- Title
- Classification under streaming emerging new classes : A solution using completely-random trees
- Creator
- Mu, Xin; Ting, Kaiming; Zhou, Zhi-Hua
- Date
- 2017
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/163309
- Identifier
- vital:12837
- Identifier
-
https://doi.org/10.1109/TKDE.2017.2691702
- Identifier
- ISBN:1041-4347
- Abstract
- This paper investigates an important problem in stream mining, i.e., classification under streaming emerging new classes or SENC. The SENC problem can be decomposed into three subproblems: detecting emerging new classes, classifying known classes, and updating models to integrate each new class as part of known classes. The common approach is to treat it as a classification problem and solve it using either a supervised learner or a semi-supervised learner. We propose an alternative approach by using unsupervised learning as the basis to solve this problem. The proposed method employs completely-random trees which have been shown to work well in unsupervised learning and supervised learning independently in the literature. The completely-random trees are used as a single common core to solve all three subproblems: unsupervised learning, supervised learning, and model update on data streams. We show that the proposed unsupervised-learning-focused method often achieves significantly better outcomes than existing classification-focused methods.
- Relation
- IEEE Transactions on Knowledge and Data Engineering Vol. 29, no. 8 (2017), p. 1605-1618
- Rights
- © 2017 IEEE
- Rights
- This metadata is freely available under a CCO license
- Subject
- Data stream; Emerging new class; Ensemble method; Anomaly detection; Completely-random trees
- Full Text
- Reviewed
- Hits: 888
- Visitors: 1080
- Downloads: 210
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE2 | Submitted version | 1 MB | Adobe Acrobat PDF | View Details Download |