To improve the error detection efficiency and the benefit of regression testing of test case sequence， a test case prioritization approach based on historical data and multi-objective optimization was proposed. Firstly， the test case set was clustered according to the text topic similarity and code coverage similarity of test cases， and the association rules were mined for execution failure relationships between test cases according to the historical execution information， thereby preparing for the subsequent process. Then， the multi-objective optimization algorithm was used to sort the test cases in each cluster. After that， the final sorting sequence was generated to separate the similar test cases. Finally， the association rules between test cases were used to dynamically adjust the execution order of test cases， so that the test cases that may fail were executed with priority， so as to further improve the efficiency of defect detection. Compared with random search approach， the approach based on clustering， the approach based on topic model， the approach based on association rules and multi-objective optimization， the proposed approach has the average value of Average Percentage of Faults Detected （APFD） increased by 12.59%， 5.98%， 3.01% and 2.95%， respectively， and has the average value of APFD cost-cognizant （APFDc） increased by 17.17%， 5.04%， 5.08% and 8.21%， respectively. Experimental results show that the proposed approach can improve the benefit of regression testing effectively.

For a long time, video copyright infringement problems have emerged one after another, and the detection of video similarity is an important approach of identifying video copyright infringement. Concerning the problems of the correlation difficulty of multi-feature relation and high time complexity in the existing video similarity detection methods, a fast comparison method based on perceptual hashing and dicing was proposed. First, the key image frames of the video were used to generate a digital fingerprint set. Then, based on the dicing method, the corresponding inverted index was generated to speed up the comparison between digital fingerprints. Finally, the similarity was judged according to the obtained Hamming distance between the digital fingerprints. Experimental results show that the proposed method can reduce the detection time by an average of 93% with ensuring the detection accuracy compared to the traditional perceptual hashing comparison methods; in the comparison with three common methods including Multi-Feature Hashing (MFH), Self-Taught Hashing (STH) and SPectral Hashing (SPH), the mean Average Precision (mAP) of the proposed method is increased by 1.4%, 2% and 2.3%,respectively, and the detection time is shortened by 25%, 32% and 16%, respectively, which verifies the feasibility of the proposed method.

In recent years, deep learning technology has developed rapidly. In Natural Language Processing (NLP) tasks, with text representation technology rising from the word level to the document level, the unsupervised pre-training method using a large-scale corpus has been proved to be able to effectively improve the performance of models in downstream tasks. Firstly, according to the development of text feature extraction technology, typical models were analyzed from word level and document level. Secondly, the research status of the current pre-trained models was analyzed from the two stages of pre-training target task and downstream application, and the characteristics of the representative models were summed up. Finally, the main challenges faced by the development of pre-trained models were summarized and the prospects were proposed.

In order to realize the accurate detection and classification of muscle fatigue states, a new complete muscle fatigue detection and classification system based on human surface ElectroMyoGraphy (sEMG) signals was proposed. Firstly, human sEMG signals were collected through AgCl surface patch electrode and high-precision analog front-end device ADS1299. The time-domain and frequency-domain features of sEMG signals reflecting human muscle fatigue states were extracted after the denoising preprocessing using wavelet transformation. Then, on the basis of the common features such as Integrated ElectroMyoGraphy (IEMG), Root Mean Square (RMS), Median Frequency (MF), Mean Power Frequency (MPF), in order to depict the fatigue states of human muscle more finely, the Band Spectral Entropy (BSE) of frequency domain features of sEMG signals were introduced. In order to compensate the weakness of Fourier transform in dealing with non-stationary signals, the time-frequency feature of the sEMG signals, named mean instantaneous frequency based on Ensemble Empirical Mode Decomposition-Hilbert transform (EEMD-HT), was introduced. Finally, in order to improve the classification accuracy of muscle non-fatigue and fatigue states, the Support Vector Machine optimized by Particle Swarm Optimization algorithm (PSO-SVM) with mutation was used for the classification of sEMG signals to realize the detection of human muscle fatigue states. Fifteen healthy young men were recruited to carry out sEMG signal acquisition experiments, and a sEMG signal database was established to extract features for classification. The experimental results show that, the proposed system can realize high-accuracy sEMG signal acquisition and high-accuracy classification of muscle fatigue states, and its accuracy rate of classification is above 90%.

In order to improve the accuracy and the Out Of Vocabulary (OOV) recognition rate of the Chinese word segmentation, a Chinese word segmentation system based on character representation learning method was proposed. Firstly, the word in the text was mapped to a vector in a high-dimentioanl vecter space using Skip-gram model; then the K-means clustering algorithm was used to acquire clusters of the word vector, and the clustering results were regarded as features of Conditional Random Fields (CRF) model for training. Finally the CRF model was used for word segmentation and OOV recognition. The influences of the word vector dimensions, the number of clusters and different cluster algorithm on word segmentation were analyzed. Experiments were conducted on the 4th CCF Conference on Natural Language Processing & Chinese Computing (NLPCC2015) corpus. Experimental results show that the proposed system can effectively improve Chinese short text segmentation performance without using external knowledge, the F-value and the OOV recognition rate achieve to 95.67% and 94.78% respectively.

Concerning the low correct recognition rate of the Electromyography (EMG) control system, a new Human-Computer Interaction (HCI) system based on Electrooculogram (EOG) assisted EMG was designed and implemented. The feature vectors of EOG and EMG were extracted by threshold method and improved wavelet transform separately, and the feature vectors were integrated together. Then the features were classified by multi-class Support Vector Machine (SVM), and the different control commands were generated according to the result of pattern recognition. The experimental results prove that, compared with the single EMG control system, the new system has better operability and stability with higher correct recognition rate.

To solve the premature convergence problem of Particle Swarm Optimization (PSO), two new methods were introduced to improve the performance cooperatively: When particles’ fitness values were worse than the average, the dynamic Zaslavskii chaotic map formula was devised to modify the inertia weight and velocity, which can make particles break away from the local best and search the global best dynamically; On the contrary, when fitness values were better than or equal to the average, the introduced dynamic nonlinear functions were used to modify the inertia weight and velocity, which can make particles retain favorable conditions and converge to the global best continually. Two methods coordinate dynamically, and make two dynamic swarms cooperate to evolve. Experimental results demonstrate that the new introduced algorithm outperforms several other famous improved PSO algorithms on many well-known benchmark problems.

A new face contour extraction method was proposed by useing skin color and multiple information fusion.The method computed skin probability image based on TSL color space,then selected seed point,finally used multiple information to carry out region growing,extracted face contour.The method employed image pyramid process to avoid heavy computing burdens caused by region growth.Experiment results indicated that the proposed algorithm can extract face contour from approximate skin color backgrounds efficiently and accurately,and bears noise endurance and application adaptability.

Real-time systems could be modeled by using aspect-oriented programming (AOP) technology based on UML. Timing requirements could be separated from the systems and expressed as a time-aspect independence of the systems. So the time-aspect can be designed concurrently, and the time feature of the systems can be managed by the unified model. The time-aspect could be woven into systems to compose real-time systems based on the AOP technology only when needed for a particular application. Real-time systems could be modeled from the static structure, dynamic behaviors and weaving of the time-aspect. The model extends UML to meet the need of AOP technology and the time model, and improves the usability of the software. Finally an elevator case was given as an example.