Since Practical Byzantine Fault Tolerance （PBFT） consensus algorithm applied to consortium blockchain has the problems of insufficient scalability and high communication overhead， an improved practical Byzantine fault tolerance consensus algorithm based on Raft algorithm named K-RPBFT （K-medoids Raft based Practical Byzantine Fault Tolerance） was proposed. Firstly， blockchain was sharded based on K-medoids clustering algorithm， all nodes were divided into multiple node clusters and each node cluster constituted to a single shard， so that global consensus was improved to hierarchical multi-center consensus. Secondly， the consus between the cluster central nodes of each shard was performed by adopting PBFT algorithm， and the improved Raft algorithm based on supervision nodes was used for intra-shard consensus. The supervision mechanism in each shard gave a certain ability of Byzantine fault tolerance to Raft algorithm and improved the security of the algorithm. Experimental analysis shows that compared with PBFT algorithm， K-RPBFT algorithm greatly reduces the communication overhead and consensus latency， improves the consensus efficiency and throughput while having Byzantine fault tolerance ability， and has good scalability and dynamics， so that the consortium blockchain can be applied to a wider range of fields.

Aiming at how to use the food safety standard reference network to find the key standards that have a great impact on food safety inspection and detection from many national food safety standards， a method of finding the important nodes in the food safety standard reference network based on multi-attribute comprehensive evaluation was proposed. Firstly， the importance of standard nodes were evaluated by using the degree centrality， closeness centrality and betweenness centrality in social network analysis as well as the Web page importance evaluation algorithm PageRank respectively. Secondly， the Analytic Hierarchy Process （AHP） was used to calculate the weight of each evaluation index in the importance evaluation， and multi-attribute decision-making method based on TOPSIS （Technique for Order Preference by Similarity to an Ideal Solution） was used to comprehensively evaluate the importance of standard nodes and found out the important nodes. Thirdly， the important nodes obtained from the comprehensive evaluation and the important nodes obtained from the degree based evaluation were deleted from their own reference network respectively， and the connectivity of the reference networks after deleting the important nodes was tested. The worse the connectivity was， the more important the nodes were. Finally， the Louvain community discovery algorithm was used to test the network connectivity， that is to find the communities of the network nodes. The more nodes not included in the communities， the worse the network connectivity. Experimental results show that after deleting the important nodes found by the comprehensive evaluation method based on multi-attribute， more nodes cannot be included in the communities than those of the evaluation method based on degree， proving that the proposed method can better find the important nodes in the reference network. The proposed method helps standard makers quickly grasp the core contents and key nodes when revising and updating standards， and plays a guiding role in the construction of the system of national food safety standards.

Considering the limitations of the feature extraction of high-density crowd images with perspective distortion, a crowd counting model, named LMCNN, that combines Global Feature Perception Network (GFPNet) and Local Association Feature Perception Network (LAFPNet) was proposed. GFPNet was the backbone network of LMCNN, its output feature map was serialized and used as the input of LAFPNet. And the characteristic that the Recurrent Neural Network (RNN) senses the local association features on the time-series dimension was used to map the single spatial static feature to the feature space with local sequence association features, thus effectively reducing the impact of perspective distortion on crowd density estimation. To verify the effectiveness of the proposed model, experiments were conducted on Shanghaitech Part A and UCF_CC_50 datasets. The results show that compared to Atrous Convolutions Spatial Pyramid Network (ACSPNet), the Mean Absolute Error (MAE) of LMCNN was decreased by 18.7% and 20.3% at least, respectively, and the Mean Square Error (MSE) was decreased by 22.3% and 22.6% at least, respectively. The focus of LMCNN is the association between the front and back features on the spatial dimension, and by fully integrating the spatial dimension features and the sequence features in a single image, the crowd counting error caused by perspective distortion is reduced, and the number of people in dense areas can be more accurately predicted, thereby improving the regression accuracy of crowd density.

