Publications by authors named "Yuming Shang"
Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of input sequences for task performance, necessitating additional neural network layers to enhance feature representation, which in turn increases computational expenses. These approaches have also failed to fully leverage the comprehensive knowledge inherent within the source code and its associated text, potentially limiting classification efficacy.
View Article and Find Full Text PDFArticle Synopsis
- - The Middle Route of China's South-to-North Water Diversion Project is crucial for providing drinking water to North China, but there's insufficient understanding of hydrodynamics, water quality, and ecological interactions in its early operational phase.
- - This study analyzes the ecological changes in the main canal's environment, specifically looking at factors impacting algae growth, using principal component analysis to assess water quality and algae distribution.
- - Findings reveal that water quality varies along the canal, with COD and algal density increasing from south to north, while dissolved oxygen decreases; algal density is highest in summer and lowest in winter, with different water flow conditions affecting algae distribution.
The Middle Route of the South-to-North Water Diversion Project of China (MRSNWDPC), the longest trans-basin water diversion project in the world, has been in operation for over 6 years. The water quality of this mega hydro-project affects the safety of more than 60 million people and the health of an ecosystem over 160,000 km. Abnormal algal proliferation can cause water quality deterioration, eutrophication, and hydro-project operation issues.
View Article and Find Full Text PDF