In this article, it will be shown that a nonparametric and data-adaptive approach to the variance change point (VCP) detection problem is possible by formulating it as a pattern classification problem. Technical aspects of the VCP detector are discussed, which include its training strategy and selection of proper classification tool.
Bibliographical noteFunding Information:
This work was supported by the Korea Research Foundation Grant funded by Korea Government (KRF 2003-C0008).
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence