Xiaoying Wang

In the Internet of Vehicles (IoV) environment, data among vehicles exhibits Non-Independent Identical Distribution (Non-IID) characteristics due to the diversity of vehicle types, on-board hardware, and user preferences. In addition, when users request location-based services (LBS), they face the risk of privacy leakage and have higher Quality of Service (QoS) requirements. Therefore, personalized location privacy protection has become an urgent issue. Most existing research focuses on protecting overall privacy but lacks personalized strategies to address varying user needs and struggles with handling Non-IID data. To address these challenges, this paper proposes a personalized hierarchical federated learning framework (PHFedDA) based on heterogeneous data aggregation. First, we apply a personalized location privacy budget allocation scheme (PLPB) to vehicle trajectories, and a quality assessment model is proposed for evaluating the accuracy of vehicle trajectory aggregation, through which an effective balance between aggregation accuracy and privacy protection is achieved. Then, we design a personalized hierarchical federated learning algorithm to effectively deal with the Non-IID data problem caused by the differences in vehicle end-user preferences. Finally, through simulation experiments, our PHFedDA framework achieves an 8.74% improvement in aggregation accuracy over the best-performing baseline scheme DSLP. Additionally, the model accuracy improves by 7.52% compared to the top-performing baseline scheme SCAFFOLD. Compared to other baseline schemes mentioned in this paper, PHFedDA demonstrates significant advantages in security and handling data heterogeneity.

In recent years, deep neural networks, including Convolutional Neural Networks, Transformers, and State Space Models, have achieved significant progress in Remote Sensing Image (RSI) Super-Resolution (SR). However, existing SR methods typically overlook the complementary relationship between global and local dependencies. These methods either focus on capturing local information or prioritize global information, which results in models that are unable to effectively capture both global and local features simultaneously. Moreover, their computational cost becomes prohibitive when applied to large-scale RSIs. To address these challenges, we introduce the novel application of Receptance Weighted Key Value (RWKV) to RSI-SR, which captures long-range dependencies with linear complexity. To simultaneously model global and local features, we propose the Global-Detail dual-branch structure, GDSR, which performs SR by paralleling RWKV and convolutional operations to handle large-scale RSIs. Furthermore, we introduce the Global-Detail Reconstruction Module (GDRM) as an intermediary between the two branches to bridge their complementary roles. In addition, we propose the Dual-Group Multi-Scale Wavelet Loss, a wavelet-domain constraint mechanism via dual-group subband strategy and cross-resolution frequency alignment for enhanced reconstruction fidelity in RSI-SR. Extensive experiments under two degradation methods on several benchmarks, including AID, UCMerced, and RSSRD-QH, demonstrate that GSDR outperforms the state-of-the-art Transformer-based method HAT by an average of 0.09 dB in PSNR, while using only 63% of its parameters and 51% of its FLOPs, achieving an inference speed 3.2 times faster.

Deep learning for precipitation forecasting remains constrained by complex meteorological factors affecting accuracy. To address this issue, this paper proposes TransMambaCNN, which is a spatiotemporal transformer network fusing state-space models and CNNs for short-term precipitation forecasting. The core of the model employs a Convolutional State-Space Module (C-SSM), which efficiently extracts spatiotemporal features from multi-source meteorological variables by replacing the self-attention mechanism in the Vision Transformer (ViT) with an Attentive State-Space Module (ASSM) and augmenting its feature extraction capacity with integrated depthwise convolution. Its dual-branch architecture consists of a global branch, where C-SSM captures long-range dependencies and global spatiotemporal patterns, and a local branch, which leverages multi-scale convolutions based on SimVP’s Inception structure to extract fine-grained local features. The deep fusion of these dual branches significantly enhances spatiotemporal feature representation.Experiments demonstrate that in southeastern China and adjacent marine areas (period of high precipitation: April–September), TransMambaCNN achieves a 13.38% and 47.67% improvement in Threat Score (TS) over PredRNN at thresholds of ≥25 mm and ≥50 mm, respectively. In the Qinghai Sanjiangyuan region of western China (a precipitation-scarce area), TransMambaCNN’s TS score surpasses SimVP by 11.86 times at the ≥25 mm threshold.

The inability of existing super-resolution methods to jointly model short-range and long-range spatial dependencies in remote sensing imagery limits reconstruction efficacy. To address this, we propose LSTMConvSR, a novel framework inspired by top-down neural attention mechanisms. Our approach pioneers an LSTM-first–CNN-next architecture. First, an LSTM-based global modeling stage efficiently captures long-range dependencies via downsampling and spatial attention, achieving 80.3% lower FLOPs and 11× faster speed. Second, a CNN-based local refinement stage, guided by the LSTM’s attention maps, enhances details in critical regions. Third, a top-down fusion stage dynamically integrates global context and local features to generate the output. Extensive experiments on Potsdam, UAVid, and RSSCN7 benchmarks demonstrate state-of-the-art performance, achieving 33.94 dB PSNR on Potsdam with 2.4× faster inference than MambaIRv2.