Aiming at the problems of low accuracy and low operation efficiency of federated learning algorithm in user behavior prediction, a loss-free Federated Learning Security tree (FLSectree) algorithm was proposed. Firstly, through the derivation of the loss function, its first partial derivative and second partial derivative were proved to be sensitive data, and the optimal split point after encryption was returned by scanning and splitting the feature index sequence, so as to protect the sensitive data from being disclosed. Then, by updating the instance space, the splitting was continued and the next best split point was found until the termination condition was satisfied. Finally, the results of training were used to obtain local algorithm parameters for each participant. Experimental results show that the FLSectree algorithm can effectively improve the accuracy and the training efficiency of user behavior prediction algorithm under the premise of protecting the data privacy. Compared with the SecureBoost algorithm in Federated AI Technology Enabler (FATE) framework of federated learning, FLSectree algorithm has the user behavior prediction accuracy increased by 9.09% and has the operation time reduced by 87.42%, and the training results are consistent with centralized Xgboost algorithm.

Content offloading technology based on mobile edge computing can effectively reduce the traffic pressure on the backbone network and improve the end user's experience. A content offloading scheme of greedy strategy was designed for the heterogeneous contact rate between end users and small base stations. Firstly, the content optimal offloading problem was transformed into the content maximum delivery rate problem. Secondly, the maximum delivery rate problem was proved to satisfy the submodularity. On this basis, the greedy algorithm was used to deploy the content. The algorithm was able to guarantee its optimality with the probability (1-1/e). Finally, the impacts of content popularity index and cache size on different offloading schemes were analyzed in detail. The experimental results show that the proposed scheme improves the content delivery rate and reduces the content transmission delay at the same time.

In most routing algorithms of the previous work, the flooding method is used to obtain auxiliary information, which wastes network resources. Motivated by this, a distributed social distance routing algorithm was proposed. Firstly, the stability and regularity of contact between nodes were analyzed to determine the friend relationship. Then, the social-distance between nodes was constructed by the friend relationship. In addition, a table for recording the shortest social distance to other nodes was maintained by each node, and the minimum social distance was continually updated by exchanging and comparing the information in the table. The construction of social distance only needs to exchange information among friends instead of all nodes, which can greatly reduce the time of auxiliary-information exchange. Finally, when the packet was sent to the relay node with a smaller social distance to its destination node, the delivery ratio could be significantly improved. The experimental results demonstrate that, compared with the Probabilistic Routing Protocol using History of Encounters and Transitivity (PRoPHET) algorithm, the delivery ratio of the proposed algorithm is increased by about 3%, the data packet transmission delay is reduced by about 27%, and the auxiliary-information exchange times is reduced by about 63%. Compared with the routing based on Betweenness centrality and Similarity (SimBet) algorithm, the delivery ratio of the proposed algorithm is increased by about 11%, the data packet transmission delay basically equals, the auxiliary-information exchange times is reduced by about 63%. The social distance algorithm provides a theoretic support for large-scale mobile opportunistic networks, because of its better performance in scalability.

An improved robust OctoMap based on full visibility model was proposed to meet accuracy needs of 3D map for mobile robot autonomous navigation and it was applied to the RGB-D SLAM (Simultaneous Localization And Mapping) based on Kinect. First of all, the connectivity was judged by considering the the relative positional relationship between the camera and the target voxel and the map resolution to get the number and the location of adjacent voxels which met connectivity. Secondly, according to the different connectivity, the visibility model of the target voxel was built respectively to establish the full visibility model which was more universal. The proposed model could effectively overcome the limitations of the robust OctoMap visibility model, and improve the accuracy. Next, the simple depth error model was replaced by the Kinect sensor depth error model based on Gaussian mixture model to overcome the effect of the sensor measurement error on the accuracy of map further and reduce the uncertainty of the map. Finally, the Bayesian formula and linear interpolation algorithm were combined to update the occupancy probability of each node in the octree to build the volumetric occupancy map based on a octree. The experimental results show that the proposed method can effectively overcome the influence of Kinect sensor depth error on map precision and reduce the uncertainty of the map, and the accuracy of map is improved obviously compared with the robust OctoMap.

Many traditional machine learning methods tend to get biased classifier which leads to lower classification precision for minor class in sequential imbalanced data. To improve the classification accuracy of minor class, a new hybrid sampling online extreme learning machine on sequential imbalanced data was proposed. This algorithm could improve the classification accuracy of minor class as well as reduce the loss of classification accuracy of major class, which contained two stages. In offline stage, the principal curve was introduced to model the confidence regions of minor class and major class respectively based on the strategy of balanced samples. Over-sampling of minority and under-sampling of majority was achieved based on confidence region. Then the initial model was established. In online stage, only the most valuable samples of major class were chosen according to the sample importance, and then the network weight was updated dynamically. The proposed algorithm had upper bound of the information loss through the theoretical proof. The experiment was taken on two UCI datasets and the real-world air pollutant forecasting dataset of Macao. The experimental results show that, compared with the existing methods such as Online Sequential Extreme Learning Machine (OS-ELM), Extreme Learning Machine (ELM) and Meta-Cognitive Online Sequential Extreme Learning Machine (MCOS-ELM), the proposed method has higher prediction precision and better numerical stability.

The characteristic that mobile opportunistic network exploits node contacts to forward packets is very suitable for the Ad Hoc networking requirements in actual environment, thus a large number of applications are produced. Considering the smart devices are generally carried by people or integrated in vehicles, human involvement is one of the most important factors for the success of these applications, this paper explored the influence of human mobility on data communication. The authors observed that people always visited hot regions, while other regions were visited less frequently. Motivated by this observation, the GS (Gathering Spray), a human gathering point assisted spraying scheme for mobile opportunistic scenarios was proposed. GS assumed each hot region configured a Access Point (AP), which had a higher priority to cache and spray messages than other mobile nodes. Theoretical analysis verifies that GS achieves a lower mean delivery delay than the Spray-Wait, and the simulation results show that GS improves the packet delivery ratio simultaneously.