Feature selection is a key step in data preprocessing for software defect prediction. Aiming at the problems of existing feature selection methods such as not significant dimension reduction performance and low classification accuracy of selected optimal feature subset， a feature selection method for software defect prediction based on Self-adaptive Hybrid Particle Swarm Optimization （SHPSO） was proposed. Firstly， combined with population partition， a self-adaptive weight update strategy based on Q-learning was designed， in which Q-learning was introduced to adaptively adjust the inertia weight according to the states of the particles. Secondly， to balance the global search ability in the early stage of the algorithm and the convergence speed in the later stage， the curve adaptivity based time-varying learning factors were proposed. Finally， a hybrid location update strategy was adopted to help particles jump out of the local optimal solution as soon as possible and increase the diversity of particles. Experiments were carried out on 12 public software defect datasets. The results show that the proposed method can effectively improve the classification accuracy of software defect prediction model and reduce the dimension of feature space compared with the method using all features， the commonly used traditional feature selection methods and the mainstream feature selection methods based on intelligent optimization algorithms. Compared with Improved Salp Swarm Algorithm （ISSA）， the proposed method increases the classification accuracy by about 1.60% on average and reduces the feature subset size by about 63.79% on average. Experimental results show that the proposed method can select a feature subset with high classification accuracy and small size.

Aiming at the problems in Multi-scale Generative Adversarial Networks Image Inpainting algorithm （MGANII）， such as unstable training in the process of image inpainting， poor structural consistency， insufficient details and textures of the inpainted image， an image inpainting algorithm of multi-scale generative adversarial network was proposed based on multi-feature fusion. Firstly， aiming at the problems of poor structural consistency and insufficient details and textures， a Multi-Feature Fusion Module （MFFM） was introduced in the traditional generator， and a perception-based feature reconstruction loss function was introduced to improve the ability of feature extraction in the dilated convolutional network， thereby supplying more details and texture features for the inpainted image. Then， a perception-based feature matching loss function was introduced into local discriminator to enhance the discrimination ability of the discriminator， thereby improving the structural consistency of the inpainted image. Finally， a risk penalty term was introduced into the adversarial loss function to meet the Lipschitz continuity condition， so that the network was able to converge rapidly and stably in the training process. On the dataset CelebA， compared with MANGII， the proposed multi-feature fusion image inpainting algorithm can converges faster. Meanwhile， the Peak Signal-to-Noise Ratio （PSNR） and Structural SIMilarity （SSIM） of the images inpainted by the proposed algorithm are improved by 0.45% to 8.67% and 0.88% to 8.06% respectively compared with those of the images inpainted by the baseline algorithms， and Frechet Inception Distance score （FID） of the images inpainted by the proposed algorithm is reduced by 36.01% to 46.97% than the images inpainted by the baseline algorithms. Experimental results show that the inpainting performance of the proposed algorithm is better than that of the baseline algorithms.

In order to reduce the regression test set and improve the efficiency of regression test in the Continuous Integration （CI） environment， a regression test suite selection method for the CI environment was proposed. First， the commits were prioritized based on the historical failure rate and execution rate of each test suite related to each commit. Then， the machine learning method was used to predict the failure rates of the test suites involved in each commit， and the test suite with the higher failure rate were selected. In this method， the commit prioritization technology and the test suite selection technology were combined to ensure the increase of the failure detection rate and the reduction of the test cost. Experimental results on Google’s open-source dataset show that compared to the methods with the same commit prioritization method and test suite selection method， the proposed method has the highest improvement in the Average Percentage of Faults Detected per cost （APFDc） by 1% to 27%； At the same cost of test time， the TestRecall of this method increases by 33.33 to 38.16 percentage points， the ChangeRecall increases by 15.67 to 24.52 percentage points， and the test suite SelectionRate decreases by about 6 percentage points.

