Time pattern reconstruction for classification of irregularly sampled time series

C Sun, H Li, M Song, D Cai, B Zhang, S Hong - Pattern Recognition, 2024 - Elsevier
Abstract Irregularly Sampled Time Series (ISTS) include partially observed feature vectors
caused by the lack of temporal alignment across dimensions and the presence of variable …

A ranking-based cross-entropy loss for early classification of time series

C Sun, H Li, M Song, S Hong - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
Early classification tasks aim to classify time series before observing full data. It is critical in
time-sensitive applications such as early sepsis diagnosis in the intensive care unit (ICU) …

Expanding electrocardiogram abilities for postoperative mortality prediction with deep learning

S Hong, Q Zhao - The Lancet Digital Health, 2024 - thelancet.com
The remarkable evolution of surgical techniques has broadened the scope of treatable
conditions. From interventional procedures to open surgeries, the surgical landscape is …

Curricular and Cyclical Loss for Time Series Learning Strategy

C Sun, H Li, M Song, D Cai, S Hong - arXiv preprint arXiv:2312.15853, 2023 - arxiv.org
Time series widely exists in real-world applications and many deep learning models have
performed well on it. Current research has shown the importance of learning strategy for …

Adaptive model training strategy for continuous classification of time series

C Sun, H Li, M Song, D Cai, B Zhang, S Hong - Applied Intelligence, 2023 - Springer
The classification of time series is essential in many real-world applications like healthcare.
The class of a time series is usually labeled at the final time, but more and more time …

[HTML][HTML] Learning using privileged information with logistic regression on acute respiratory distress syndrome detection

Z Gao, S Cheng, E Wittrup, J Gryak… - Artificial Intelligence in …, 2024 - Elsevier
The advanced learning paradigm, learning using privileged information (LUPI), leverages
information in training that is not present at the time of prediction. In this study, we developed …

Review of Data-centric Time Series Analysis from Sample, Feature, and Period

C Sun, H Li, Y Li, S Hong - arXiv preprint arXiv:2404.16886, 2024 - arxiv.org
Data is essential to performing time series analysis utilizing machine learning approaches,
whether for classic models or today's large language models. A good time-series dataset is …

Temporal Pattern Reconstruction for Classification of Irregularly Sampled Time Series

C Sun, H Li, M Song, D Cai, B Zhang… - Available at SSRN … - papers.ssrn.com
Abstract Irregularly Sampled Time Series (ISTS) include partially observed feature vectors
caused by the lack of temporal alignment across dimensions and the presence of variable …