Aiming at the problem that the existing neural network models have insufficient ability to characterize the features of classification objects in image classification tasks and cannot achieve high recognition accuracy, an image classification algorithm based on Lightweight Group-wise Attention Module (LGAM) was proposed. The proposed module reconstructed the feature maps from the channel and space of the input feature maps. Firstly, the input feature maps were grouped along the channel direction, and channel attention weight corresponding to each group was generated. At the same time, ladder type structure was used to solve the problem that the information between the groups was not circulated. Secondly, the global spatial attention weight was generated based on the new feature maps concatenated by each group, and the reconstructed feature maps were obtained by weighting the two attention weights. Finally, the reconstructed feature maps were merged with the input feature maps to generate the enhanced feature maps. Experiments were performed on the Cifar10 and Cifar100 datasets and part of the ImageNet2012 dataset with using the classification Top-1 error rate as the evaluation indicator to compare the ResNet, Wide-ResNet and ResNeXt enhanced by LGAM. Experimental results show that the Top-1 error rates of the neural network models enhanced by LGAM are 1 to 2 percentage points lower than those of the models before enhancing. LGAM can improve the feature characterization ability of existing neural network models, thus improving the recognition accuracy of image classification.

In consideration of the problems of low utilization rate of action information and insufficient attention of temporal information in video human action recognition, a human action recognition model based on tightly coupled spatiotemporal two-stream convolutional neural network was proposed. Firstly, two 2D convolutional neural networks were used to separately extract the spatial and temporal features in the video. Then, the forget gate module in the Long Short-Term Memory (LSTM) network was used to establish the feature-level tightly coupled connections between different sampled segments to achieve the transfer of information flow. After that, the Bi-directional Long Short-Term Memory (Bi-LSTM) network was used to evaluate the importance of each sampled segment and assign adaptive weight to it. Finally, the spatiotemporal two-stream features were combined to complete the human action recognition. The accuracy rates of this model on the datasets UCF101 and HMDB51 selected for the experiment and verification were 94.2% and 70.1% respectively. Experimental results show that the proposed model can effectively improve the utilization rate of temporal information and the ability of overall action representation, thus significantly improving the accuracy of human action recognition.

Facial action unit detection aims at making computers detect the action unit targets based on the given facial images or videos automatically. Due to a great amount of research during the past 20 years, especially the construction of more and more facial action unit databases and the raise of deep learning based methods, facial action unit detection technology has been rapidly developed. Firstly, the concept of facial action unit and commonly used facial action unit databases were introduced, and the traditional methods including steps such as pre-processing, feature extraction and classifier learning were summarized. Then, for several important research areas, such as region learning, facial action unit correlation learning and weak supervised learning, systematic review and analysis were conducted. Finally, the shortcomings of the existing reasearch and potential developing trends of facial action unit detection were discussed.

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.

Aiming at the problem of low information extraction rate of traditional methods and the unideal coloring effect in the grayscale image colorization field, a grayscale image colorization algorithm based on dense neural network was proposed to improve the colorization effect and make the information of image be better observed by human eyes. With making full use of the high information extraction efficiency of dense neural network, an end-to-end deep learning model was built and trained to extract multiple types of information and features in the image. During the training, the loss of the network output result (such as information loss and classification loss) was gradually reduced by comparing with the original image. After the training, with only a grayscale image input into the trained network, a full and vibrant vivid color image was able to be obtained. The experimental results show that the introduction of dense network can effectively alleviate the problems such as color leakage, loss of detail information and low contrast, during the colorization process. The coloring effect has achieved significant improvement compared with the current advanced coloring methods based on Visual Geometry Group (VGG)-net, U-Net, dual stream network structure, Residual Network (ResNet), etc.

