Aiming at the problem of insufficient representation ability of features extracted by the existing vehicle re-identification methods based on convolution Neural Network （CNN）， a vehicle re-identification method based on the combination of wavelet features and attention mechanism was proposed. Firstly， the single-layer wavelet module was embedded in the convolution module to replace the pooling layer for subsampling， thereby reducing the loss of fine-grained features. Secondly， a new local attention module named Feature Extraction Module （FEM） was put forward by combining Channel Attention （CA） mechanism and Pixel Attention （PA） mechanism， which was embedded into CNN to weight and strengthen the key information. Comparison experiments with the benchmark residual convolutional network ResNet-50 and ResNet-101 were conducted on VeRi dataset. Experimental results show that increasing the number of wavelet decomposition layers in ResNet-50 can improve mean Average Precision （mAP）. In the ablation experiment， although ResNet-50+Discrete Wavelet Transform （DWT） has the mAP reduced by 0.25 percentage points compared with ResNet-101， it has the number of parameters and computational complexity lower than those of ResNet-101， and has the mAP， Rank-1 and Rank-5 higher than those of ResNet-50 without DWT， verifying that the proposed model can effectively improve the accuracy of vehicle retrieval in vehicle re-identification.

To find the optimal deployment of allocating the maximum number of virtual Field Programmable Gate Array (vFPGA) in the minimum number of Field Programmable Gate Array (FPGA) in reconfigurable cryptographic resource pool, the traditional Ant Colony Optimization (ACO) algorithm was optimized, and a vFPGA deployment strategy based on optimized ACO algorithm with considering FPGAs’ characteristics and actual requirements was proposed. Firstly, the load balancing among FPGAs was achieved by giving ants the ability of perceiving resource status, at the same time, the frequent migration of vFPGAs was avoided. Secondly, the free space was designed to effectively reduce the Service Level Agreement (SLA) conflicts caused by dynamical demand change of tenants. Finally, CloudSim toolkit was extended to evaluate the performance of the proposed strategy through simulations on synthetic workflows. Simulation results show that the proposed strategy can reduce the usage number of FPGAs by improving the resource utilization under the promise of guaranteeing the system service quality.

Aiming at the integrity threat of Android systems at present brought by kernel-level attacks, a method for dynamic measurement of Android kernel, namely DIMDroid (Dynamic Integrity Measurement of Android), was proposed. The hardware-assisted virtualization technology was used to provide the isolation between the measurement module and the measured Android system. First of all, the static and dynamic measurement objects were obtained by analyzing the kernel elements that affect kernel integrity in the running of the Android system. Secondly, these measurement objects were semantically reconstructed at the measurement layer. Finally, an integrity analysis was performed to determine whether the Android kernel is under attack or not. At the same time, the boot protection based on hardware-based trust chain and the runtime protection based on memory isolation were performed to ensure the security of DIMDroid itself. The experimental results show that DIMDroid can detect the rootkit which breaks Android kernel integrity in time, and the performance loss of the method is within an acceptable range.

Aiming at the problem of cryptographic performance being affected by the excessive interrupt transmission cost of the cipher device in virtual environment, an interrupt path optimization method for virtual cryptographic device with Reducing Context Switching (RCS) was proposed. Firstly, a host to Virtual Cipher Machine (VCM) relationship mapping table was established in the kernel of the virtual machine. Then, the types of the interrupt requests that the host transmits to the VCM were judged by the relational mapping table, and the unassigned types in VCM were registered. Finally, the interrupts were handled by the VCM interrupt handler directly. In the process, the system context switching overhead was reduced due to the host intervening and the cryptographic performance was improved. The speed at which the VCM executes the encryption was selected as a performance reference in the experiment. The results show that the speed of VCM using Advanced Encryption Standard (AES) algorithm is increased by 16.35% and that using Secure Hash Algorithm (SHA256) is increased by 12.25%.

The traditional cross domain authentication schemes are few and complex. In order to solve the problems, a new biometric and password two-factor cross domain authentication scheme based on blockchain technology was proposed. Firstly, the fuzzy extraction technology was used to extract the random key of biometrics for participation authentication, and the problem of permanent unavailability caused by the biometric leakage was solved. Secondly, the untampered blockchain was used to store the public information of biometrics, and the threat of being vulnerable to active attacks for the fuzzy extraction technology was solved. Finally, based on the distributed storage function and consortium blockchain architecture of blockchain, the two-factor cross domain authentication of user in local and remote environment was realized. The results of security analysis and efficiency analysis show that, in terms of security, the proposed scheme has the security properties of anti-man-in-the-middle attack and anti-replay attack; in terms of efficiency and feasibility, the efficiency of the proposed scheme is moderate, users do not need to carry smart cards, and the expandability of system is strong.

