To mine the process model including multi-concurrent 2-loops of triangles in incomplete logs, an AlphaMatch algorithm based on extended Alpha algorithm was proposed. Two activities in triangle structure could be correctly matched in 2-loops of triangles by AlphaMatch in the log without repeated activity sequence, thus the process model with multi-concurrent 2-loops of triangles could be mined. Firstly, the activities in 2-loops of triangles were divided into two categories according to the number of activities. Then, a matrix of head and tail position of the activities was constructed to match the two categories and a footprint matrix was constructed to show the relationship between activities. Finally, a large number of experiments were carried out on ProM platform from model correctness, mining efficiency, fitness and precison. Experimental results show that the Petri net model including multi-concurrent 2-loops of triangles can be mined efficiently by the proposed algorithm.

In order to solve the problems such as too many nodes and low compressibility in the tree structure constructed by CANonical-order tree (CAN-tree) algorithm, an improved CAN-tree algorithm based on restructure was proposed. Firstly, a tree structure was constructed directly with canonical-order, which scans the database only once in the frequent itemset mining algorithm. Then, in order to get a tree structure with high compressibility, a pruning operation was used with support in desending order to restructure the tree. Finally, frequent itemsets were mined out for the reconstructed tree structure. The experimental results show that compared with original CAN-tree algorithm, the number of nodes constructed by the improved CAN-tree algorithm is reduced to less than 20%,and the execution efficiency is improved by 4 to 6 times. The proposed algorithm shortens the execution time of the frequent itemset mining algorithm and effectively compresses the tree structure in it.

The tangential angle acquisition of the traditional geometric path tracking algorithm depends on high precision inertial navigation equipments. In order to solve the problem, a new path tracking algorithm based on cubic B-spline curve fitting was proposed. Firstly, the smooth path was generated by fitting the discrete path points in the priori map. Then, the discrete path points were regenerated by using an interpolation method according to the path equation, and the tangential angle at each point was calculated to realize the optimization and tracking of the multi-sensor fusion path. On the real intelligent vehicle experiment platform, the 20 km/h low-speed-circle and the 60 km/h high-speed-straight-path tracking tests for the proposed algorithm were carried out under the two real road scenes. Under the two typical test scenarios of low-speed-large-curvature and high-speed-straight-path, the maximum lateral error of path tracking of the proposed algorithm is kept within 0.3 m. The experimental results show that, the proposed algorithm can effectively solve the problem of traditional geometric path tracking algorithm's dependence on inertial navigation device, and maintain good tracking performance at the same time.

Concerning that the increasement of accumulated error causes serious distortion of Unmanned Aerial Vehicle (UAV) remote sensing images stitching, a projection error correction algorithm based on space intersection was proposed, Using space intersection theory, the spatial coordinates of 3D points were calculated according to correspondence points. Then all 3D points were orthographic projected onto the same space plane, and the orthographic points were projected onto the image plane to get corrected correspondence points, Finally, M-estimator Sample Consensus (MSAC) algorithm was used to estimate the homography matrix, then the stitching image was obtained. The simulation results show that this algorithm can effectively eliminate the projection error, thus achieve the purpose of inhibiting UAV remote sensing image stitching error.

Concerning the problem of lacking completeness and accuracy in the individuals inference information and scientificity in the overall integration results, which exists in the process of inferring Conditional Probability Table (CPT) in Bayesian network according to expert knowledge, this paper presented a method based on the Dempster-Shafer/Analytic Hierarchy Process (DS/AHP) to derive optimal conditional probability from the expert inference information. Firstly, the inferred information extraction mechanism was proposed to make judgment objects more intuitive and judgment modes more perfect by introducing the knowledge matrix of the DS/AHP method. Then, the construction process of Bayesian network was proposed following an inference sequence of "anterior to later". Finally, the traditional method and the presented method were applied to infer the missing conditional probability table in the same Bayesian network. The numerical comparison analyses show that the calculation efficiency can be improved and the accumulative total deviation can be decreased by 41% through the proposed method. Meanwhile, the proposed method is illustrated to be scientific, applicable and feasible.

To improve the searching speed and get optimal services compositions on large scale of semantic Web services, a quick composition approach based on service cluster and Quality of Service (QoS) was proposed. Using the pre-built service clusters, it could quickly get the candidate service set with the effectively reduced searching space and semantic comparison complexity. It could obtain more optimal compositions by filtering service with the dynamically determined threshold based on the best composition QoS in the process of composition. It adopted an effective redundancy processing method to ensure minimum redundant services were used in the composition, and a service cluster internal filtering method was used to limit the number of candidate services, that solved the operation overtime problems caused by too many compositions. The results of experiments performed on large scale service storage illustrate that the searching speed is improved dozens of times than common methods, and the effectiveness of service filtering and redundancy processing is remarkable, so that the approach can quickly get multiple QoS optimal and non-redundant service compositions, and perform well on deep hierarchy composition in service storage of millions level.

In order to reduce the search space and improve the efficiency of service discovery, the concept of service cluster was put forward. Web services with the same or similar functions were encapsulated as a service cluster. The request/response schema based on service clusters was constructed. The formal definition of service cluster, the architecture and an algorithm to discover the optimal Web service in the service clusters schema were presented. The simulation experiment was conducted on 10000 Web services. The discovery time and rediscovery time under service clusters schema were less than 600ms when the number of service clusters was no more than 1000. However, the above time was more than 900ms in the current service response schema. The efficiency is greatly increased in discovering services under service clusters schema, and the rediscovery time is also greatly decreased.

In clustering based Web service discovery, the service cluster is characterized by indeterminacy because parameters are uneven in name, quantity and order, which results in a great deal of work in parameter matching. For this reason, a logic Petri net based model for Web service cluster was proposed. It built map relationship between clusters and services by denoting the service parameter sets to logic vectors based upon clusters' parameter sets, and unified management for service parameters. Therefore, parameter matching based on semantic similarity is only necessary to process on cluster layer; whereas, in a service cluster, parameter can be located directly by position vector and parameter matching can be realized by logical comparison. The matching magnitude and computation complexity are reduced enormously, and the service discovery efficiency gets improved.

This paper improved the algorithm of generating transitions and searching for path, and proposed a path editing method based on motion graphs. With regard to generating transitions, this paper detected the motion clips which can be used to blend automatically by minimizing the average frame distance between blending frames, and proposed Enhanced Dynamic Time Wrapping (EDTW) algorithm to solve this optimization problem. Concerning path search in the motion graph, this paper used the area between two curves as the target function and improved the strategy of incremental search and the strategy of branch and bound. The result shows that the proposed algorithm can edit and generate the character motions that well match the paths specified by users.

Path planning is designed to make use of terrain and enemy and other information to plan out the largest survival probability penetration trajectory of Unmanned Aerial Vehicle (UAV). After analyzing the simulation needs of path planning, the path planning of UAV was studied. Firstly, a Voronoi diagram was constructed based on the battle field environment full of threats. The Voronoi diagram yields the optimal routes to travel among a set of threat source points to avoid the threats. Then, Dijkstra algorithm was used to search the optimal route. Finally, the simulation system of path planning was carried out on the platform of Visual Studio .Net 2010 based on MS SQL Server 2008 database and Visual C # 2008 language, and the simulation result was given in graph form, which provided a good basis for further study.