Considering the lack of effective trend feature descriptors in existing methods， financial technical indicators such as Vertical Horizontal Filter （VHF） and Moving Average Convergence/Divergence （MACD） were introduced into power data analysis. An anomaly detection algorithm and a load forecasting algorithm using financial technical indicators were proposed. In the proposed anomaly detection algorithm， the thresholds of various financial technical indicators were determined based on statistics， and then the abnormal behaviors of user power consumption were detected using threshold detection. In the proposed load forecasting algorithm， 14 dimensional daily load characteristics related to financial technical indicators were extracted， and a Long Shot-Term Memory （LSTM） load forecasting model was built. Experimental results on industrial power data of Hangzhou City show that the proposed load forecasting algorithm reduces the Mean Absolute Percentage Error （MAPE） to 9.272%， which is lower than that of Autoregressive Integrated Moving Average （ARIMA）， Prophet and Support Vector Machine （SVM） algorithms by 2.322， 24.175 and 1.310 percentage points， respectively. The results show that financial technical indicators can be effectively applied to power data analysis.

The emergence of RAMCloud has improved user experience of Online Data-Intensive (OLDI) applications. However, its energy consumption is higher than traditional cloud data centers. An energy-efficient strategy for disks under this architecture was put forward to solve this problem. Firstly, the fitness function and roulette wheel selection which belong to genetic algorithm were introduced to choose those energy-saving disks to implement persistent data backup; secondly, reasonable buffer size was needed to extend average continuous idle time of disks, so that some of them could be put into standby during their idle time. The simulation experimental results show that the proposed strategy can effectively save energy by about 12.69% in a given RAMCloud system with 50 servers. The buffer size has double impacts on energy-saving effect and data availability, which must be weighed.

The activities of the programmers including copy, paste and modify result in a lot of code clone in the software systems. However, the inconsistent change of code clone is the main reason that causes program error and increases maintenance costs in the evolutionary process of the software version. To solve this problem, a new research method was proposed. The mapping relationship between the clone groups was built at first. Then the theme of lineal cloning cluster was extracted using Latent Dirichlet Allocation (LDA) model. Finally, the inconsistent change probability of code clone was predicted. A software which contains eight versions was tested and an obvious discrimination was got. The experimental results show that the method can effectively predict the probability of inconsistent change and be used for evaluating quality and credibility of software.

An fast image stitching algorithm based on improved Speeded Up Robust Feature (SURF) was proposed to overcome the real-time and robustness problems of the original SURF based stitching algorithms. The machine learning method was adopted to build a binary classifier, which identified the critical feature points obtained by SURF and removed the non-critical feature points. In addition, the Relief-F algorithm was used to reduce the dimension of the improved SURF descriptor to accomplish image registration. The weighted threshold fusion algorithm was adopted to achieve seamless image stitching. Several experiments were conducted to verify the real-time performance and robustness of the improved algorithm. Furthermore, the efficiency of image registration and the speed of image stitching were improved.

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%.

A workflow customization model for a collaborative Software-as-a-Service (SaaS) platform of industrial chains was proposed based on the mapping between workflow with operation and the custom relationship between the enterprise groups with workflow. A drive rule and a load and control mode of the workflow model were proposed to provide the dynamic load based on the identities of users. The proposed method was validated by the workflow customization on out application of the after service of automobile parts industrial chains, which showed that it met the needs of workflow customization on the collaborative SaaS platform of industrial chains.

In order to overcome the problems of low convergence precision and easily relapsing into local extremum in basic Fruit Fly Optimization Algorithm(FOA), by introducing the chaos algorithm into the evolutionary process of basic FOA, an improved FOA called Adaptive Chaos FOA (ACFOA)is proposed. In the condition of local convergence, chaos algorithm is applied to search the global optimum in the outside space of convergent area and to jump out of local extremum and continue to optimize. Experimental results show that the new algorithm has the advantages of better global searching ability, speeder convergence and more precise convergence.

