Chunjing Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Chunjing Xiao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Kevin Chetty
Faculty of Engineering Sciences, University College London, London, WC1E 6BT, UK
1 shared publication - Wei Lu
Department of Cardiovascular Surgery, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou 324000, China
1 shared publication - Wei Yang
College of Computer and Information Engineering, Henan University, Kaifeng, China
1 shared publication - Xianghe Du
The School of Computer and Information Engineering Henan University 475004 Kaifeng China
1 shared publication - Xiaomin Wang
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Xue Jiang
The School of Computer and Information Engineering Henan University 475004 Kaifeng China
1 shared publication
Latest Publications
- Open Access
Boundary-enhanced time series data imputation with long-term dependency diffusion models
Data imputation is crucial for addressing challenges posed by missing values in multivariate time series data across various fields, such as healthcare, traffic, and economics, and has garnered significant attention. Among various methods, diffusion model-based approaches show notable performance improvements. However, existing methods often cause disharmonious boundaries between missing and known regions and overlook long-range dependencies in missing data estimation, leading to suboptimal results. To address these issues, we propose a Diffusion-based time Series Data Imputation (DSDI) framework. We develop a weight-reducing injection strategy that incorporates the predicted values of missing points with reducing weights into the reverse diffusion process to mitigate boundary inconsistencies. Further, we introduce a multi-scale S4-based U-Net, which combines hierarchical information from different levels via multi-resolution integration to capture long-term dependencies. Experimental results demonstrate that our model outperforms existing imputation methods.
Open AccessBoundary-enhanced time series data imputation with long-term dependency diffusion models
Data imputation is crucial for addressing challenges posed by missing values in multivariate time series data across various fields, such as healthcare, traffic, and economics, and has garnered significant attention. Among various methods, diffusion model-based approaches show notable performance improvements. However, existing methods often cause disharmonious boundaries between missing and known regions and overlook long-range dependencies in missing data estimation, leading to suboptimal results. To address these issues, we propose a Diffusion-based time Series Data Imputation (DSDI) framework. We develop a weight-reducing injection strategy that incorporates the predicted values of missing points with reducing weights into the reverse diffusion process to mitigate boundary inconsistencies. Further, we introduce a multi-scale S4-based U-Net, which combines hierarchical information from different levels via multi-resolution integration to capture long-term dependencies. Experimental results demonstrate that our model outperforms existing imputation methods.