Since the computing capacity and battery energy of unmanned aerial vehicle (UAV) are constrained, UAV as aerial user is hard to handle the high computational complexity and time-sensitive applications. This paper investigates a cellular-connected multi-UAV network supported by mobile edge computing. Multiple UAVs carrying tasks fly from a given initial position to a termination position within a specified time. To handle the large number of tasks carried by UAVs, we propose a energy cost of all UAVs based problem to determine how many tasks should be offloaded to high-altitude balloons (HABs) for computing, where UAV-HAB association, the trajectory of UAV, and calculation task splitting are jointly optimized. However, the formulated problem has nonconvex structure. Hence, an efficient iterative algorithm by applying successive convex approximation and the block coordinate descent methods is put forward. Specifically, in each iteration, the UAV-HAB association, calculation task splitting, and UAV trajectory are alternately optimized. Especially, for the nonconvex UAV trajectory optimization problem, an approximate convex optimization problem is settled. The numerical results indicate that the scheme of this paper proposed is guaranteed to converge and also significantly reduces the entire power consumption of all UAVs compared to the benchmark schemes.

Accurate numerical weather prediction is an important prerequisite for refined public and commercial meteorological services. ECMWF forecast products are widely used around the world, where as systematic forecast errors always exist. As a correction of numerical prediction products, multi-source data fusion can effectively reduce prediction errors, which is also a typical high-dimensional nonlinear mapping problem. Due to the heterogeneity of geographic data and ground truth data and satellite data, it is necessary to establish a mechanism to fully extract and utilize effective information from these data while avoid noise and redundancy of the information. In recent years, deep learning methods have been extensively applied to data post-processing in meteorological field. Aiming at errors in numerical weather prediction and the nonlinear mapping problem in multi-source data fusion, this study designs a correction deep learning model NFC-Net for ECMWF numerical prediction products, which mainly includes a multi-source data spatial resolution alignment module, a spatiotemporal feature extraction module, and a UNet correction module. NFC-Net optimizes and corrects the forecast results by integrating multi-source data such as FY-4A satellite data, DEM, and ERA5 historical truth data, and utilizes multi-source data spatial resolution alignment module and spatiotemporal feature extraction module to achieve feature extraction and fusion for multi-source heterogeneous data. At the same time, this paper also proposes a spatial resolution alignment algorithm based on convolutional neural networks (UPS-MSR algorithm) and a dual self-attention mechanism (DSA). The UPS-MSR algorithm uses up-sampling and multi-scale residual networks to achieve grid alignment of meteorological and geographic data with different resolutions, which can effectively avoid information loss. The DSAConvlstm network embedded in DSA module can balance the spatiotemporal correlation and element correlation when extracting features from high-dimensional meteorological information. To evaluate the performance of the proposed method NFC-Net, correction experiments on two weather elements, i.e., 2 m temperature and 10 m wind speed in the ECMWF products, are carried out and the results are compared with the ECMWF forecast results, ANO, Convlstm, Fuse-CUnet and ERA5. The experiments show that the root mean square errors (RMSEs) of 2 m temperature and 10 m wind speed corrected by the NFC-Net model decrease by 49.71% and 50.86%, respectively when compared to that in the ECMWF forecast products. The experimental results indicate that the introduction of high-resolution DEM data in the NFC-Net model can obviously optimize land surface process of the model, and the correction effect is more pronounced under complex terrain condition. The use of FY-4A satellite data enables the model to obtain more three-dimensional information during correction. The application of DSA module can make the model pay more attention to variables that have strong correlations with correction elements, and thereby significantly improves the quality of correction. The proposed method can prospectively be applied in the correction of ECMWF forecast results and promote the accuracy of numerical weather prediction.

Breast mass identification is of great significance for early screening of breast cancer, while the existing detection methods have high missed and misdiagnosis rate for small masses. We propose a small target breast mass detection network named Residual asymmetric dilated convolution-Cross layer attention-Mean standard deviation adaptive selection-You Only Look Once (RCM-YOLO), which improves the identifiability of small masses by increasing the resolution of feature maps, adopts residual asymmetric dilated convolution to expand the receptive field and optimize the amount of parameters, and proposes the cross-layer attention that transfers the deep semantic information to the shallow layer as auxiliary information to obtain key feature locations. In the training process, we propose an adaptive positive sample selection algorithm to automatically select positive samples, which considers the statistical features of the intersection over union sets to ensure the validity of the training set and the detection accuracy of the model. To verify the performance of our model, we used public datasets to carry out the experiments. The results showed that the mean Average Precision (mAP) of RCM-YOLO reached 90.34%, compared with YOLOv5, the missed detection rate for small masses of RCM-YOLO was reduced to 11%, and the single detection time was reduced to 28 ms. The detection accuracy and speed can be effectively improved by strengthening the feature expression of small masses and the relationship between features. Our method can help doctors in batch screening of breast images, and significantly promote the detection rate of small masses and reduce misdiagnosis.