Aiming to the problems of low embedding capacity and poor visual quality of the extracted secret images in existing generative data hiding algorithms， a generative data hiding algorithm based on multi-scale attention was proposed. First， a generator with dual encode-single decode based on multi-scale attention was designed. The features of the cover image and secret image were extracted independently at the encoding end in two branches， and fused at the decoding end by a multi-scale attention module. Skip connections were used to provide different scales of detail features， thereby ensuring high-quality of the stego-image. Second， self-attention module was introduced into the extractor of the U-Net structure to weaken the deep features of the cover image and enhance the deep features of the secret image. The skip connections were used to compensate for the detail features of the secret image， so as to improve the accuracy of the extracted secret data. At the same time， the adversarial training of the multi-scale discriminator and generator could effectively improve the visual quality of the stego-image. Experimental results show that the proposed algorithm can achieve an average Peak Signal-to-Noise Ratio （PSNR） and Structure Similarity Index Measure （SSIM） of 40.93 dB and 0.988 3 for the generated stego-images， and an average PSNR and SSIM of 30.47 dB and 0.954 3 for the extracted secret images under the embedding capacity of 24 bpp.

Existing emotion recognition models based on Electroencephalogram （EEG） almost ignore differences in emotional states at different time periods， and fail to reinforce key emotional information. To solve the above problem， a Multiple Context Vectors optimized Convolutional Recurrent neural network （CR-MCV）was proposed. Firstly， feature matrix sequence of EEG signals was constructed to obtain spatial features of multi-channel EEG by Convolutional Neural Network （CNN）. Then， recurrent neural network based on multi-head attention was adopted to generate multiple context vectors for high-level abstract feature extraction. Finally， a fully connected layer was used for emotion classification. Experiments were carried out on DEAP （Database for Emotion Analysis using Physiological signals） dataset， and the classification accuracy in arousal and valence dimensions was 88.09% and 89.30%， respectively. Experimental results show that the CR-MCV can adaptively allocate attention of features and strengthen salient information related to emotion states based on utilization of electrode spatial position information and saliency characteristics of emotional states at different time periods.

Sparse-dense Matrix Multiplication （SpMM） is widely used in the fields such as scientific computing and deep learning， and it is of great importance to improve its efficiency. For a class of sparse matrices with band feature， a new storage format BRCV （Banded Row Column Value） and an SpMM algorithm based on this format as well as an efficient Graphics Processing Unit （GPU） implementation were proposed. Due to the fact that each sparse band can contain multiple sparse blocks， the proposed format can be seen as a generalization of the block sparse matrix format. Compared with the commonly used CSR （Compressed Sparse Row） format， BRCV format was able to significantly reduce the storage complexity by avoiding redundant storage of column indices in sparse bands. At the same time， the GPU implementation of SpMM based on BRCV format was able to make more efficient use of GPU’s shared memory and improve the computational efficiency of SpMM algorithm by reusing the rows of both sparse and dense matrices. For randomly generated band sparse matrices， experimental results on two different GPU platforms show that BRCV outperforms not only cuBLAS （CUDA Basic Linear Algebra Subroutines）， but also cuSPARSE based on CSR and block sparse formats. Specifically， compared with cuSPARSE based on CSR format， BRCV has the maximum speedup ratio of 6.20 and 4.77 respectively. Moreover， the new implementation was applied to accelerate the SpMM operator in Graph Neural Network （GNN）. Experimental results on real application datasets show that BRCV outperforms cuBLAS and cuSPARSE based on CSR format， also outperforms cuSPARSE based on block sparse format in most cases. In specific， compared with cuSPARSE based on CSR format， BRCV has the maximum speedup ratio reached 4.47. The above results indicate that BRCV can improve the efficiency of SpMM effectively.

Attackers can illegally open a vehicle by forgeing the Radio Frequency IDentification （RFID） signal sent by the vehicle remote key. Besides， when the vehicle remote key is lost or stolen， the attacker can obtain the secret data inside the vehicle remote key and clone a usable vehicle remote key， which will threaten the property and privacy security of the vehicle owner. Aiming at the above problems， a Vehicle RKE Two-Factor Authentication （VRTFA） protocol for vehicle Remote Keyless Entry （RKE） that resists physical cloning attack was proposed. The protocol is based on Physical Uncloneable Function （PUF） and biological fingerprint feature extraction and recovery functions， so that the specific hardware physical structure of the legal vehicle remote key cannot be forged. At the same time， the biological fingerprint factor was introduced to build a two-factor authentication protocol， thereby solving the security risk of vehicle remote key theft， and further guaranteeing the secure mutual authentication of vehicle RKE system. Security analysis results of the protocol using BAN logic show that VRTFA protocol can resist malicious attacks such as forgery attack， desynchronization attack， replay attack， man-in-the-middle attack， physical cloning attack， and full key leakage attack， and satisfy the security attributes such as forward security， mutual authentication， data integrity， and untraceability. Performance analysis results show that VRTFA protocol has stronger security and privacy and better practicality than the existing RFID authentication protocols.

