20 October 2023 in IEEE Sensors Journal
An automatic detection method for surface defects on railway tracks holds significant importance in ensuring the safety of railway transportation. However, in practice, defects on railway tracks exhibit characteristics such as being scarce in number, small in size, and having significant shape variations. Therefore, implementing supervised learning techniques under the constraint of limited labeled data is a major challenge. To address this problem, we propose R-SSRL, a designed framework based on self-supervised representation learning. Inspired by deep neural networks, the R-SSRL is organized based on a convolutional encoder-decoder neural network to segment rail defects. And it uses a novel self-supervised algorithm and a designed defect simulation method to learn possible feature representations of defects from defect-free rail samples. This enables the R-SSRL to utilize defect-free samples that are readily available, to improve model performance with limited labeled data. Experiments on a real-world dataset show that the R-SSRL framework exhibits superior performance in the rail defect detection task, outperforming other models.
1 July 2026 in IEEE Transactions on Mobile Computing
22 June 2026 in ACM Computing Surveys
The rapid advancement of unmanned aerial vehicle (UAV) swarm systems has enabled their deployment in large-scale applications such as disaster response, environmental monitoring, logistics, and communication networks. In these scenarios, effective scheduling and coordination of UAV swarms are critical for mission success, particularly under complex spatiotemporal constraints. This article provides a comprehensive survey of scheduling and planning algorithms for large-scale UAV swarm coordination under spatiotemporal constraints. The unique challenges posed by these constraints are analyzed, and state-of-the-art algorithms, including sampling-based, graph-based, mathematical optimization-based, and learning-based methods, are systematically evaluated. In addition, two representative application domains, sensing and communication, are investigated to demonstrate how spatiotemporal constraints shape algorithm design and performance. Furthermore, this article also explores the key challenges faced by UAV swarms and proposes corresponding future research directions, which are crucial for advancing the development of this field. This survey aims to serve as a foundational reference for researchers and practitioners developing scalable coordination and planning solutions for UAV swarms.