25 September 2025 in Expert Systems with Applications
10 February 2025 in IEEE Sensors Journal
The use of drones for image monitoring has gained popularity in railway operations due to several significant advantages. Drones provide high-resolution aerial imagery that covers vast and hard-to-reach areas, enabling comprehensive monitoring of the entire railway network. They offer flexibility and rapid deployment, allowing for real-time data collection and analysis, which is crucial for early detection of potential risks such as landslides, erosion, or track obstructions. Moreover, drones can operate in challenging weather conditions and difficult terrains, ensuring continuous monitoring where traditional methods might fail. However, data collected from drones for railway side slope monitoring is scarce and the railway side slope defect identification and risk assessment have not been fully studied. Furthermore, its frequency is often limited due to operational safety concerns, leading to insufficient data acquisition. To address these limitations, this study innovatively employs diffusion models augmented by large language models (LLM) to enhance training datasets with high-quality synthetic images that encapsulate various defect scenarios. The enhanced YOLO system, integrated with attention mechanisms and LLM-augmented diffusion generation, significantly improves detection accuracy by enabling the model to better generalize under varied real-world conditions. In this study, we collected 600 images from hazardous real-world environments and provided a comprehensive evaluation framework, demonstrating superior performance metrics compared to traditional methods. This approach offers a promising solution for automating and enhancing the reliability of geological hazard monitoring along railway side slopes. The source dataset will be open-sourced at https://github.com/CRH380-CR400/Dataset-of-slope-diseases-along-railway-lines.
11 December 2024 in Space Weather
In this study, we developed a novel deep learning model to predict the disturbance storm time (Dst) index 1–4 hr ahead. We also employed the Monte Carlo (MC) dropout technique to estimate the uncertainty and provide the prediction interval by introducing a recalibration factor. The proposed model achieves excellent scalability by extracting representative embeddings from the Dst index time series through an encoder‐decoder framework and integrating these with external solar wind parameters via a prediction network. We utilized magnetic storm data from 1998 to 2018 to evaluate the performance of the prediction model. Experimental results indicate that the proposed model reduces root mean square errors (RMSE) and improves the coefficient of determination (R2) compared to existing methods. Quantitative uncertainty analysis demonstrates that the prediction interval is reliable in most cases. The percent distribution across test storms by comparing the uncertainty‐based prediction of the minimum peak with the mean prediction indicates the probabilistic forecast model is competitive.