It's difficult to implement maintainability design and evaluation effectively in the early stages of development of space TT&C ground system. To solve this problem,a maintainability design and evaluation system is constructed based on virtual reality technology,a maintainability design and evaluation workflow is developed,and a comprehensive evaluation criteria for maintainability design is proposed. In the virtual maintenance scenario,virtual maintenance prototypes and virtual maintenance resources are used to verify the overall process,and immersive simulation is conducted to verify the accessibility,visibility,and human body comfort of the maintenance of components of a vehicle mounted space TT&C ground system. Thus the quantitative comprehensive evaluation of virtual maintainability design is achieved. The results show that this method reduces costs by 68% , shortens duration by 61% compared with traditional method. It may serve as a practical reference for visualizing,quantifying carrying out maintainability design and evaluation in the early stages of development of space TT&C ground system.

In broadband reconnaissance scenarios，achieving high signal detection accuracy often entails significant computational costs. To address this，a multi-scale convolution attention sparse detection(MSCAS) method is proposed，which incorporates prior knowledge of signal spectrograms by capturing long-range temporal dependencies and suppressing irrelevant frequency-domain interference. MSCA-S introduces a multiscale horizontal convolution attention(MSHCA) mechanism that jointly extracts multi-dimensional signal features，enhancing detection accuracy while reducing computational complexity through horizontal convolution. Building on MSHCA，a hierarchically stacked broadband signal detection framework is developed，and sparse feature parameters are used to further optimize computational efficiency. MSCA-S is evaluated on a real-world and simulated broadband signal dataset(2.5 MHz spectrum) collected in Qingdao，achieving an average detection accuracy of 95.6% across varying signal-to-noise ratios. Compared with the frequency-sensitive signal detector，the Swin-Transformer-based protocol recognition method，and the Res-101 detection method，MSCA-S improves accuracy by 0.05%，2.94%，and 6.14%，respectively，while reducing computational costs by 1.53×10¹⁰，1.79×10¹⁰，and 4.59×10¹⁰，respectively.

For the issue of decreased detection performance under low signal-to-noise ratio (SNR) conditions due to insufficient utilization of covariance matrix information in covariance-based eigenvalue algorithms for constructing detection statistics,a novel spectral sensing algorithm based on the ratio of the difference between the maximum and minimum eigenvalues to the harmonic mean of eigenvalues is proposed. This algorithm constructs the detection statistic by incorporating both the extreme eigenvalues and the harmonic mean of eigenvalues from the covariance matrix,thereby more comprehensively exploiting the eigenvalue information within the covariance matrix to enhance the detection capability. Furthermore, a novel approach for calculating the harmonic mean is introduced, leveraging the asymptotic distribution theory of eigenvalues in random matrices. This approach aims to not only improve the accuracy of the decision threshold but also further boost the detection performance. Simulation results demonstrate that the proposed algorithm,without requiring prior knowledge of primary users or channel conditions,achieves a detection probability increase of no less than 10% compared with several classic algorithms at -20 dB SNR.

In order to achieve low-latency and low-energy offshore communication, the dynamic service cache update mechanism is introduced into the complex neural network, and the mobile edge dynamic service caching policy (MEDSCP ) based on double deep Q network (DDQN ) is proposed by cleverly designing the complex neural network structure based on offshore communication scenarios. The policy firstly obtains the optimal offloading decision set through the user terminal task offloading decision game, and then utilizes mobile edge computing(MEC) and dynamic service caching update to reduce the delay and energy cost of task execution in the offshore communication environment, aiming to improve the efficiency of task processing in offshore communication and to expand the development potential of this industry. Simulation experimental results show that the proposed MEDSCP strategy can achieve fast convergence of the algorithm while guaranteeing the training effect,and also effectively reduce the delay-energy weighted sum of offshore communications compared with existing work.

For the optimal feature subset selection and model parameter optimization in ultra-wideband non-line-of-sight(NLOS) recognition，a new NLOS recognition method based on the cross-validation recursive feature elimination algorithm of Light Gradient Boosting Machine(LightGBM) and Optuna parameter tuning is proposed. First，six important features，including the difference between the first path signal and the total received signal power，and the maximum noise，are selected as the optimal feature subset using the recursive feature elimination and cross-validation algorithm. Then，Optuna is used to optimize the hyperparameters of LightGBM model. Line-of-sight and non-line-of-sight feature data is collected，and the Support Vector Machine，Extreme Gradient Boosting algorithm，and parameter-optimized LightGBM model are trained and tested. The results demonstrate that the selected features exhibit excellent discriminative ability，with the optimized LightGBM model achieving a recognition accuracy of 95.28% .

