Many of the existing multi-view clustering algorithms lack the ability to estimate the reliability of different views and thus weight the views accordingly， and some multi-view clustering algorithms with view-weighting ability generally rely on the iterative optimization of specific objective function， whose real-world applications may be significantly influenced by the practicality of the objective function and the rationality of tuning some sensitive hyperparameters. To address these problems， a Multi-view Ensemble Clustering algorithm based on View-wise Mutual Information Weighting （MEC-VMIW） was proposed， whose overall process consists of two phases： the view-wise mutual weighting phase and the multi-view ensemble clustering phase. In the view-wise mutual weighting phase， multiple random down-samplings were performed to the dataset， so as to reduce the problem size in the evaluating and weighting process. After that， a set of down-sampled clusterings of multiple views was constructed. And， based on multiple runs of mutual evaluation among the clustering results of different views， the view-wise reliability was estimated and used for view weighting. In the multi-view ensemble clustering phase， the ensemble of base clusterings was constructed for each view， and multiple base clustering sets were weighted to model a bipartite graph structure. By performing efficient bipartite graph partitioning， the final multi-view clustering results were obtained. Experiments on several multi-view datasets confirm the robust clustering performance of the proposed multi-view ensemble clustering algorithm.

Since the traditional wavelet threshold functions have some drawbacks such as the non-continuity on the points of threshold, large deviation of estimated wavelet coefficients, Gibbs phenomenon and distortion are generated and Signal-to-Noise Ratio (SNR) can be hardly improved for the denoised signal. To overcome these drawbacks, an improved wavelet threshold function was proposed. Compared with the soft, hard, semi-soft threshold function and others, this function was not only continuous on the points of threshold and more convenient to be processed, but also was compatible with the performances of traditional functions and the practical flexibility was greatly improved via adjusting dual threshold parameters and dual variable factors. To verify this improved function, a series of simulation experiments were performed, the SNR and Root-Mean-Square Error (RMSE) values were compared between different denoising methods. The experimental results demonstrate that the smoothness and distortion are greatly enhanced. Compared with soft function, its SNR increases by 22.2% and its RMSE decreases by 42.6%.

With regard to the requirement of Internet of Things (IoT) application development and the data unification-modeling requirement of Measuring and Control System (MCS), the paper designed a MCS structure based on IEEE1451 standard, which had sensors plug-and-play and IPv6 communication functions. The paper realized dynamic description of network data flow from underlying sensor, intelligent measuring and control node to remote monitor and control application by UML modeling, and finished a general XML data-exchanging interface design. The designed MCS was applied in the process industry of ethanol production. The application results show that it realizes accurate and efficient transmission by using XML data exchanging technology based on IEEE1451 standard. Its data exchanging delay is about 0.51 ms, which can satisfy the requirements of openness, crossing platform and network real-time monitoring application.

Focusing on nurse assignment problem, this paper firstly analyzed nurse assignment problem in aspects of patient-nurse relations, nurses’ professional titles, patients’ nursing grades. An improved stochastic programming model was built which was more suitable for hospitals in China. Then according to the solution structure of the problem, a Genetic Algorithm with Perturb Mutation (PMGA) which was added on every vectors among the solution with a probability was designed. Compared to random greedy algorithm and Bender’s decomposition based greedy algorithm in experiment, PMGA results were more effective than other methods in solving nurse assignment problem within 30 minutes and it would reduce workload more than 8.9% for each nurse in a shift. Especially, GA with perturb mutation was more efficient in solving multi-scenario, multi-trap nurse assignment problems which have solutions without field continuity.

For various applications in today’s service-oriented enterprise computing systems, such as process-oriented service discovering or clustering, it is necessary to measure the distance between two process models. In this paper, we propose a quantitative measure to calculate the distance or similarity between different structured processes. We first introduce a structured workflow model and transform each process into a process structure tree, and then calculate the process distance and its similarity based on the tree edit distance of two structure trees. The proposed distance metric satisfies three distance measure properties, i.e., identity of indiscernible, symmetry and triangle inequality. These properties make the distance metric can be used as a quantitative tool in effective process model management activities. Experiment studies show that the method is feasible. Compared to the adjacency matrix method, the proposed method is more reasonable due to the semantic distance between different structures is considered.

To manage the risk of service, it is necessary to obtain stochastic character of Quality of Service (QoS) that is represented as accurate probability distribution. This paper presented an approach to estimate probability distribution of Web service QoS in the case of small number of samples. Using max entropy principle, the analytical formula of the probability density function can be obtained by transforming the probability distribution estimation problem into an optimal problem with constraints obtained from sampling QoS data. Then an algorithm to estimate parameters of the probability density function was designed. The experimental and simulation results based on real Web service QoS data show the effectiveness of the proposed approach for probability distribution estimation of different QoS attribute. The efficiency and feasibility of the distribution estimation algorithm have got validated by experiments too.

In a complex environment and concerning the problems of choosing parameters brought by the mixture of two multi-robot formation methods, the Leader-Follower method and a behavior-based method, this paper improved two methods and optimized five kinds of behavior parameters online to make the multi-robot formation better with the help of Particle Swarm Optimization (PSO) algorithm. The simulation results validate that the proposed algorithm is feasible and it achieves expected optimization effects.

The solution of Electron-molecule scattering model based on serial mode meets two challenges: long running time and large memory requirement. Parallel computing which would reduce the workload of one computer is a useful method to meet the challenge. Based on master-slave parallel model structure, several optimized approaches were introduced and the parallel algorithm for Electron-molecule scattering was realized. Results of the experiments obtain satisfied speedup and parallel efficiency, and prove the feasibility and validity of this solution.

Random testing is a widely used method of automatic software testing. It selects test data from the input domain at random, so it is easy to actualize automatically. However, the likelihood of finding adequate test data randomly to meet a certain testing criterion is extremely low. Therefore, a pathoriented automatic random testing method based on double constraint propagation (DCPART) was proposed. For a given path, its domain could be gained by splitting a input variables domain and executing doubly constraint propagation algorithm. Moreover, a corresponding test data generator was developed and the empirical work was conducted on a number of programs. Experimental results show that the method can compute path domain more accurately than PRT method, and random testing efficiency can thus be remarkably enhanced.

Platform specific models in most MDA-based development approach for Web applications are defined as the concrete framework on which the target system runs, which leads to the close coupling between platform specific design models and the target frameworks as well as reduce the design model's reusability. In order to resolve these problems, the description of the target framework for Web application was added in the extended MDA-based development model that supported multi-target-frameworks, and in which abstract platform specific model and concrete platform specific model was introduced. J2EE and JavaServer Faces were respectively used as target platform and target framework in the experimental research. The experimental results show this approach can make an effect support to model-driven development for the enhancement of the model's flexibility and reusability.