Ring signature is widely used to solve the problems of user identity and data privacy disclosure because of its spontaneity and anonymity； and certificateless public key cryptosystem can not only solve the problem of key escrow， but also do not need the management of public key certificates； certificateless ring signature combines the advantages of both of the above mentioned， and has extensive research significance， but most of the existing certificateless ring signature schemes are based on the calculation of bilinear pairings and modular exponentiation， which are computationally expensive and inefficient. In order to improve the efficiency of signature and verification stages， a new Efficient CertificateLess Ring Signature （ECL-RS） scheme was proposed， which used elliptic curve with low computational cost， high security and good flexibility. The security statute of ECL-RS scheme stems from a discrete logarithm problem and a Diffie-Hellman problem， and the scheme is proved to be resistant to public key substitution attacks and malicious key generation center attacks under Random Oracle Model （ROM） with unforgeability and anonymity. Performance analysis shows that ECL-RS scheme only needs （n+2） （n is the number of ring members） elliptic curve scalar multiplication and scalar addition operations as well as （n+3） one-way hash operations， which has lower computational cost and higher efficiency while ensuring security.

Most of the existing network embedding methods only preserve the local structure information of the network， while they ignore other potential information in the network. In order to preserve the community information of the network and reflect the multi-granularity characteristics of the network community structure， a network Embedding method based on Multi-Granularity Community information （EMGC） was proposed. Firstly， the network’s multi-granularity community structure was obtained， the node embedding and the community embedding were initialized. Then， according to the node embedding at previous level of granularity and the community structure at this level of granularity， the community embedding was updated， and the corresponding node embedding was adjusted. Finally， the node embeddings under different community granularities were spliced to obtain the network embedding that fused the community information of different granularities. Experiments on four real network datasets were carried out. Compared with the methods that do not consider community information （DeepWalk， node2vec） and the methods that consider single-granularity community information （ComE， GEMSEC）， EMGC’s AUC value on link prediction and F1 score on node classification are generally better than those of the comparison methods. The experimental results show that EMGC can effectively improve the accuracy of subsequent link prediction and node classification.

In order to solve the turning problem of PID controller parameters, an automatic tuning method based on Internal Model Control (IMC) algorithm and system identification was proposed. In this approach, an identification method based on the open-loop unit step response was employed. The input/output data during the transient process were used to obtain a First Order Plus Dead Time (FOPDT) or Second Order Plus Dead Time (SOPDT) model. Then the parameters of PID controller were determined by IMC algorithm. As to the determination of the IMC filter parameter λ, two parameters, γ and σ were introduced in this method. Then the parameter λ was determined by the relationship between the square of output error and the two parameters above. In the simulation experiments, compared with the traditional IMC based PID controller, the Integral Absolute Error (IAE) index can be improved by about 20% without the input disturbance, while the index can be improved by about 10% with disturbance. The simulation results show that in the premise of ensuring the system robustness, the proposed algorithm not only improves the speed of the transient response, but also effectively restrains the overshoot of the system output.

Concerning the difficulties of parameter estimation for industrial modeling in practice, an innovative approach through data mining to correct parameter of model was proposed. Mining data from a large number of actual data accumulated in production process could be used for correcting parameter through statistical method. The improved method of least square was used for industrial data which contained noise. In view of the characteristics of industrial data, such as incompletion and common distribution, parameter should be segmented and combined to be corrected. For dynamic compensation of statistical model, dynamic parameter can be estimated through data mining of historical dynamic process. Parameter correction and data mining should be interactive with each other. To reduce the scope of massive data mining and improve sufficiency of sample data required for parameter correction, the network model of co-ordination was designed. It is shown in actual cases that this method is efficient and practical. The accuracy of simulation can be greatly improved through this method.