In this paper, attraction and exclusion operations of bacterial chemotaxis were introduced into original Fruit Fly Optimization Algorithm (FOA), and FOA based on Bacterial Chemotaxis (BCFOA) was proposed. Exclusion (to escape the worst individual) or attraction (to be attracted by the best individual) was decided to perform by judging the fitness variance is zero or no, so that the problem of premature convergence caused by the loss of population diversity, which resulted from the fact that individuals only were attracted by the best one in FOA, was solved. The experimental results show that the new algorithm has the advantages of better global searching ability, and faster and more precise convergence.

Concerning the high computation complexity and low efficiency in traditional stereo matching method based on belief propagation, a fast-converging algorithm was proposed. When calculating the confidence level of each pixel, the algorithm only utilized the information translated from the neighboring pixels in an adaptive support window, while ignoring the impact of the pixels beyond the window. The experimental results show that the proposed algorithm can reduce 40% to 50% of computation time while maintaining the matching accuracy. Therefore, it can meet the real-time requirement for stereo matching.

Based on Euclidean distance, the classic Fuzzy C-Means (FCM) clustering algorithm has the limitation of equal partition trend for data sets. And the clustering accuracy is lower when the distribution of data points is not spherical. To solve these problems, a distance correction factor based on dot density was introduced. Then a distance matrix with this factor was built for measuring the differences between data points. Finally, the new matrix was applied to modify the classic FCM algorithm. Two sets of experiments using artificial data and UCI data were operated, and the results show that the proposed algorithm is suitable for non-spherical data sets and outperforms the classic FCM algorithm in clustering accuracy.

Concerning the copyright protection of binary document images, a zero watermark algorithm was proposed. This algorithm constructed the texture image based on Local Binary Pattern (LBP), and then zero watermark information was constructed from the texture spectral histograms of the texture image. This method had a better invisibility compared to other text image watermarking, and the original image information would not be changed. Watermark attacks including image cropping, adding noise and rotation operators were tested. The experimental results show that the proposed zero watermark algorithm has a good performance in robustness. And these attack operators have little impact on zero watermark information, and the algorithm is of stability with the lowest standard correlation above 0.85.

A new strategy of resources distribution based on fuzzy decision making was provided, and a model of multi-objective fuzzy decision making was built to solve the resources distribution problems in grid computing. Also implementation of the strategy was described. Analysis proves that this model not only provides the best resources to tasks, but also enhances the success of matching resources and the efficiency of using resources.

A new anomaly detection method was proposed based on positive selection. The method learned the characteristic of "self" space by clustering, and then selected typical samples from every cluster to construct detectors. And positive selection was used to detect anomalies. The new algorithm is not only effective in certain application with large number of "self" samples, but also avoids the shortcoming by randomly selecting sample in VDetector. Experimental results on Ring data and biomedical data show that the new method is more effective in anomaly detection.

Design and implementation of a government official document classification system with topic phrase were presented. This system fully considered the value of topic phrase in the classification preprocessing, and made feature space transformation and dimension reduction by the stochastic keyword generation and the Bootstrapping. It differed from the traditional text classification preprocessing, and the performance of the official document classification system was improved. Official document classification using stochastic keyword generation outperforms other methods.

A dynamic resource allocation scheme based on dynamic policies and mobile predicted information was presented for the problem that traditional policies cannot preferably get adapted to the change of network state. Policy Decision Point （PDP） made decisions before the mobile users' arriving and worked out parameter values of the action according to the predicted information of the users,guidance policies and universal policies when it made decisions, which decreased the amount of stored policies and improved the adaptability of policies to network state. By experiments and analysis, it is shown that this scheme insures new call blocking probability, reduces handoff call dropping probability and increases network resource utilizing rate.

Safety is still a crucial requirement in component-based safety critical software. A safety interface scheme under multi-faults mode was introduced, and this scheme was applied to the development of railway computer interlocking software. By defining the safety interface for each component of the interlocking software, the safety of the interlocking system was guaranteed.

A process-oriented performance evaluation was presented, which analysed the systems combined workload characteristic with resource utility by different nodes' roles. This way simplifies the complex system environment and the test result-set includes much more information than common ways. This method has been applied in some real systems with tens of nodes and several key problems in design and hidden troubles of equipments have been found in time.