods still have improvement space due to insufficient multi-dimensional analysis and link analysis. Aiming at the fact, a user relevance measure method combining Latent Dirichlet Allocation (LDA) and meta-path analysis was proposed. Firstly, the LDA was used to model the topic, and the relevance of nodes was analyzed by the node contents in the network. Secondly, the meta-path was introduced to describe the relationship type between nodes, and relevance measure was carried out for users in heterogeneous information network by relevance measure method (DPRel). Thirdly, the relevance of nodes was incorporated into the calculation of user relevance measure. Finally, the experiment was carried out on IMDB real movie dataset, and the proposed method was compared with the collaborative filtering recommendation method embedded in LDA topic model ULR-CF (Unifying LDA and Ratings Collaborative Filtering) and meta-path based similarity method (PathSim).The experimental results show that the proposed method can overcome the drawback of data sparsity and improve the accuracy of user relevance measure.

To solve the sparse and cold start problems of recommendation system, a Trust Regularization Euclidean Embedding (TREE) algorithm by fusing trust information was proposed. Firstly, the Euclidean embedding model was employed to embed the user and project in the unified low-dimensional space. Secondly, to measure the trust information, both the project participation degree and user common scoring factor were brought into the user similarity calculation formula. Finally, a regularization term of social trust relationship was added to the Euclidean embedding model, and trust users with different preferences were used to constrain the location vectors of users and generate the recommendation results. In the experiments, the proposed TREE algorithm was compared with the Probabilistic Matrix Factorization (PMF), Social Regularization (SoReg), Social Matrix Factorization (SocialMF) and Recommend with Social Trust Ensemble (RSTE) algorithms. When dimensions are 5 and 10, TREE algorithm has the Root Mean Squared Error (RMSE) decreased by 1.60% and 5.03% respectively compared with the optimal algorithm RSTE on the dataset Filmtrust.While on the dataset Epinions, the RMSE of TREE algorithm was respectively 1.12% and 1.29% lower than that of the optimal algorithm SocialMF. Experimental results show that TREE algorithm further alleviate the sparse and cold start problems and improves the accuracy of scoring prediction.

Concerning the high time complexity of traditional heuristic search-based multi-label feature selection algorithm, an Easy and Fast Multi-Label Feature Selection (EF-MLFS) method was proposed. Firstly, Mutual Information (MI) was used to measure the features and the correlations between the labels of each dimension; then, the obtained correlations were added up and ranked; finally, feature selection was performed according to the total correlation. The proposed method was compared to six existing representative multi-label feature selection methods such as Max-Dependency and Min-Redundancy (MDMR) algorithm, Multi-Label Naive Bayes (MLNB) method. Experimental results show that the average precision, coverage, Hamming Loss and other common multi-label classification indicators are optimal after feature selection and classificationby using EF-MLFS method. In addition, global search is not required in the method, so the time complexity is significantly reduced compared with MDMR and Pairwise Mutli-label Utility (PMU).

Concerning the low recommendation accuracy of personalized commodity recommendation methods, a Commodity Recommendation Method Integrating User Trust and Brand Recognition (TBCRMI) was proposed. By analyzing the user's purchase behavior and evaluation behavior, the user's recognition of brands and the activities of users themselves were calculated. Then Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm was used to cluster the users, based on which the user trust relationship was fused, and the nearest neighbors were obtained by Top- K method. Finally, the target user commodity recommendation list was generated based on the nearest neighbors. In order to verify the effectiveness of the algorithm, two datasets (Amazon Food and Unlocked Mobile Phone) were used, User based Collaborative Filtering (UserCF) algorithm, Collaborative Filtering recommendation algorithm with User trust (SPTUserCF) and Merging Trust in Collaborative Filtering (MTUserCF) algorithm were chosen, and the accuracy, recall and F1 value were compared and analyzed. The experimental results show that TBCRMI is superior to the commonly used personalized commodity recommendation methods in either multi-brand comprehensive recommendation or single brand recommendation.