Aiming at high energy consumption of data center in container cloud, a virtual resource deployment strategy based on host selection algorithm with Power Full (PF) was proposed. Firstly, the allocation and migration scheme of virtual resource in container cloud was proposed and the significant impact of host selection strategy on energy consumption of data center was found. Secondly, by studying the mathematical relationship between the utilization of host and the utilization of containers, between the utilization of host and the utilization of virtual machines and between the utilization of host and energy consumption of data center, a mathematical model of the energy consumption of data center in container cloud was constructed and an optimization objective function was defined. Finally, the function of host's energy consumption was simulated using linear interpolation method, and a host selection algorithm with PF was proposed according to the clustering property of the objects. Simulation results show that compared with First Fit (FF), Least Full (LF) and Most Full (MF), the energy consumption of the proposed algorithm is averagely reduced by 45%,53% and 49% respectively in the computing service of regular tasks and different host clusters; is averagely reduced by 56%,46% and 58% respectively in the computing service of regular tasks and same host cluster; is averagely reduced by 32%,24% and 12% respectively in the computing service of irregular tasks and different host clusters. The results indicate that the proposed algorithm realizes reasonable virtual resource deployment in container cloud, and has advantage in data center energy saving.

Aiming at the low recognition rate caused by low quality of face images in the process of face recognition, a face image quality evaluation model based on convolutional neural network was proposed. Firstly, an 8-layer convolutional neural network model was built to extract deep semantic information of face image quality. Secondly, face images were collected in unconstrained environment, and were filtered by traditional image processing method and manual selecting, then the dataset obtained was used to train the model parameters. Thirdly, by accelerating training on GPU (Graphics Processing Unit), the mapping relationship of fitted face images to categories was obtained. Finally, the input probability of high-quality image category was taken as the image quality score, and the face image quality scoring mechanism was established. Experimental results show that compared with VGG-16 network, the precision rate of the proposed model is reduced by 0.21 percentage points, but the scale of the parameters is reduced by 98%, which greatly improves the efficiency of the model. At the same time, the proposed model has strong discriminant ability in aspects such as face blur, illumination, posture and occlusion. Therefore, the proposed model can be applied to real-time face recognition system to improve the accuracy of the system without affecting the efficiency.

For the application of reversible watermarking technology in three-Dimensional (3D) medical images, a 3D medical image reversible watermarking algorithm based on unidirectional prediction error expansion was proposed. Firstly, the intermediate pixels were predicted according to the 3D gradient changes between them and their neighborhood pixels to obtain the prediction errors. Then, considering the features of the 3D medical image generated by magnetic resonance imaging, the external information was embedded into the 3D medical image by combining unidirectional histogram shifting with prediction error expansion. Finally, the pixels were re-predicted to extract the external information and restore the original 3D image. Experimental results on MR-head and MR-chest data show that compared with two-dimensional (2D) gradient-based prediction, the mean absolute deviation of prediction error produced by 3D gradient-based prediction are reduced by 1.09 and 1.40, respectively; and the maximal embedding capacity of each pixel is increased by 0.0456 and 0.1291 bits, respectively. The proposed algorithm can predict the pixels more accurately and embed more external information, so it is applicable to 3D medical image tempering detection and privacy protection for patients.

Aiming at the insufficiency of feature extraction in the existing Content-Based Medical Image Retrieval (CBMIR) algorithms, which resulted in imperfect semantic information representation and poor image retrieval performance, an algorithm based on multi-scale dense network was proposed. Firstly, the size of pulmonary nodule image was reduced from 512×512 to 64×64, and the dense block was added to solve the gap between the extracted low-level features and high-level semantic features. Secondly, as the information of pulmonary nodule images extracted by different layers in the network was varied, in order to improve the retrieval accuracy and efficiency, the multi-scale method was used to combine the global features of the image and the local features of the nodules, so as to generate the retrieval hash code. Finally, the experimental results show that compared with the Adaptive Bit Retrieval (ABR) algorithm, the average retrieval accuracy for pulmonary nodule images based on the proposed algorithm under 64-bit hash code length can reach 91.17%, which is increased by 3.5 percentage points; and the average time required to retrieve a lung slice is 48 μs. The retrieval results of the proposed algorithm are superior to other comparative network structures in expressing rich semantic features and retrieval efficiency of images. The proposed algorithm can contribute to doctor diagnosis and patient treament.

