In order to solve the problems of high computing cost and over-fitting of the model caused by complicated network structure in pulmonary nodule detection method, an improved residual network structure combining deep separable convolution and pre-activation was proposed. And the proposed network structure was applied to a pulmonary nodule detection model. Based on the target detection network Faster R-CNN, with U-Net coder-decoder structure adopted, the deep separable convolution and pre-activation operations were used by the model to improve the 3D residual network structure. Firstly, with the use of deep separable convolution, the complexity and computing cost of the model were reduced. Then, the regularization of the model was improved by introducing the pre-activation operation, and the phenomenon of overfitting was alleviated. Finally, the rectangular convolution kernel was used to expand the receptive field of the convolution operation on the premise that the computing cost of the model was slightly increased, so as to effectively take into account both the global and local characteristics of the pulmonary nodules. On the LUNA16 dataset, the proposed method has the sensitivity of 96.04%, and the Free-response area under the Receiver Operating Characteristic curve (FROC) score of 83.23%. The experimental results show that the method improves the sensitivity of pulmonary nodule detection, effectively reduces the average number of false positives in the detection results, and improves the detection efficiency. This proposed method can effectively assist radiologists in detecting pulmonary nodules.

At present, the face recognition methods based on deep learning have the problems of large model parameter size and slow feature extraction speed, and the existing face datasets have the problem of single pose, which cannot achieve good recognition effect in the actual face recognition task. Aiming at this problem, a multi-pose face dataset was established, and a lightweight multi-pose face recognition method was proposed. Firstly, the MTCNN (Multi-Task cascaded Convolutional Neural Network) algorithm was used by the method for face detection, and the high-level features included in the last network of MTCNN were used for face tracking. Then, the face pose was judged according to the positions of the detected face key points, the current face features were extracted by the neural network with ArcFace as loss function, and the current face features were compared with the face features of the corresponding pose in the face database to obtain the face recognition result. The experimental results show that the accuracy of the proposed method is 96.25% on the multi-pose face dataset, which is 2.67% higher than that on the face dataset with single pose. It shows that the proposed multi-pose face recognition method can effectively improve the recognition accuracy.

In recent years, Software Supply Chain (SSC) security issues have frequently occurred, which has brought great challenges to software security research. Since there are millions of new software released every day, it is essential to detect the pollution of SSC automatically. The problem of SSC pollution was first analyzed and discussed. Then focusing on the requirements of pollution detection in the downstream of SSC, the automatic program reverse analysis methods and their applications in the SSC pollution detection was introduced. Finally, the shortcomings and challenges faced by the existing technologies in solving the problem of SSC pollution was summarized and analyzed, and some researches worth studying to overcome these challenges were pointed out.

Since Practical Byzantine Fault Tolerance (PBFT) consensus algorithm applied to the alliance chain has the problems of static network structure, random selection of master node and large communication overhead, an Evolution of Practical Byzantine Fault Tolerance (EPBFT) consensus algorithm was proposed. Firstly, a series of activity states were set for consensus nodes, making the nodes have complete life cycle in the system through state transition, so that the nodes were able to dynamically join and exit while the system has a dynamic network structure. Secondly, the selection method of master node of PBFT was improved with adding the election process of master node with the longest chain as the election principle. After the election of master node, the reliability of master node was further ensured through data synchronization and master node verification process. Finally, the consensus process of PBFT algorithm was optimized to improve the consensus efficiency, thus the communication overhead of EPBFT algorithm was reduced to 1/2 of that of PBFT algorithm with little view changes. The experimental results show that EPBFT algorithm has good effectiveness and practicability.

The exponential growth in the number of wireless mobile devices leads that heterogeneous cooperative Small Base Stations (SBS) carry large-scale traffic load. Aiming at this problem, an Online-hot Video Cache Replacement Policy (OVCRP) based on cooperative SBS and popularity prediction was proposed. Firstly, the changes of popularity in short term of online-hot videos were analyzed, then a k-nearest neighbor model was constructed to predict the popularities of the online-hot videos, and finally the locations for cache replacement of online-hot videos were determined. In order to select appropriate locations to cache the online-hot videos, with minimization of overall transmission delay as the goal, a mathematical model was built and an integer programming optimization algorithm was designed. The simulation experiment results show that compared with the schemes such as RANDOM cache (RANDOM), Least Recently Used (LRU) and Least Frequently Used (LFU), the proposed OVCRP has obvious advantages in average cache hit rate and average access delay, reducing the network burden of cooperative SBS.

