Concerning the problem of low accuracy of human activity recognition, a recognition method combining Support Vector Machine (SVM) with context-awareness (actual logic or statistical model of human motion state transition) was proposed to identify six types of human activities (walking, going upstairs, going downstairs, sitting, standing, lying). Logical relationships existing between human activity samples were used by the method. Firstly, the SVM model was optimized by using the Improved Particle Swarm Optimization (IPSO) algorithm. Then, the optimized SVM was used to classify the human activities. Finally, the context-awareness was used to correct the error recognition results. Experimental results show that the classification accuracy of the proposed method reaches 94.2% on the Human Activity Recognition Using Smartphones (HARUS) dataset of University of California， Irvine (UCI), which is higher than that of traditional classification method based on pattern recognition.

In recent years, significant progress has been made in human interaction recognition based on RGB video sequences. Due to its lack of depth information, it cannot obtain accurate recognition results for complex interactions. The depth sensors (such as Microsoft Kinect) can effectively improve the tracking accuracy of the joint points of the whole body and obtain three-dimensional data that can accurately track the movement and changes of the human body. According to the respective characteristics of RGB and joint point data, a convolutional neural network structure model based on RGB and joint point data dual-stream information fusion was proposed. Firstly, the region of interest of the RGB video in the time domain was obtained by using the Vibe algorithm, and the key frames were extracted and mapped to the RGB space to obtain the spatial-temporal map representing the video information. The map was sent to the convolutional neural network to extract features. Then, a vector was constructed in each frame of the joint point sequence to extract the Cosine Distance (CD) and Normalized Magnitude (NM) features. The cosine distance and the characteristics of the joint nodes in each frame were connected in time order of the joint point sequence, and were fed into the convolutional neural network to learn more advanced temporal features. Finally, the softmax recognition probability matrixes of the two information sources were fused to obtain the final recognition result. The experimental results show that combining RGB video information with joint point information can effectively improve the recognition result of human interaction behavior, and achieves 92.55% and 80.09% recognition rate on the international public SBU Kinect interaction database and NTU RGB+D database respectively, verifying the effectiveness of the proposed model for the identification of interaction behaviour between two people.

Traditional network operation and maintenance evaluation method has two problems. First, it is too dependent on domain experts' experience in indicator selection and weight assignment, so that it is difficult to obtain accurate and comprehensive assessment results. Second, the network operation and maintenance quality involves data from multiple manufacturers or multiple devices in different formats and types, and a surge of users brings huge amounts of data. To solve the problems mentioned above, an indicator selection method based on correlation was proposed. The method focuses on the steps of indicator selection in the process of evaluation. By comparing the strength of the correlation between the data series of indicators, the original indicators could be classified into different clusters, and then the key indicators in each cluster could be selected to construct a key indicators system. The data processing methods and weight determination methods without human participation were also utilized into the network operation and maintenance quality evaluation model. In the experiments, the indicators selected by the proposed method cover 72.2% of the artificial indicators. The information overlap rate is 31% less than the manual indicators'. The proposed method can effectively reduce human involvement, and has a higher prediction accuracy for the alarm.

Aiming at the problems of mismatching and too large matching distance because of curves scaling, shifting, rotation and non-uniform sampling in the process of online signature verification, a curve segment similarity matching method was proposed. In the progress of online signature verification, two curves were partitioned into segments and matched coarsely at first. A dynamic programming algorithm based on cumulative difference matrix of windows was introduced to get the matching relationship. Then, the similarity distance for each matching pair and weighted sum of all the matching pairs were calculated, and the calculating method is to fit each curve of matching pairs, carry out the similarity transformation within a certain range, and resample the curves to get the Euclidean distance. Finally, the average of the similarity distance between test signature and all template signatures was used as the authentication distance, which was compared with the training threshold to judge the authenticity. The method was validated on the open databases SUSIG Visual and SUSIG Blind respectively with 3.56% and 2.44% Equal Error Rate (EER) when using personalized threshold, and the EER was reduced by about 14.4% on Blind data set compared with the traditional Dynamic Time Wraping (DTW) method. The experimental results show that the proposed method has certain advantages in skilled forgery signature and random forgery signature verification.