The large network transmission delay and high energy consumption in cloud computing as well as the limited computing resource in edge servers are the bottlenecks for the development of delay-sensitive Internet of Things (IoT) applications. In order to improve the Quality of Service (QoS) of IoT applications while achieving green computing for computing systems, an edge-cloud cooperation Drift-plus-Penalty-based Computation Offloading (DPCO) policy was proposed. Firstly, mathematical modeling was performed on the business model, the transmission delay as well as the computation delay of the computation job, the computation energy as well as the transmission energy generated by the system were modeled by constructing the IoT-Edge-Cloud model. Then, the system consumption and the job average delay were optimized, with the queueing stability of the edge servers as constraint condition, the edge-cloud cooperation computation offloading optimization model was built. After that, with the optimization targets as the penalty function, the drift-plus-penalty function properties of computation offloading optimization model were analyzed based on Liapunov stability theory. Finally, DPCO was proposed based on the above results, the long-term energy consumption per unit time and the average system delay were reduced by selecting the computation offloading policy of minimizing the present drift-plus-penalty function in every time slot. In comparison with Light Fog Processing (LFP), the benchmarked Edge Computing (EC) and Cloud Computing (CC) policies, DPCO consumes the lowest system energy, which is 2/3 of that of the CC policy; DPCO also provides the shortest average job delay, which is 1/5 of that of the CC policy. The experimental results show that DPCO can efficiently reduce the energy consumption of edge-cloud computing system, shorten the end-to-end delay of the computation job, and satisfy the QoS requirements of delay-sensitive IoT applications.

Aiming at the problem that the discontinuity of the pitch sequence of the same sound source was caused by the interference of different sound sources in polyphonic music which reduced the accuracy of pitch estimation, an improved pitch contour creation and selection algorithm for melody extraction was proposed. Firstly, a method based on auditory streaming cues and the continuity of pitch salience was proposed to create pitch contour by calculating the pitch salience of each point in the time-frequency spectrum. In order to further select the melody pitch contour, the non-melodic pitch contours were removed according to the repetitive characteristics of the accompaniment, and dynamic time warping algorithm was used to calculate the similarity between the melodic and non-melodic pitch contours. Finally, the octave errors in the melodic pitch contours was detected based on the long term relationship of the adjacent pitch contours. Simulation experiments on the data set ORCHSET show that the pitch estimation accuracy and the overall accuracy of the proposed algorithm are improved by 2.86% and 3.32% respectively compared with the oringinal algorithm, which can effectively solve the pitch estimation problem.

Aiming at the problem of field segmentation in the reverse analysis of binary protocol message format, a novel algorithm with format keywords as the reverse analysis target was proposed, which can optimally determine the boundaries of binary protocol format keywords by improved n-gram algorithm and optimal path search algorithm. Firstly, by introducing the position factor into n-gram algorithm, a boundary extraction algorithm of format keywords was proposed based on the iterative n-gram-position algorithm, which effectively solved the problems that the n value was difficult to determine and the candidate boundary extraction of format keywords with fixed offset position in the n-gram algorithm. Then, the branch metric was defined based on the hit ratio of frequent item boundaries and the left and right branch information entropies, and the constraint conditions were constructed based on the difference of n-gram-position value change rate between keywords and non-keywords. The boundary selection algorithm of format keywords based on the optimal path search was proposed to determine the joint optimal bound for format keywords. The experimental results of testing on five different types of protocol message datasets such as AIS1, AIS18, ICMP00, ICMP03 and NetBios show that, the proposed algorithm can accurately determine the boundaries of different protocol format keywords, its F values are all above 83%. Compared with the classical algorithms of Variance of the Distribution of Variances (VDV) and AutoReEngine, the F value of the proposed algorithm is increased averagely by about 8 percentage points.