Focusing on the issues in review helpfulness prediction methods that training datasets are difficult to construct in supervised models and unsupervised methods do not take sentiment information in to account, an unsupervised model combining semantics and sentiment information was proposed. Firstly, opinion helpfulness score was calculated based on opinion support score of reviews and replies, and then review helpfulness score was calculated. In addition, a review summary method combining syntactic analysis and improved Latent Dirichlet Allocation (LDA) model was proposed to extract opinions for review helpfulness prediction, and two kinds of constraint conditions named must-link and cannot-link were constructed to guide topic learning based on the result of syntactic analysis, which can improve the accuracy of the model with ensuring the recall rate. The F1 value of the proposed model is 70% and the sorting accuracy is nearly 90% in the experimental data set, and the instance also shows that the proposed model has good explanatory ability.

With the popularization of cloud computing technology, many enterprises have migrated or are planning to migrate their business and applications to the cloud. But it may face the problems of application performance degradation, and the key business and applications may suffer security threats. Therefore, migrating to cloud or deploying in independent server is a problem that needs to be further studied. In this paper, based on the Tsinghua cloud platform, Tsinghua cloud monitoring platform was set up based on Nagios. Firstly, Tsinghua cloud platform and its architecture were introduced, and then Nagios and the architecture of Tsinghua cloud monitoring platform were discussed. For cloud migration performance evaluation, Ubuntu and Windows were used as operating system platforms, CPU load and memory usage were used as evaluation indexes, two applications of CPU computing type and server load type respectively ran on the cloud server and the independent server. At last, the experimental results were analyzed and compared. The experimental result shows that some applications have better performance on independent servers that may not be suitable for migrating to cloud platform.

In order to improve the accuracy of data decision making, an optimization approach was proposed for the algorithm of multi-objectives group decision making. By the interval-valued intuitionistic fuzzy set theory, the optimization was approached by the method of iterative computation gradually in the situation that the part weight information was incomplete usually. Results of the simulation indicate that the algorithm has low time complexity, and can be implemented in the computer easily; moreover, it also shows the effectiveness and accuracy of the algorithm.

Most of the current approaches to evaluate the degree of image scrambling depend on original images. And there are no scientific mathematical models as their theoretic basis. A linear model for difference statistic distribution of ideal scrambled image was put forward in this paper by analyzing the difference statistic distribution of scrambled image. Furthermore，three methods were presented based on this model to evaluate image scrambling degree. The first one was the absolute difference of slope, the second was the absolute difference of difference, and the third was method of overlapping area. The experimental results indicate that these methods are very sensitive to the statistical distribution of image difference, and they are independent of original image with good agreement with human vision system, so they can achieve blind evaluation for image scrambling degree objectively.

To deal with the problems of low accuracy and local convergence in conventional Particle Swarm Optimization (PSO) algorithm, the chaos algorithm and cloud model algorithm were introduced into the evolutionary process of PSO algorithm and the chaos cloud model particle swarm optimization (CCMPSO) algorithm was proposed. The particles were divided into excellent particles and normal particles when CCMPSO was in convergent status. To search the global optimum location, the cloud model algorithm as well as excellent particles was applied to local refinement in convergent area, meanwhile chaos algorithm and normal particles were used to global optimization in the outside space of convergent area. The convergence of CCMPSO was analyzed by eigenvalue method. The simulation results prove the CCMPSO has better optimization performance than other main PSO algorithms.

Independent Component Analysis (ICA) is a method for blind source separation based on higher-order statistics. It is hard to deal with the signal in the environment of Gaussian noise, because the higher-order cumulant of Gaussian signal is zero. A noisy image separation algorithm based on Curvelet threshold de-noising processing and FastICA was proposed. The results of simulation in Gaussian noise show that it can solve the problem of performance deterioration of ICA algorithms while processing noisy mixtures. Curvelet transform used in noisy images separation can improve the quality of Signal-to Noise Ratio (SNR) and the performance of separation compared with ICA that has been de-noised by wavelet.