Cloud computing data are vulnerable to be theft illegally and tampered maliciously. To solve these problems, a Dynamic Updating Ciphertext-Policy Attribute-Based Encryption (DU-CPABE) scheme which enables both data dynamic updating and security protection was proposed. Firstly, by using linear partitioning algorithm, data information was divided into fixed size blocks. Secondly, the data blocks were encrypted by using Ciphertext-Policy Attribute-Based Encryption (CP-ABE) algorithm. Finally, based on conventional Merkle Hash Tree (MHT), an Address-MHT (A-MHT) was proposed for the operation of dynamically updating data in cloud computing. The theoretical analysis proved the security of the scheme, and the simulation in ideal channel showed that, for five updates, compared with CP-ABE method, the average time overhead of data update was decreased by 14.6%. The experimental results show that the dynamic updating of DU-CPABE scheme in cloud computng services can effectively reduce data update time and system overhead.

Personalized recommendation as an effective means of information gathering has been successfully applied to e-commerce, music and film and other fields. Most of the studies have focused on the recommended accuracy, lack of consideration of the diversity of recommended results, and neglected the process characteristics of the recommended items in the application area (e. g. "Internet of Things plus E-government"). Aiming at this problem, an e-government recommendation algorithm Combining User Community and Associated Sequence mining (CAS-UC) was proposed to recommend the items most associated with users. Firstly, the static basic attributes and dynamic behavior attributes of the users and items were modeled separately. Secondly, based on the user's historical record and attribute similarity for user community discovery, the user set most similar to the target user was pre-filtered to improve the diversity of the recommended results and reduce the computational amount of the core recommendation process. Finally, the associated sequence mining of the items was taken full account of the business characteristics of e-government, and the item sequence mining with time dimension was added to further improve the accuracy of the recommended results. The simulation experiments were carried out with the information after desensitization of users on the Spark platform of ewoho.com in Wuhu. The experimental results show that CAS-UC is suitable for the recommendation of items with sequence or process characteristics, and has higher recommendation accuracy compared with traditional recommendation algorithms such as cooperative filtering recommendation, matrix factorization and recommendation algorithm based on semantic similarity. The multi-community attribution factor of the user increases the diversity of the recommended results.

There are serious load imbalance and single point performance bottleneck effect in the traditional static topology leader-based distributed consensus algorithm, and the algorithm is unable to work properly when the number of breakdown nodes is larger than 50% of the cluster size. To solve the above problems, a distributed consensus algorithm (Yac) based on dynamic topology and limited voting was proposed. The algorithm dynamically generated the membership subset and Leader nodes to participate in the consensus voting, and varied with time, achieving statistical load balance. With removal of the strong constraints of all the majority of members to participate in voting, the algorithm had a higher degree of failure tolerance. The security constraints of the algorithm were reestablished by the log chain mechanism, and the correctness of the algorithm was proved. The experimental results show that the load concentration effect of single point in the improved algorithm is significantly lower than that of the mainstream static topology leader-based distributed consensus algorithm Zookeeper. The improved algorithm has better fault tolerance than Zookeeper in most cases and maintains the same as Zookeeper in the worst case. Under the same cluster size, the improved algorithm has higher throughput upper limit than Zookeeper.

Focusing on the electricity user group feature, a residential electricity consumption analysis method based on geographic regularized matrix factorization in smart grid was proposed to explore the characteristics of electricity users and provide decision support for personalized better power dispatching. In the proposed algorithm, customers were firstly mapped into a hidden feature space, which could represent the characteristics of users' electricity behavior, and then k-means clustering algorithm was employed to segment customers in the hidden feature space. In particular, geographic information was innovatively introduced as a regularization factor of matrix factorization, which made the hidden feature space not only meet the orthogonal characteristics of user groups, but also make the geographically close users mapping close in hidden feature space, consistent with the real physical space. In order to verify the effectiveness of the proposed algorithm, it was applied to the real residential data analysis and mining task of smart grid application in Sino-Singapore Tianjin Eco-City (SSTEC). The experimental results show that compared to the baseline algorithms including Vector Space Model (VSM) and Nonnegative Matrix Factorization (NMF) algorithm, the proposed algorithm can obtain better clustering results of user segmentation and dig out certain power modes of different user groups, and also help to improve the level of management and service of smart grid.

Acceleration data in 3 axes during a signature process can be collected to authenticate users. Because of complex structures of Chinese signature, the process of signing in the air is hard to be forged, but it also increases differences between signatures performed by the same user which brings more difficulties in authentication. Classical verification methods applied to 2-D signature or hand gesture cannot solve this problem. In order to improve the performance of in-air Chinese signature verification, the classical Global Sequence Alignment (GSA) algorithm was improved, and the interpolation was applied to matching sequences. Different from classical GSA algorithm which uses matching score to measure similarity between sequences, two distance indexes, Euclidean distance and absolute value distance, were introduced to calculate the differences between sequences after interpolation. Experimental results show that both of the two improved GSA algorithms can improve the accuracy of authentication, the Equal Error Rate (EER) of them are decreased by 37.6% and 52.6% respectively compared with the classical method.