Extrapolation technique of weather radar echo possesses a widely application prospects in short-term nowcast. The traditional methods of radar echo extrapolation are difficult to obtain long limitation period and have low utilization rate of radar data. This problem is researched from deep learning perspective in this paper, and a new model named Dynamic Convolutional Neural Network based on Input (DCNN-I) was proposed. According to the strong correlation between weather radar echo images at adjacent times, dynamic sub-network and probability prediction layer were added, and a function was created that maped the convolution kernels to the input, through which the convolution kernels could be updated based on the input weather radar echo images during the testing. In the experiments of radar data from Nanjing, Hangzhuo and Xiamen, this method achieved higher accuracy of prediction images compared with traditional methods, and extended the limitation period of exploration effectively.

It is difficult to diagnose the faults of large-scale digital-analog hybrid circuit because it has numerous fault modes, the circuit failure status is complex and can be propagated easily. To solve these problems, a new failure diagnosis method, namely Modularized Back Propagation (BP) neural network based on Fault Propagation (MBPFP), was proposed. Firstly, fault propagation between subcircuits was analyzed on the basis of circuit module division, and failure source and transmission source were modularized. Secondly, the set of fault causes was narrowed and the fault module was determined by the anomaly detection model of subcircuit in 1-order positioning. Finally, the fault location was realized and the fault mode was identified by the BP neural network of target module in 2-order positioning. The experimental results show that compared with the traditional BP neural network method, the proposed MBPFP method has a high fault coverage and the accuracy is improved by at least 8 percentage points, which is outperforms the traditional method based on BP neural network.

Aiming at preserving the privacy of Personal Health Record (PHR) in Smart health (S-health), an attribute-based access control scheme with verifiable outsourced decryption and delegation was proposed. Firstly, the Ciphertext-Policy Attribute-Based Encryption (CP-ABE) was used to realize fine-grained access control of PHR. Secondly, the most complicated decryption was outsourced to the cloud server, and the authorized agency was used to verify the correctness of Partial Decryption Ciphertext (PDC) returned by the cloud server. Then, based on the delegation method, the outsourcing decryption and authentication could be delegated to third-party users without revealing privacy by restricted users. Finally, the adaptive security of the proposed scheme was proved under the standard model. The theoretical analysis results show that the decryption of user side only needs to perform one exponential operation, so that the proposed scheme has strong security and practicability.

With the improvement of standardization and intelligence level of secondary equipment, a kind of communication network more efficient and smarter is needed in smart substation to meet the substation operation and maintenance requirements, to achieve equipment plug and play, intelligent monitoring, subnet secure isolation and element interchange. For the application needs of substation network unified management, security isolation between subnets and equipment compatibility and interchangeability, a Software Defined Network (SDN)-based substation network architecture was proposed. IEC 61850 and OpenFlow protocols were used for network architecture design. OpenFlow controller was used to control and isolate the individual subnets to implement network device management and subnet secure isolation. The experimental results show that precise traffic control based on service types, and securely data isolation can be implemented with the proposed substation SDN-based network architecture. It has a very important application value for promoting the operation and maintenance level of smart substation.

Focusing on the shortcoming of low storage efficiency and high recovery cost after copy failure of the current Hadoop, Hopfield Neural Network (HNN) was used to improve the overall performance. Firstly, the resource characteristics that affect the storage efficiency were analyzed. Secondly, the resource constraint model was established, the Hopfield energy function was designed and simplified. Finally, the average utilization rate of 8 nodes was analyzed by using the standard test case Wordcount, and the performance and resource utilization of the proposed strategy were compared with three typical algorithms including dynamic resource allocation algorithm, energy-efficient algorithm and Hadoop default storage strategy, and the comparison results showed that the average efficiency of the storage strategy based on HNN was promoted by 15.63%, 32.92% and 55.92% respectively. The results indicate that the proposed algorithm can realize the resource load balancing, help to improve the storage capacity of Hadoop, and speed up the retrieval.

