The existing deepfake detection methods mainly model on the basis of pixel-level clues of images， and seldom consider the impact of the synthesis process on the forged images. Although good detection results are achieved， it is difficult to explain the detection process. Therefore， a multi-modal physical prior feature fusion-based explainable detection method for deepfakes was proposed. First， optical flow features， illumination features， edge features and DCT（Discrete Cosine Transform） features were used to describe the inter-frame motion differences in temporal videos， the illumination inconsistency in single-frame videos， and edge artifact information， respectively， so as to obtain multi-modal physical prior features with explainability. Second， a multi-modal mixture of experts network was proposed to construct expert sub-networks for different modalities， and after cross-modal attention weighting， the sub-networks were fused through a gated unit and input into the discriminative network for classification. Third， the SIAM （Spatial Intersection Attention Module） was introduced into the discriminative network， and the fully connected structure was replaced by the KAN （Kolmogorov-Arnold Network） structure. Finally， the multi-modal physical prior features were used to train different expert sub-networks， respectively， and the Shapley value analysis of different input features was given， thereby constructing a pre-feature-post-explanation explainable analysis framework to provide pixel-level explanations for model inference and prediction. Experimental results show that compared with algorithms such as CORE（COnsistent REpresentation learning）， SRM（Rich Models for Steganalysis）， and UCF（Uncovering Common Features）， the proposed method achieves the best performance on AUC and accuracy， with an accuracy range of 97.35% to 98.75% and an average accuracy of 98.22% on FaceForensics++ dataset， and the model’s interpretability also is improved significantly.

As the uncertainty of user requirements in the cloud-edge environment causes the microservice composition logic to be dynamically adjusted with the changes of user needs， a Dynamic Evolution method for Microservice Composition system （DE4MC） in the cloud-edge environment was proposed. Firstly， the user's operation was automatically recognized to implement the corresponding algorithm strategy. Secondly， in the deployment stage， the better node was selected by the system for deployment through the deployment algorithm in the proposed method after the user submitting the business process. Finally， in the dynamic adjustment stage， the dynamic evolution was performed by the system through the dynamic adjustment algorithm in the proposed method after the user adjusting the business process instances. In both algorithms in the proposed method， the migration cost of microservice instances， the data communication cost between microservices and users， and the data flow transmission cost between microservices were comprehensively considered to select better nodes for deployment， which shortened the running time and reduced the evolution cost. In the simulation experiment， in the deployment stage， the deployment algorithm in the proposed method has average running time of all scales 9.7% lower and total evolution cost 16.8% lower than those of the combination algorithm of Heuristic Algorithm （HA） with Non-dominated Sorting Genetic Algorithm-Ⅱ （NSGA-Ⅱ）； in the dynamic adjustment stage， compared with the combination algorithm of HA and NSGA-Ⅱ， the dynamic adjustment algorithm in the proposed method has the average running time of all scales 6.3% lower， and the total evolution cost 21.7% lower. Experimental results show that the proposed method ensures timely evolution of the microservice composition system in the cloud-edge environment with low evolution cost and short business process time， and provides users with satisfactory quality of service.

In order to protect user's identity privacy and data security for access control in wireless sensor networks, a privacy-preserving access control protocol in multi-user wireless sensor networks was proposed. The protocol employed attribute-based encryption algorithms and distributed access control mode, using the attribute certificates, digital signatures and threshold mechanism to achieve the pay access, fine-grained access control and anonymous access. And it also ensured the confidentiality of data transmission and data integrity of query command. Analysis and protocol comparison shows that the proposed protocol has several advantages over the current access control methods: lower cost in computation, communication and storage, better scalability and better adaptation to access control requirement of payment wireless sensor network.

Electronic Paper Display (EPD) can exhibit good comfortability in reading, but it has a critical drawback - slow refresh, which will be overcome by optimizing the design of the display's driver software. A tri-buffer-based architecture as well as its design methodology for the EPD driver software was proposed in this paper. Also an e-reader integrating the EPD driver in it was implemented to verify the design. Compared with the traditional dual-buffer architecture, the proposed tri-buffer scheme set an additional memory area to keep the EPD data frame. Test results show that the driver software works well in a real device without screen flicker and can help the display to achieve excellent performance.

CT image denoising restoration is a basic procedure in medical image processing. Cartoon-texture decomposition method was extended in order to resolve the problems of computational difficulty and low precision while applying cartoon-texture models in medical image denoising. First, the structure of cartoon-texture model was described by curvelet transform. Second, the texture of cartoon-texture decomposition was described using more sparse dual-tree complex wavelet transform. Third, an image cartoon images-texture model was established by combining curvelet transform and sparse representation. The algorithms of cartoon-texture model were discussed at last. The simulation experimental results show that the new method can effectively resolve the problem of large amount of iterative calculation using medical image denoising algorithm, and the image quality after processing can be improved as well.

Signal decomposition is a process that obtains information from signals and it is a foundational and key technique for many fields such as pattern recognition, intelligent system and machinery fault diagnosis. It is very important to study non-stationary signal decomposition which always includes lots of information that can reflect the changing of the system and widely exists. After improving the sparsity of signal representation, the engineering background of feature extraction for non-stationary signal was studied in this paper, the characteristics, mechanisms, development history and current and future challenges of five types of methods were analyzed in depth, the models of these methods were compared, together with the state-of-the-art of feature extraction models in signal processing and analysis and some successful applications available were systematically reviewed. Finally, several main problems and a few deficiencies were pointed out, and future research directions were anticipated.

Negative Selection (NS) algorithm of artificial immunology has been successfully applied to anomaly detection on some lowdimension data, but the performance becomes unfavorable on highdimension data. Realvalued negative selection algorithm with variablesized detectors (VRNS) was applied to network intrusion detection and a variation of it (IVRNS) was proposed to improve the performance on highdimension data. In the improved algorithm, the detectors were used to control the coverage of them according to the overlap among the detectors. Experimental results prove the effectiveness of this novel algorithm on high-dimension data and a high detection rate with a lower false alarm rate in network intrusion.

Graph theory was utilized to improve image segmentation of traditional Fuzzy C-Means (FCM). The proposed algorithm used weighting of graph theory to calculate the distance of FCM, compared with Euclid distance, the proposed algorithm not only considered the distance of every sample, but also considered the Grayscale difference of every sample, and gained fuzzy membership function which was suitable for image segmentation. Based on the experimental result, probability of error and index of evaluation through comparing with image segmentation based traditional FCM and image segmentation based graph theory. The improved FCM in this paper is proved to be an appropriate method which is suitable for image segmentation.

In this paper, we studied the algorithm of E-mail classification using nave Bayes classification. The concepts of Fizz Network and Fizz Degree were proposed. We presented the algorithm to depict the communication network of criminous orgnization, and the algorithm for structure mining. Finally, the experiments prove the good performance of the proposed algorithm.

Self generating neural networks have been presented as a better alternative to fixed structure in data mining application. The paper provided the algorithm of Self Organising Map(SOM), and presented an version of Growing Self Organising Map(GSOM) model which can extend into a nearest prototype classifier, and gave an application in data mining using GSOM.