The multi-scale analysis technology has been widely used in the field of digital image processing, the inpainting image with large damaged area has become a hot and difficult spot of image inpainting. Based on the principle of multi-resolution analysis and the traditional method of image inpainting, a new algorithm for image inpainting based on non-subsampled contourlet transform was proposed. Firstly, the image was decomposed into low frequency and high frequency parts by using the non-subsampled contourlet transform, then the parts of different frequency after image decomposition were inpainted respectively. The low frequency components of the image were inpainted by the improved method of texture synthesis. Because after non-subsampled contourlet transform, the information of the corresponding position between the low frequency component and the high frequency component is consistent, the information of corresponding position of other high frequency components could be repaired while the low frequency component was repaired. Finally, the inpainting of the texture image was completed by reconstruction process of non-subsampled contourlet transform. Generally, the selection of image inpainting parameters was appropriate for the best image effect, thus a counter-example was given for authentication. The structural similarity measure among the proposed algorithm and the classical Criminisi algorithm and the wavelet inpainting algorithm has little difference, but the Peak Signal-To-Noise Ratio (PSNR) measurement has different result according to the different texture characteristics of images and the different location characteristics of damaged areas. The simulation results show that the proposed method is very good for the promotion of the non-subsampled Contourlet transform in image inpainting application, and it can get better repair effect while inpainting the image with large damaged area.

With the extensive application of wideband receivers, the blind detection of non-cooperation burst signal in broadband is increasingly important. It is difficult to detect burst signals with low duty cycle time and to distinguish the burst signals with high duty cycle time from continuous-time signals. The problem was solved by constructing two broadband spectral statistics including maximum spectrum and maximum difference spectrum. By keeping the maximum value of instantaneous spectrum, the maximum spectrum has the information of both burst and non-burst signals; by keeping the maximum value of difference between adjacent instantaneous spectrums, the maximum difference spectrum can extract burst information and suppress continuous-time signals. By using these two spectrums, the detection of burst signals in broadband is completed. The test results show that the proposed algorithm can handle burst signals of all the duty cycle time.

Traditional hypernetwork model is biased towards the majority class, which leads to much higher accuracy on majority class than the minority when being tackled on imbalanced data classification problem. In this paper, a Boosting ensemble of cost-sensitive hypernetworks was proposed. Firstly, the cost-sensitive learning was introduced to hypernetwork model, to propose cost-sensitive hyperenetwork model. Meanwhile, to make the algorithm adapt to the cost of misclassification on positive class, cost-sensitive hypernetworks were integrated by Boosting. The proposed model revised the bias towards the majority class when traditional hypernetwork model was tackled on imbalanced data classification, and improved the classification accuracy on minority class. The experimental results show that the proposed scheme has advantages in imbalanced data classification.

A closed-loop scheduling algorithm was proposed for multi-user Multi-Input Multi-Output (MIMO) system to improve wireless spectral performance. Using greedy scheduling technology from multi-user diversity, the algorithm combined the adaptive modulation in the physical layer with automatic repetitive request in the data link layer, and the system's spectral efficiency was enhanced under the interaction of the multi-antenna diversity and multi-user diversity. Considering the practical case of delayed feedback environment, the closed-form expressions of system spectral efficiency under delayed channel were derived. And the experimental results show that this algorithm can hardly be influenced by delay time, which is more applicable to multi-user MIMO system.

Discrete finite element was used as basic unit to simulate and predict deformation of the whole elastomer for complexity of soft tissue deformation in medical image. The process of registration was regarded as solving 2D stress problem by finite element method. The finite element energy function was also improved. Mutual Information (MI) with high accuracy and robustness was selected as metric for solving equation. In order to improve registration efficiency, registration process was optimized by the multi-resolution strategy. By registration experiment for medical images in radiotherapy and comparison with the existing methods, better registration results were obtained. The proposed registration method is more sensitive to the rigid displacement and with improvement in speed. All that shows this registration method is of high precision and efficiency.

Wireless sensor network is a multi-hop wireless network which is made up of a lot of distributed smart sensor nodes. Aiming at the characteristics of the wireless sensor network, under the energy-efficient MAC protocol, the distributed algorithm which adapted to the expansibility of network size was proposed, and simulated by NS-2. This algorithm implemented the expansibility of network size in MAC layer, and enhanced the adaptive ability of network to the variety of the network size.