Concerning the problem that the existing schemes of provable data possession are inefficient and can not support full dynamic update, a novel dynamic provable data possession scheme based on B ⁺ tree was proposed. Bilinear pairing techniques and data version table were introduced to support fine-grained dynamic operations at the block level and to protect user's data privacy in the proposed scheme. The third party auditor could identify the wrong data and locate it accurately by optimizing the system model and designing the retrieved value of data node. In comparison with the scheme based on the Merkel Hash Tree (MHT), theoretical analysis and experimental results show that the proposed scheme can significantly reduce the cost of constructing the authentication data structure, simplify the dynamic update process, and improve the verification efficiency of the third party auditor.

Concerning the problem that the Hidden Markov Model (HMM) parameters are difficult to configure, an improved method of situation assessment based on HMM was proposed to reflect the security of the network. The proposed method used the output of intrusion detection system as input, classified the alarm events by Snort manual to get the observation sequence, and established the HMM model, the improved Simulated Annealing (SA) algorithm combined with the Baum_Welch (BW) algorithm to optimize the HMM parameters, and used the method of quantitative analysis to get the security situational value of the network. The experimental results show that the proposed method can improve the accuracy and convergence speed of the model.

To deal with the discrete series protocol message without session information, a new Separate Protocol Message based Format Signature Construction (SPMbFSC) algorithm was proposed. First, separate protocol message was clustered, then the keywords of the protocol were extracted by improved frequent pattern mining algorithm. At last, the format signature was acquired by filtering and choosing the keywords. Simulation results show that SPMbFSC is quite accurate and reliable, the recognition rate of SPMbFSC for six protocols (DNS, FTP, HTTP, IMAP, POP3 and IMAP) achieves above 95% when using single message as identification unit, and the recognition rate achieves above 90% when using session as identification unit. SPMbFSC has better performance than Adaptive Application Signature (AdapSig) extraction algorithm under the same experimental conditions. Experimental results indicate that the proposed SPMbFSC does not depend on the integrity of session data, and it is more suitable for processing incomplete discrete seriesprotocol message due to the reception limitation.

Aiming at the problems of complex retinal image processing, poor generalization and lack of complete automatic recognition system, a complete retinal image automatic recognition system based on deep neural network was proposed. Firstly, the image was denoised, normalized, and data preprocessed. Then, a compact neural network model named CompactNet was designed. The structure parameters of CompactNet were inherited from AlexNet. The deep network parameters were adjusted adaptively based on the training data. Finally, the performance experiments were conducted on different training methods and various network structures. The experimental results demonstrate that the fine-tuning method of CompactNet is better than the traditional network training method, the classification index can reach 0.87, 0.27 higher than the traditional direct training. By comparing LeNet, AlexNet and CompactNet, CompactNet network model has the highest classification accuracy, and the necessity of preprocessing methods such as data amplification is confirmed by experiments.

Aiming at the problem that the network lifetime was reduced because of the high energy consumption of the nodes covered by multiple radiation sources in large scale Wireless Sensor Network (WSN), a new clustering algorithm based on Evolutionary Game Theory (EGT) was proposed. The non-cooperative game theory model was established by mapping the search space of the optimal node sets to the strategy space of the game and using the utility function of the game as objective function respectively; then the optimization objective was achieved by using Nash equilibrium analysis and the perturb-recover process of equilibrium states. Furthermore, a detailed clustering algorithm was presented to group the optimal node sets into clusters for further location. The proposed algorithm was compared with the nearest-neighbor algorithm and the clustering algorithm based on Discrete Particle Swarm Optimization (DPSO) algorithm in the location accuracy and the network lifetime under the RSSI (Received Signal Strength Indication)/TDOA (Time Difference of Arrival) two rounds cooperative location scheme. Simulation results show that the proposed algorithm decreases the energy consumption of the nodes covered by multiple radiation sources, prolongs the network lifetime and guarantees the precise location.