To balance load in cryptography cloud systems, a Virtual cipher machine Scheduling Method based on Entropy Weight Evaluation (VSMEWE) was proposed. In order to improve the quality of cryptography service and economize resources of cryptography cloud effectively, a virtual cipher machine migration selection solution was presented, according to the comparison results of comprehensive evaluation values of cloud cipher machine. To achieve the best comprehensive evaluation values, it evaluated the resource states of cloud cipher machine with the main indexes including the utilizations of resources, such as CPU, memory, network bandwidth and throughput bandwidth of cipher card. Finally, a migration selection scheme of virtual cipher machine was decided by the scheduling method. Compared with Entropy algorithm and Baseline algorithm, the experimental results show that the proposed algorithm has characteristics of wholeness and chronergy, the effect of load balancing is improved, and the execution efficiency is increased by 6.8% and 22.7% respectively.

Since the current cloud task scheduling algorithm in the cryptography cloud environment cannot achieve the target that tasks are processed in real-time, a real-time threshold scheduling method based on rolling optimization window was proposed. Firstly, a cryptography cloud service architecture was given by integrating the link of key calling into the process of cryptographic task; secondly, to realize real-time scheduling, a cryptographic task scheduler model based on the rolling window and a throughput analysis model which was used to obtain the real-time throughput data were established; finally, to meet the objective needs of high-speed cryptographic service for cloud tenants, a throughput threshold scheduling algorithm was proposed, which migrates virtual cipher machine in real-time according to the changes of real-time throughput relative to throughput threshold. The simulation results show that compared with the method without the rolling optimization window or virtual machine migration technology, the proposed method has characteristics of shorter task completion time and lower CPU utility, meanwhile the real-time throughput of it can be continuously kept in 70%-85% of the network bandwidth, thus verifying its effectiveness and real-time performance in the cryptography cloud environment.

The "consumption first and replenishment afterward" operation model of the power supply companies may cause the risk of arrears due to poor credit of some power consumers. Therefore, it is necessary to analyze of the tremendous user data in real-time and quickly before the arrears' happening and provide a list of the potential customers in arrear. In order to solve the problem, a method for arrears alert of power consumers based on the parallel classification algorithm was proposed. Firstly, the arrear behaviors were modeled by the parallel Random Forest (RF) classification algorithm based on the Spark framework. Secondly, based on previous consumption behaviors and payment records, the future characteristics of consumption and payment behavior were predicted by time series. Finally, the list of the potential hig-risk customers in arrear was obtained by using the obtained model for classifying users. The proposed algorithm was compared with the parallel Support Vector Machine (SVM) algorithm and Online Sequential Extreme Learning Machine (OSELM) algorithm. The experimental results demonstrate that, the prediction accuracy of the proposed algorithm performs better than the other algorithms in comparison. Therefore, the proposed method is a convenient way for electricity recycling management to remind the customers of paying the electricity bills ahead of time, which can ensure timeliness electricity recovery. Moreover, the proposed method is also beneficial for consumer arrear risk management of the power supply companies.

Focusing on the low accuracy and long detection time of arc detection in engineering drawing vectorization, a fast arc detection algorithm based on tangent lines matching was proposed. Firstly, tangent lines on the circle outer boundary were detected from eight directions (0, π/4, π/2, …, 7π/4) and were added in tangent lines set. Secondly, the tangent lines in the set were paired up, and the center and radius of circles were estimated to obtain circle candidate set. Finally, tracing detection was performed for every candidate circle after merging data of circle candidate set, and every candidate circle was ascertained as a circle or an arc. The paring process was executed during the tangent lines searching, and the number of pairing was effectively reduced by removing the relative tangent lines of the identified candidate circle. In the contrast experiments with RANdom SAmple Consensus (RANSAC) algorithm and Effective Voting Method (EVM), the proposed method reached average detection accuracy of 97.250%, and the average detection time was 12.290 s, which were better than those of the comparison methods. The experimental results illustrate that the proposed method can effectively detect the arc which length is greater than 1/8 circumference in low noise image, improve the accuracy of detection and shorten the detection time.