The existence of privacy security and resource consumption issues in hierarchical federated learning reduces the enthusiasm of participants. To encourage a sufficient number of participants to actively participate in learning tasks and address the decision-making problem between multiple mobile devices and multiple edge servers， an incentive mechanism based on multi-leader Stackelberg game was proposed. Firstly， by quantifying the cost-utility of mobile devices and the payment of edge servers， a utility function was constructed， and an optimization problem was defined. Then， the interaction among mobile devices was modeled as an evolutionary game， and the interaction among edge servers was modeled as a non-cooperative game. To solve the optimal edge server selection and pricing strategy， a Multi-round Iterative Edge Server selection algorithm （MIES） and a Gradient Iterative Pricing Algorithm （GIPA） were proposed. The former was used to solve the evolutionary game equilibrium solution among mobile devices， and the latter was used to solve the pricing competition problem among edge servers. Experimental results show that compared with Optimal Pricing Prediction Strategy （OPPS）， Historical Optimal Pricing Strategy （HOPS） and Random Pricing Strategy （RPS）， GIPA can increase the average utility of edge servers by 4.06%， 10.08%， and 31.39% respectively.

Aiming at the long delay of inference tasks in Deep Neural Network （DNN） on cloud servers， a branchy neural network deployment model based on edge computing was proposed. The distributed deployment problem of DNNs in edge computing scenarios was analyzed， and was proved to be NP-hard. A Deployment algorithm based on Branch and Bound （DBB） was designed to select appropriate edge computing nodes to reduce inference delay. And a Selection Node Exit （SNE） algorithm was designed and implemented to select the appropriate edge computing nodes for different tasks to exit the inference task. The simulation results show that， compared with the approach of deploying neural network model on the cloud， the branchy neural network model based on edge computing reduces the inference delay by 36% on average.

Aiming at the problem that the security surveillance cameras have been hidden by leaves, a leaf occlusion detection algorithm based on Support Vector Machine (SVM) was proposed. The algorithm contains three steps. First, the regions of the leaf existing in the video were segmented. The accumulated frame subtraction method was applied to achieve this purpose. Second, the color and area information of the whole video image and the segmented regions were extracted as the key features. Third, these features were used for modeling and detecting obstacle occlusion by SVM. For all the collected samples, the detection accuracy of this method can reach up to 84%. The experimental results show that the proposed algorithm can detect the leaf occlusion in security surveillance video effectively.

A new Tone Mapping (TM) algorithm based on multi-scale decomposition was proposed to solve a High Dynamic Range (HDR) image displayed on an ordinary display device. The algorithm decomposed a HDR image into multiple scales using a Local Edge-Preserving (LEP) filter to smooth the details of the image effectively, while still retaining the salient edges. Then a dynamic range compression function with parameters was proposed according to the characteristics of the decomposed layers and the request of compression. By changing the parameters, the coarse scale layer was compressed and the fine scale layer was boosted, which resulted in compressing the dynamic range of the image and boosting the details. Finally, by restructuring the image and restoring the color, the image after mapping had a good visual quality. The experimental results demonstrate that the proposed method is better than the algorithm proposed by Gu et al.(GU B, LI W J, ZHU M Y, et al. Local edge-preserving multiscale decomposition for high dynamic range image tone mapping ［J］. IEEE Transactions on Image Processing, 2013, 22(1): 70-79) and Yeganeh et al. (YEGANEH H, WANG Z. Objective quality assessment of tone-mapped images ［J］. IEEE Transactions on Image Processing, 2013, 22(2): 657-667) in naturalness, structural fidelity and quality assessment; moreover, it avoids the halo artifacts which is a common problem existing in the local tone mapping algorithms. The algorithm can be used for the tone mapping of the HDR image.

As to the low clustering quality and high communication cost of the existed distributed clustering algorithm, a distributed data stream clustering algorithm (DAPDC) which combined the density with the idea of representative points clustering was proposed. The concept of the class cluster representative point to describe the local distribution of data flows was introduced in the local sites using affinity propagation clustering, while the global site got the global model by merging the summary data structure that was uploaded from the local site by the improved density clustering algorithm. The simulation results show that DAPDC can improve the clustering quality of data streams in distributed environment significantly. Simultaneously, the algorithm can find the clusters of different shapes and reduce the amount of data transferred significantly by using class cluster representative points.

With serious sidelight, it is difficult for the traditional algorithm to eliminate shadows. To improve the illumination compensation effect, a logarithmic transformation function was presented. In order to improve the performance of face recognition, by taking this problem as a classic pattern classification problem, a new method combining Local Binary Pattern (LBP) and Support Vector Machine (SVM) was proposed. One-against-one was used to convert multi-class problem to two-class problem, that can be used by SVM. Simulation experiments were conducted on the database of CMU PIE, AR, CAS-PEAL and one face database collected by the authors. The results show that lighting effects can be well eliminated and the proposed method performs better than the traditional ones.

The template-based feature in Threading Building Blocks (TBB) simplifies parallel design and is suitable for efficient design of multi-core parallelism. Since fractal computing is CPU-intensive, it is practicable to parallelize fractal computation under TBB. As to the workload unbalance problem in parallelism, a balance method based on sampling execution time was presented to estimate workload. The proposed method realized the task partition through the workload estimate from sampling execution time, and TBB task scheduler was invoked for parallel process. The experimental results show that the proposed method has high estimation accuracy and low time rate so as to effectively achieve workload balance, and good speedups are available through TBB design.

The dynamics, autonomy and anonymity of the P2P network cause many security problems. The traditional trust model in structured P2P network can not satisfy the P2P environment commendably. In this paper, a trust model named DrTrust in unstructured P2P network was proposed, which was based on direct and recommended trust scheme. It takes advantage of the combination of the direct trust and recommended trust to calculate the trust accurately, using distributed way to store trust value and incentive and punishment mechanism to update trust value. The experimental results prove that DrTrust outperforms the current trust models in accurate trust computation and the inhibition to the malicious peers.

An improved approach: median-length included angle chain, combined with the included angle chain was presented to extract the structural features of the palm vein. The way is to model a curve segment of palm vein textures by a number of variable-length line segments through media value iteration and let distance criterion control the fitting error, under permitted error, using the included angles sequence between a pair of neighboring line segments to represent the curve segment. Experimental results show that while the computation precision is ensured, the proposed algorithm still can reduce the computation and acquire the structural features of the palm vein.

Although watershed transformation is a powerful tool for image segmentation, it might give rise to over-segmentation. A novel medical image segmentation algorithm based on anisotropic diffusion filtering using watershed transformation was proposed. First, input image was got through adaptive anisotropic diffusion filter, and then, a multi-scale morphological grads image was obtained as the input of watershed so as to give prominence to the contours of the image and smooth the areas with even luminance. Experiments show that the algorithm can restrain the over-segmentation phenomena effectively, thus obtaining good segmentation results.

To improve the performance of Mobility Anchor Point (MAP) selection algorithm for Hierarchical Mobile IPv6 (HMIPv6), a novel algorithm supporting load sharing was proposed. The algorithm utilized MAP's preference value to characterize the load on that MAP, introduced sharing threshold to judge whether the MAP called "quasi-MAP" had overloaded, and adjusted the selection policy dynamically by the judgment. It is easy to implement. Simulation results indicate that the proposed algorithm reduces protocol cost greatly and has a good effect on load sharing.