Heterologous splicing is a typical tampering behavior for digital voice. It mainly uses the audio editing software to splice the voice clips recorded in different scenes, so as to achieve the purpose of changing the semantics of voice. Considering the difference of background noise in different scenes, a tampering detection algorithm based on noise consistency for digital voice heterologous splicing was proposed. Firstly, the Time-Recursive Averaging (TRA) algorithm was applied to extract the background noise contained in the voice to be detected. Then, the Change-Point Detection (CPD) algorithm was used to detect whether abrupt changes existed in the noise variance, which was used to determine whether the voice was tampered, and to locate the tampering position of the testing voice. The experimental results show that the proposed algorithm can achieve good performance in detecting the tampering position of heterologous splicing for digital voice.

A kind of Energy-efficient Scheduling Algorithm under the Constraint of Reliability (ESACR) for the random tasks in multiprocessor system was proposed. It would choose the processor which might consume the least energy when the task's deadline could be guaranteed. For the signal processor, Earliest Deadline First (EDF) strategy was used to schedule the tasks and all the tasks were made execute in the same voltage/frequency. When the new task could not match the deadline, the non-execution voltage/frequency of former tasks would be raised. At the same time, the recovery time was reserved for the executing task in order to promise that the task could be rescheduled when errors happened. The simulation shows that the ESACR can provide the better energy efficiency with the guarantee of system reliability , compared to Highest Voltage Energy-Aware (HVEA), Minimum Energy Minimum Completion time (ME-MC) and Earliest Finish First (EFF).

As an important part of the urban vehicle network, bus vehicle network provides supports for a wide range of urban-vehicle communication network due to cyclical movement law. However, the complex urban road environment brings great challenges to highly efficient and reliable routing protocols for bus vehicle network. In bus vehicle network with the characteristics of cyclical movement, a new protocol named SRMHR (Single & Realmending-Multi Hop Routing) was proposed to ensure the single hop link's life time and multi-hop submission probability in limited delay. According to the signal propagation attenuation model and vehicle mobility model, a single hop selection mechanism and a multi-hop delay probability forwarding mechanism were proposed to ensure the reliability and effectiveness of bus-assistant forwarding. On the urban traffic simulation platform, using real road traffic data of slight adjustment, the performance of signal attenuation model, single hop selection mechanism and light correction model under different traffic densities were tested. The results prove the validity of each link of the scheme. Comparison with SF (Spray and Focus) and SW (Spray and Wait) proves that SRMHR protocol has a higher successful rate of data transmission and lower delivery delay.

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.

In mass data era, the research on knowledge discovery of massive and distributed data has become the hot spot in both academic field and industry. The problem of load balance is one of the important factors that must be considered in developing a distributed mining algorithm. Therefore, a distributed association rules mining algorithm with load balance based on vertical FP-tree (VFP-LBDM) was proposed in this paper. Vertical frequent pattern tree was used in this algorithm to store items and their associations, and there was no need to combine the local mining results. Therefore, the communication cost was reduced and the processing procedure was also simplified. At the same time, the algorithm used the hybrid architecture in which the central site assigned tasks according to the processing capacity of each local site. It realized the load balance and improved the performance of the algorithm. The experiment shows that the algorithm given in this paper is feasible and has higher efficiency.

With the enhancement of computing performance in multiprocessor systems, the management of energy consumption becomes more important, and how to meet real-time constraints and effectively reduce energy consumption in the real-time scheduling is also a key issue. Based on multiprocessor computing systems, concerning randomly arrived task, On-Line Energy-Aware Scheduling Algorithm (OLEAS) was proposed. The algorithm meeting the task deadlines under the premise possibly puts the task scheduler on the least energy consumption producing processor. When a task on all the processors could not meet the deadline requirements, the part of the task between the processors shall be adjusted possibly to meet the deadline requirements. Meanwhile, OLEAS was in a bid to execute the task on a single processor according to the average voltage/frequency, thus reducing the energy consumption. When the new task did not meet the deadline requirements, the former voltage/frequency of unexecuted tasks should be one by one adjusted higher. Compared with the performance of EFF (Earliest Finish First), HVEA (Highest Voltage Energy-Aware), LVEA (Lowest Voltage Energy-Aware), MEG (Minimum Energy Greedy) and ME-MC (Minimum Energy Minimum Completion time) in simulated experiments, the final result shows OLEAS owns obviously comprehensive advantage in the aspect of meeting task deadlines and energy consumption saving.

