A ResNet-based faked sample detection algorithm was proposed for the detection of faked samples in audio scenes with low faking cost and undetectable sound replacement. The Constant Q Cepstral Coefficient （CQCC） features of the audio were extracted firstly， then the input features were learnt by the Residual Network （ResNet） structure， by combining the multi-layer residual blocks of the network and feature normalization， the classification results were output finally. On TIMIT and Voicebank databases， the highest detection accuracy of the proposed algorithm can reach 100%， and the lowest false acceptance rate of the algorithm can reach 1.37%. In realistic scenes， the highest detection accuracy of this algorithm is up to 99.27% when detecting the audios recorded by three different recording devices with the background noise of the device and the audio of the original scene. Experimental results show that it is effective to use the CQCC features of audio to detect the scene replacement trace of audio.

In order to improve the accuracy of visibility forecast, especially the accuracy of low-visibility forecast, an ensemble learning model based on random forest and LightGBM for visibility forecast was proposed. Firstly, based on the meteorological forecast data of the numerical modeling system, combined with meteorological observation data and PM _2.5 concentration observation data, the random forest method was used to construct the feature vectors. Secondly, for the missing data with different time spans, three missing value processing methods were designed to replace the missing values, and then the data sample set with good continuity for training and testing was created. Finally, a visibility forecast model based on LightGBM was established, and its parameters were optimized by using the network search method. The proposed model was compared to Support Vector Machine(SVM), Multiple Linear Regression(MLR) and Artificial Neural Network(ANN) on performance. Experimental results show that for different levels of visibility, the proposed visibility forecast model based on LightGBM algorithm obtains the highest Threat Score(TS); when the visibility is less than 2 km, the average correlation coefficient between the visibility values of observation stations predicted by the model and the observation values of visibility of observation stations is 0.75, the average mean square error between them is 6.49. It can be seen that the forecast model based on LightGBM can effectively improve the accuracy of visibility forecast.

To effectively improve the automation level of legacy software system reconstruction based on the microservice architecture, according to the principle that there is a certain correlation between resource data operated by two classes with dependencies, a microservice identification method based on class dependencies under resource constraints was proposed. Firstly, the class dependency graph was built based on the class dependencies in the legacy software program, and the resource entity label for each class was set. Then, a dividing algorithm was designed for the class dependency graph based on the resource entity label, which was used to divide the original software system and obtain the candidate microservices. Finally, the candidate microservices with higher dependency degrees were combined to obtain the final microservice set. Experimental results based on four open source projects from GitHub demonstrate that, the proposed method achieves the microservice division accuracy of higher than 90%, which proves that it is reasonable and effective to identify microservices by considering both class dependencies and resource constraints.

To improve the accuracy of protein-ATP (Adenosine TriPhosphate) binding sites, an algorithm was proposed by using One Dimensional Convolutional Neural Network (1D-CNN). Firstly, based on the protein sequence information, position specific score matrix information, secondary structure information and water solubility information were combined and random under-sampling was used to eliminate the impact of data imbalance. Then, the missing features were completed by recoding. Finally, the training features were obtained. A 1D-CNN was trained to predict protein-ATP binding sites, the network structure was optimized, and experiments were carried out to compare the proposed method and other machine learning methods. Experimental results show that the proposed method is effective and can achieve better performance on AUC (Area Under Curve) compared to the traditional Support Vector Machine (SVM).

Focusing on the issue of extracting title and career attributes from unstructured text for specific person, an distant supervision and pattern matching based method was proposed. Features of personal attributes were described from two aspects of string pattern and dependency pattern. Title and career attributes were extracted by two stages. At first, both distant supervision and human annotated knowledge were used to build high coverage pattern base to discover and extract a candidate attribute set. Then the literal connections among multiple attributes and dependency relations between the specific person and candidate attributes were used to design a filtering rule set. Test on CLP-2014 PAE share task shows that the F-score of the proposed method reaches 55.37%, which is significantly higher than the best result of the evaluation ( F-measure 34.38%), and it also outperforms the method based on supervised Conditional Random Field (CRF) sequence tagging method with F-measure of 43.79%. The experimental results show that by carrying out a filter process, the proposed method can mine and extract title and career attributes from unstructured document with a high coverage rate.

To solve the problem of receiver buffer blocking and load unbalance of Concurrent Multipath data Transfer using Stream Control Transmission Protocol (CMT-SCTP) in heterogeneous network environments, an improved round-robin data scheduling algorithm was proposed. The network condition of each path was estimated by the proposed algorithm according to the sender queue information and the congestion status of links. Then the proposed data scheduling algorithm distributed the transmission task to each path based on its network condition, curtailed the queuing time of data chunks in sender buffer and reduced the number of out-of-order data chunks in receiver buffer. Simulation results show that the improved round-robin data scheduling algorithm can effectively enhance the transmission efficiency of CMT-SCTP in a heterogeneous wireless network environment and mitigate the receiver buffer blocking problem. It can also adapt to different network conditions.

In order to improve the operational efficiency of SemiDefinite Programming (SDP), a new nonmonotonic trust region algorithm was proposed. The SDP problem and its duality problem were transformed into unconstrained optimization problem and the trust region subproblem was constructed, the trust region radius correction condition was modified. When the initial search point was near the canyon, the global optimal solution still could be found. The experimental results show that the number of iterations of the algorithm is less than the classical interior point algorithm for small and medium scale semidefinite programming problems, and the proposed algorithm works faster.

Based on the analysis of the advantages and disadvantages of the Genetic Algorithm and Simulated Annealing Algorithm,a new Genetic Algorithm was proposed.The genetic algorithm with optimum reservation strategy was served as the main flow of the new algorithm which syncretized the mechanism of improved simulated annealing.In order to get the global optimum solution,the improved simulated annealing took the double threshold value and kept the middle optimum solution to reduce the computing capacity and enhanced the convergence speed.Through the simulation test of function,the result indicates that the new algorithm can improve the convergence speed and the ability of jumping out the local optimum solution greatly.