| Title | Adaptive model training strategy for continuous classification of time series |
| Authors | Sun, Chenxi Li, Hongyan Song, Moxian Cai, Derun Zhang, Baofeng Hong, Shenda |
| Affiliation | Peking Univ, Sch Intelligence Sci & Technol, Beijing, Peoples R China Peking Univ, Key Lab Machine Percept, Minist Educ, Beijing, Peoples R China Peking Univ, Natl Inst Hlth Data Sci, Beijing, Peoples R China Peking Univ, Inst Med Technol, Hlth Sci Ctr, Beijing, Peoples R China |
| Keywords | NEURAL-NETWORKS |
| Issue Date | Feb-2023 |
| Publisher | APPLIED INTELLIGENCE |
| Abstract | 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-sensitive applications require classifying time series continuously. For example, the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. For this demand, we propose a new concept, Continuous Classification of Time Series (CCTS). Different from the existing single-shot classification, the key of CCTS is to model multiple distributions simultaneously due to the dynamic evolution of time series. But the deep learning model will encounter intertwined problems of catastrophic forgetting and over-fitting when learning multi-distribution. In this work, we found that the well-designed distribution division and replay strategies in the model training process can help to solve the problems. We propose a novel Adaptive model training strategy for CCTS (ACCTS). Its adaptability represents two aspects: (1) Adaptive multi-distribution extraction policy. Instead of the fixed rules and the prior knowledge, ACCTS extracts data distributions adaptive to the time series evolution and the model change; (2) Adaptive importance-based replay policy. Instead of reviewing all old distributions, ACCTS only replays important samples adaptive to their contribution to the model. Experiments on four real-world datasets show that our method outperforms all baselines. |
| URI | http://hdl.handle.net/20.500.11897/671258 |
| ISSN | 0924-669X |
| DOI | 10.1007/s10489-022-04433-z |
| Indexed | SCI(E) |
| Appears in Collections: | 机器感知与智能教育部重点实验室 医学部待认领 |