In view of the problems of false detection and missed detection when an unmanned aerial vehicle (UAV) detects targets at different scales,a YOLOv8-FDT UAV algorithm model with a multi-scale fusion mechanism is proposed. First, a dynamic upsampling module is added to the Neck layer of the baseline model to reduce the number of model parameters and improve the real-time performance of the model for target recognition. In addition, in order to enable the entire algorithm model to capture different scale semantic information of the target in the feature fusion stage,adaptive downsampling and depth convolution are integrated to design the feature diffusion pyramid network(FDPN). Finally,experiments on the UAV aerial photography dataset VisDrone2019 show that the mean average precision(mAP) of all categories of the improved model is increased by 6.24% compared with that of the baseline model.

Object detection technology aims to locate and identify specific category targets in images or videos. However，in low-illumination scenarios，problems such as low contrast，blurred boundaries，and noise interference，result in the decline of detection performance. To address this，a Color Channel Transformation Enhancement-based Object Detection (C2TEOD ) algorithm is proposed. Firstly，a color channel transformation module is constructed，and learnable parameters are introduced to transform different color channels，enhancing the flexibility of the enhancement strategy. Then，an image enhancement module is employed to preprocess the input images. This module is jointly optimized with the object detection network using detection loss functions，thereby enabling the enhancement module to learn to generate representations that explicitly facilitate the subsequent detection task. Additionally，a selective self-supervised regression loss is proposed that uses both the original low-illumination images and the enhanced images as inputs to optimize the detection network. According to detection results，the enhancement module is further optimized through self-supervised regression to improve detection performance. Experimental results show that，compared with the baseline method，the mean average precision(mAP) metrics on the Exdark，M3FD，and LLVIP datasets are improved by 2.2%，1.1%，and 0.2% respectively.

In order to further improve the accuracy of human action recognition and fully explore the spatiotemporal features of action sequences, a graph convolution action recognition method based on spatiotemporal feature fusion and attention mechanism is proposed. The spatial attention map convolution is used to refine the topology to capture the correlation features of the joints under different motion types,and the time convolution structure is extended by the time domain multi-scale convolution module to capture the multi-scale time features. A multi-level feature fusion module is constructed,which takes the initial feature and the convolution output feature of the time-domain multiscale graph as the module input,and uses a two-branch structure to obtain the global and local channel features respectively. On this basis,a limb attention mechanism is proposed to divide the human topological structure and calculate the attention weights in the channel dimension respectively to enhance the model's ability to pay attention to local action features. The experimental results show that the recognition accuracy is 93.0% and 96.9% in CS and CV evaluation mode of NTU RGB+D data set,and 89.8% and 91.1% in X-Sub and X-Set evaluation mode of NTU RGB+D 120 data set,respectively. The recognition accuracy is higher than that of ST-GCN,CTR-GCN and other models.

Recently, with the development of deep learning, the field of lightweight object detection has witnessed significant progress. However, mainstream lightweight detectors ignore the extraction of multi-scale semantic information. In addition, these approaches ignore the relationship between deep semantic features and shallow detail features. To relieve above shortcomings, a Pyramid Pooling Enhanced Multi-scale Network(PPMENet) is proposed and an Efficient Pyramid Pooling Block (EPPB) is designed to extract multi-scale deep semantic information,strengthening the feature expression ability of the model. On the other hand, a Cross Semantic Level Interaction Attention Module (CSIAM) is designed to enhance information interaction between features at different semantic levels. Experimental results on the MS COCO 2017 test set show that PPMENet gets 28.0% average precision, only with 2.16×10⁶ model size and 0.97GFLOPs,and achieves inference speed of 218 frame/s. Compared with other methods, PPMENet realizes a good balance between detection accuracy and model execution efficiency.

In order to reduce complexity of construction of indoor positioning fingerprint database and improve the positioning accuracy, an indoor fingerprint positioning algorithm based on matrix completion under the 5G ultra-dense network is proposed. In the offline database construction stage,the algorithm first uses the K-nearest Neighbor(KNN) interpolation method to complete the matrix of part of the fingerprint database to construct a complete database. Secondly,the sparse auto-encoder is used to extract the sparse features of the fingerprint database, and the high-dimensional received signal strength indication (RSSI) signal is reduced. In the online fingerprint matching stage,the weighted KNN algorithm is used to estimate the coordinates of the point to be located. After experimental simulation,the average relative error of the algorithm to reconstruct the fingerprint database is 0.31% . Compared with that of the traditional KNN fingerprint matching algorithm,the average error is reduced by 24.41% .