Class-incremental learning for time series: benchmark and evaluation

Class-incremental learning for time series: benchmark and evaluation

Real-world environments are inherently non-stationary, frequently introducing new classes over time. This is especially common in time series classification, such as the emergence of new disease classification in healthcare or the addition of new activities in human activity recognition. In such cas...

Full description

Bibliographic Details
Main Authors: Qiao, Zhongzheng, Pham, Quang, Cao, Zhen, Hoang, H. Le, Suganthan, P. N., Jiang, Xudong, Ramasamy, Savitha
Other Authors: School of Electrical and Electronic Engineering
Format: Conference Paper
Language:English
Published: 2024
Subjects:
Computer and Information Science
Class-incremental Learning
Continual Learning
Time series classification
Online Access:https://hdl.handle.net/10356/178334

Internet

https://hdl.handle.net/10356/178334

Similar Items