Concerning the poor robustness and low hiding strength of existing file hiding method based on Universal Serial Bus (USB), a new file hiding method based on capacity disguised and double file system was proposed. By analyzing the characteristics and management mechanism of Nand flash chips, the capacity disguise was achieved to deceive the host by tampering equipment capacity value in Command Status Wrap (CSW). Based on the memory management mechanism of the Flash Translation Layer (FTL), the storage area was divided into two parts including the hiding area and the common area by different marks, and a double file system was established using format function. Request for switching file system was sent by writing specific data, then it was achieved after user authentication to realize secure access to hiding areas. The experimental results and theoretical analysis show that the proposed method can achieve hiding file which is transparent to operating system, moreover, it is not affected by device operation and has better robustness and stronger hiding effect with respect to the methods based on hooking Application Programming Interface (API), modifying File Allocation Table (FAT) or encryption.

Cloud task scheduling is a hot issue in the research of cloud computing. The cloud task scheduling method directly affects the overall performance of the cloud platform. A task scheduling method Template-Based Genetic Algorithm (TBGA) was proposed. Firstly, according to the processor's CPU speed, bandwidth and etc., the amount of tasks that should be allocated to each processor was calculated. andwas called allocation template. Secondly, according to the template, the tasks were combined into multiple subsets and finally each subset of tasks was allocated to the corresponding processor by using genetic algorithm. Experimental results show that the method can obtain shorter time scheduling for total tasks. TBGA reduced 20% of task set completion time compared with Min-Min algorithm and 30% of task set completion time compared with Genetic Algorithm (GA). Therefore, the TBGA is an effective task scheduling algorithm.

The existing methods for monitoring clipboard operations cannot defend kernel-level attacks and satisfy the practical needs due to the simple protection strategy. In order to mitigate these disadvantages, a clipboard operations monitoring technique for document contents based on Virtual Machine Monitor (VMM) was proposed, as well as a classification protection strategy for electronic documents based on clipboard operations monitoring. Firstly, system calls were intercepted and identified in VMM by modifying the shadow registers. Secondly, a mapping table between process identifier and document path was created by monitoring the document open operations, then the document path could be obtained by process identifier when the clipboard operations were intercepted. Finally, clipboard operations were filtered according to classification protection strategy. The experimental results show that the performance loss to Guest OS file system caused by the monitoring system decreases with the increase of the record size; when the record size reaches more than 64 KB, the performance loss is within 10%, which has little effect on the user.

In order to solve the problem of fixed target size in Kernel Correlation Filtering (KCF) tracker, a scale adaptive tracking method was proposed. Firstly, the Lucas-Kanade optical flow method was used to track the movement of keypoints in the neighbor frames, and the reliable points were obtained by introducing the forward-backward method. Secondly, the reliable points were used to estimate the target changing in scale. Thirdly, the scale estimation was applied to the adjustable Gaussian window. Finally, the forward-backward tracking method was used to determine whether the target was occluded or not, the template updating strategy was revised. The fixed target size limitation in the KCF was solved, the tracker was more accurate and robust. The object tracking datasets were used to test the algorithm. The experimental results show that the proposed method ranks over the original KCF, Tracking-Learning-Detection (TLD), Structured output tracking with kernel (Struck) algorithms both in success plot and precision plot. Compared with the original method, the proposed tracker can be better applied in target tracking with scale variation and occlusion.

Concerning the problem that the existing Voice Activity Detection (VAD) algorithms based on Hidden Markov Model (HMM) were poor to track noise, a method using Baum-Welch algorithm was proposed to train the noise with different characteristics, and the corresponding noise model was generated to establish a library. When voice activity was detected, depending on the measured background noise of the speech, the voice was dynamically matched to a noise model in the library. Meanwhile, in order to meet real-time requirements of speech signal processing, reduce the complexity of the speech parameter extraction, the threshold was improved to ensure the inter-frame correlation of the speech signal. Under different noise environments, the improved algorithm performance was tested and compared with Adaptive Multi-Rate (AMR), G.729B of the International Telecommunications Union (ITU-T). The test results show that the improved algorithm can effectively improve the accuracy of detection and noise tracking ability in real-time voice signal processing.