The multi-class classification algorithms based on traditional Support Vector Machine (SVM) are weak on training speed when dealing with large-scale data. To solve the problem, this paper proposed a multi-class classification algorithm based on Twin Support Vector Machine (TWSVM). It combined binary tree multi-class classification and constructed classifiers based on TWSVM on the nodes of binary tree. To reduce the error accumulation of Binary Tree SVM (BT-SVM), it firstly got clustering centers through the clustering algorithm, and then compared the distances between them to determine the separation sequence of classes. Finally, it was applied to network intrusion detection. The experimental results show that the proposed algorithm has higher detection accuracy and certain advantages on training speed especially for large-scale data. The training speed is approximately two times faster than that of the traditional BT-SVM algorithm. It is valuable for large-scale data processing in the field of network intrusion detection.

The structure of the text is neglected by using the majority of used kernels to classification, so that a lot of semantic information is lost. In order to solve this problem, a Word Sequence Kernel (WSK) based on dependence measure was proposed and used in the field of spam filtering in this paper. Firstly, the features of each E-mail were extracted and the dependence measure of each feature was calculated; then the word sequence kernel was used as kernel function to train Support Vector Machine (SVM), and the decay factor of each feature was calculated by taking the dependence measure of each feature into account in the training process; finally, the optimized SVM filter was used to spam filtering. The experimental results show that the improved word sequence kernel gets higher accuracy compared to the commonly used kernels and string subsequence kernel. The proposed method improves the accuracy of spam filtering.

Kernel Canonical Correlation Analysis (KCCA) is a recently addressed supervised machine learning methods, which is a powerful approach of extracting nonlinear features. However, the standard KCCA algorithm may suffer from computational problem as the training set increases. To overcome the drawback, an improved KCCA was proposed. Firstly, a scheme based on geometrical consideration was proposed to select a subset of samples that were projected to feature space (Reproducing Kernel Hilbert Space). And then, an efficient algorithm was proposed to enhance the efficiency of the feature extraction, which selected the most contributive eigenvectors for training and classification, and then calculated the corresponding eigenvectors for classification. Finally, the improved KCCA was combined with a multi-class classification method based on Support Vectors Data Description (SVDD) for classification and recognition, which put forward new ideas for pattern recognition based on kernels. The experimental results on ORL face database show that the proposed method reduces the training time and the system storage without deteriorating the recognition accuracy compared with standard KCCA.

Nowadays, Radio Frequency IDentification (RFID) security protocols based on Hash function have poor mobility and cannot satisfy the requirements of some fields. Aiming to boost up the mobility of RFID security protocols, a Mobile RFID Security Protocol was presented and GNY logic was used to prove its correctness. Analysis shows that presented protocol has satisfied mobility and security, and the protocol can be used in transmitting freight and field operation of war time, etc.

A revision method was proposed for the offset of separation hyperplane of binary-classification imbalanced data in Support Vector Machine (SVM). Firstly, the principal values were found respectively of the two classes of samples in feature space by using Kernel Principal Component Analysis (KPCA). Secondly, one penalty proportion was given based on the information provided by the sizes of the two sample data and their values. Finally, a new separation hyperplane was generated through the optimization training. The hyperplane revised the error of the standard support vector machines. Experiment results prove the validity of the method. Compared with standard support vector machines, the proposed method can not only balance but also decrease the classification error.

In order to enhance the sense of realism of the integration of virtual and real objects in augmented reality scenes， a variation-aware online dynamic illumination estimation method for indoor scenes was proposed. Unlike the existing methods that directly calculate lighting parameters or generate lightmaps， the lighting variation images of the scene under different lighting conditions are estimated by this method to implement the dynamic update of the scene illumination， which can obtain dynamic lighting of the scene more accurately and retain detailed information of the scene. The Convolutional Neural Network （CNN） of the proposed network includes two sub-networks， namely Low Dynamic Range （LDR） image feature extraction network and illumination estimation network. The whole network structure took a High Dynamic Range （HDR） panoramic lightmap with all the main light sources open in the scene as the initial lightmap， and this lightmap and the LDR image with limited field of view after lighting change were used as the input together. Firstly， the CNN was built based on AlexNet to extract the LDR image features， and these features were connected with the HDR lightmap features in illumination estimation network sharing encoder. Then， the U-Net structure was used to estimate the lighting variation image and the mask of light source by introducing the attention mechanism， so as to update the dynamic illumination of the scene. In the numerical evaluation of panoramic lightmap， the Mean Squared Error （MSE） indicator of the proposed method was improved by about 79%， 65%， 38%， 17%， and 87% compared with those of Gardner’s method， Garon’s method， EMLight， Guo’s method， and coupled dual StyleGAN panoramic synthesis network StyleLight， respectively， and other indicators were also improved. The above proves the effectiveness of the proposed method from both qualitative and quantitative aspects.