In view of the low accuracy of functional Magnetic Resonance Imaging （fMRI） brain age prediction and the lack of research on the combination of this problem and deep learning， an fMRI brain age prediction model with Lightweight Multi-scale Convolutional Network （LMCN） was proposed. Firstly， the Pearson correlation coefficient （R） of the Region Of Interest （ROI） in fMRI was calculated to obtain the Functional Connectivity （FC） matrix of the ROI as input. Secondly， the number of FC channels was increased to ensure the number of features and the size of the feature map was reduced simultaneously. At the same time， the multi-scale dilated convolution module RFB （Receptive Field Block） with the characteristics of human visual attention was used to extract age features. Finally， the predicted brain age was output by the fully connected layer， and the ablation prediction results of each brain region were calculated to explore the key brain regions influencing the brain age prediction results. Evaluation was carried out on two public datasets， E-NKI and Cam-CAN. It can be seen that the memory required for LMCN parameters is 2.30 MB， which is 60.3% and 52.0% less than those of MobileNetV3 and ShuffleNetV2 respectively. In terms of prediction results， on E-NKI dataset， LMCN has the Mean Absolute Error （MAE） of 5.16， the R of 0.947， and the Root Mean Square Error （RMSE） of 6.40. Compared to the model that combines network-based feature selection with the least angle regression， LMCN has the MAE decreased by 1.34 and the R increased by 0.037； on Cam-CAN dataset， LMCN has the MAE of 5.97， the R of 0.904， and the RMSE of 7.93. Compared to the connectome-based machine learning model， LMCN has the R increased by 0.019， and the RMSE decreased by 0.64. The results show that while LMCN has small number of parameters and is easy to deploy， it can improve the accuracy of fMRI brain age prediction effectively and provide clues for assessing the brain status of healthy adults.

Route planning is very important for the task execution of Unmanned Aerial Vehicle （UAV） swarm， and the computation is usually complex in high dimensional scenarios. Swarm intelligence has provided a good solution for this problem. Particle Swarm Optimization （PSO） algorithm is especially suitable for route planning problem because of its advantages such as few parameters， fast convergence and simple operation. However， PSO algorithm has poor global search ability and is easy to fall into local optimum when applied to route planning. In order to solve the problems above and improve the effect of UAV swarm route planning， a Dynamic Cluster Particle Swarm Optimization （DCPSO） algorithm was proposed. Firstly， artificial potential field method and receding horizon control principle were used to model the task scenario of route planning problem of UAV swarm. Secondly， Tent chaotic map and dynamic cluster mechanism were introduced to further improve the global search ability and search accuracy. Finally， DCPSO algorithm was used to optimize the objective function of the model to obtain each trajectory point selection of UAV swarm. On 10 benchmark functions with different combinations of unimodal/multimodal and low-dimension/high-dimension， simulation experiments were carried out. The results show that compared with PSO algorithm， Pigeon-Inspired Optimization （PIO）， Sparrow Search Algorithm （SSA） and Chaotic Disturbance Pigeon-Inspired Optimization （CDPIO） algorithm， DCPSO algorithm has better optimal value， mean value and variance， better search accuracy and stronger stability. Besides， the performance and effect of DCPSO algorithm were demonstrated in the route planning application instances of UAV swarm simulation experiments.

Random number and broadcast polynomial for every session were created. The legal nodes could recover the lost legal group keys by themselves independently according to their private information and broadcast messages, and the collusion attack between newly joined nodes and revoked nodes was resisted. New private information was distributed to revoked nodes so as to rejoin group in later sessions. Through the security and efficiency analysis, the scheme has less communication cost yet still achieves security property, suitable for mobile Ad Hoc network.

Limited by the complexity and analysis efficiency of image processing， traditional photovoltaic fault diagnosis methods based on image recognition are difficult to achieve real-time monitoring and large-scale fault classification and location. To address this problem， a photovoltaic detection algorithm based on shape factor and improved watershed segmentation was proposed. Firstly， a photovoltaic module segmentation algorithm was designed on the basis of shape factor. And the shape factor was defined as the ratio of the area to the perimeter of ??the connected region. It has scale and rotation invariance， and is able to extract the contours of photovoltaic modules with different scales in complex backgrounds to avoid interference of background areas on fault diagnosis. Secondly， the watershed algorithm was improved by iterative H value， the over-segmentation phenomenon was suppressed by adjusting the local minimum value， and the fault classification and precise location of the segmented photovoltaic module image were performed. Finally， in order to achieve remote control， the human-computer interaction interface designed by Qt Designer software was embedded in Raspberry Pi， and the intranet penetration and Virtual Network Console （VNC） were configured. At the same time， the drone was equipped with a Raspberry Pi and a high-definition camera to achieve real-time monitoring and fault diagnosis of photovoltaic station during flight. Experimental results show that the comprehensive accuracy of the proposed algorithm for identifying photovoltaic faults is 85.19%， which is 9.38 percentage points higher than that of the traditional watershed algorithm， and the over-segmentation rate is reduced by 26.1 percentage points， indicating that the proposed algorithm can control the over-segmentation phenomenon more effectively and improve the accuracy of fault diagnosis.