Collaborative recommendation is widely used in E-commerce personalized service. But the existing methods cannot provide high level personalized service due to sparse data and cold start. To improve the accuracy of collaborative recommendation, a collaborative recommendation method based on Social Network Analysis (SNA) was proposed in this paper by using SNA to improve the collaborative recommendation methods. The proposed method used SNA technology to analyze the trust relationships between users, then quantified the relationships as trust values to fill the user-item matrix, and used these trust values to calculate the similarity of users. The effectiveness of the proposed method was verified by the experimental analysis. Using trust values to expand the user-item matrix can not only solve the problem of sparse data and cold start effectively, but also improve the accuracy of collaborative recommendation.

To solve the problems such as low level automation and poor adaptability of current entity recognition methods, a Deep Web entity recognition method based on Back Propagation (BP) neural network was proposed in this paper. The method divided the entities into blocks first, then used the similarity of semantic blocks as the input of BP neural network, lastly obtained a correct entity recognition model by training which was based on the autonomic learning ability of BP neural network. It can achieve entity recognition automation in heterogeneous data sources. The experimental results show that the application of the method can not only reduce manual interventions, but also improve the efficiency and the accuracy rate of entity recognition.

In Web service matching, the concept similarity computation based on semantic distance plays an important role. Because the influence of semantic asymmetry and semantic density has not been considered in current concept similarity computation based on semantic distance, the computation result is not accurate. To enhance the accuracy of the concept similarity computation, the semantic distance-based concept similarity computation was improved by adding the asymmetry factor and density factor on the basis of the current research. Finally, the feasibility of the improved semantic distance-based concept similarity computation was verified via an example. According to the contrast analysis, the improved semantic distance-based concept similarity computation can reflect semantic relationship between concepts more truly and the computation result is more in line with the objective reality.

A great deal of Web services and requests exist in Web environment. Web services matchmaking based on semantic can improve accuracy of service discovery. Because of complicated semantic calculation, the reaction rate of Web service matchmaking was slow. Firstly, this paper analyzed the process of semantic Web service matchmaking to make clear that the large amount of semantic calculation exited in Inputs/Ouputs (I/O) matchmaking phase. Secondly, an I/O matchmaking optimized method of semantic Web services with efficient index was put forward on the basis of the studies on I/O matchmaking algorithms and main influence factors of semantic similarity, which included the creation of efficient index and the raise of the heuristic filter mechanism based on the re-hash secondary detection. Finally, the proposed method was proved to be feasible and rational via an instance. The proposed method can reduce semantic calculation and promote reaction rate by filtering some irrelevant Web services. Furthermore, the experience of users can be improved.

 This paper proposed a workflow authorization model based on RBAC(Role-Based Access Control) for collaborative design system.Different from traditional access control authorization models,this model provided the notion of temporal-spatial permission which represents the fact that can only perform certain operation on a task for a certain time interval and a certain spatial range of Internet/Intranet,namely the workflow authorization based on RBAC for collaborative design system not only relates with time,but also relates with Internet/Intranet address.It can not only ensure that only authorized users could execute a task,but also ensure that the authorization flow is synchronized with workflow and the dynamic change of spatial range of Internet/Intranet address.

The technologies of Web page parser were introduced. And after making a best estimation of the merits and weakness of the existing methods, a more effective method for segmenting the HTML page in the news Web site was proposed. And then,a HTML Parser named TVPS was designed and realized based on the requirement of the projects. The experimental results show that the system has achieved great performance and meets the needs.