17 January 2025 in IEEE Internet of Things Journal
With the rapid progress made in aerial computing technology and the increased popularity of fifth-generation (5G) networks, uncrewed aerial vehicles (UAVs) have been playing a crucial role in real-time data collection, processing, and transmission. However, due to the diversity in traffic generated by UAVs in various mission scenarios, there is a significant challenge posed in traffic classification. Therefore, a novel traffic classification model is proposed in this article on the basis of the spatial attention-enhanced convolutional neural network (SAE-CNN). This model proves effective in improving classification accuracy and latency, particularly in the context of various 5G services, such as enhanced mobile broadband (eMBB), ultrareliable low-latency communication (URLLC), and Internet service. Also, a 5G heterogeneous network platform is built to collect UAV-related aerial computing data, with extensive experiments performed to verify the superior performance of the SAE-CNN model compared to other state-of-the-art methods. The experimental results demonstrate that the proposed approach enables effective traffic management and classification for the application of UAV in complex 5G environments.
24 May 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Feature representation is a crucial issue in multimodal image registration. The handcrafted features extracted by traditional methods are highly sensitive to nonlinear radiation differences, while supervised learning methods are limited by deficient labeled samples in the remote sensing field. Therefore, this paper proposes a consistency feature representation learning method for multimodal image registration, which involves mapping data into a common feature space to realize the accurate alignment of remote sensing images. First, a contrastive network with a spatial attention mechanism is driven to enhance the capability to highlight high-level features of images. Second, a positive sample augmentation strategy is implemented with contrastive loss, which helps the model learn the inherent features better, and imposes constraints on the sample similarity to optimize the feature projection. Finally, a multimodal image registration framework is proposed to enhance the stability of feature matching. The proposed framework achieves accurate feature extraction and consistency feature description for multimodal images, ensuring robustness against nonlinear radiometric differences. Experimental results demonstrate that the proposed method obtains more reliable registration results on the SEN1-2 dataset. Furthermore, the proposed algorithm achieves superior performance on data from other modalities, indicating strong generalization ability.