Incremental Learning of Concept Drift from Streaming Imbalanced Data
Citations
1,448 citations
905 citations
Cites background or methods from "Incremental Learning of Concept Dri..."
...…both obstacles from the point of view of preprocessing (Nguyen et al., 2011; He & Chen, 2011; Wang, Minku, & Yao, 2015), particularly using SMOTE (Ditzler & Polikar, 2013), and/or cost-sensitive learning via ensembles of classifiers (Mirza, Lin, & Liu, 2015; Ghazikhani, Monsefi, & Sadoghi Yazdi,…...
[...]
...As we mentioned in Section 4.1, Ditzler and Polikar (2013) integrated the SMOTE preprocessing within a novel ensemble boosting approach that applies distribution weights among the instances depending on their distribution at each time step....
[...]
...The first is Learn++.NSE-SMOTE (Ditzler & Polikar, 2013), which is an extension of Learn++.SMOTE (Ditzler et al., 2010)....
[...]
757 citations
Cites background or methods from "Incremental Learning of Concept Dri..."
...Another example of passive online learning ensemble approach for non-stationary environments is Stanley’s Concept Drift Committee (CDC) [168] ....
[...]
...CDC (Concept Drift with MOTE), which employs oversampling of the minority class....
[...]
...The current use of AUC for data streams has been limited only to estimations on periodical holdout sets [77] or entire streams of a limited length [44]....
[...]
...[77] T.R. Hoens , R. Polikar , N.V. Chawla , Learning from streaming data with concept drift and imbalance: an overview, Prog....
[...]
...[50] R. Elwell , R. Polikar , Incremental learning of concept drift in nonstationary environments, IEEE Trans....
[...]
640 citations
Cites background from "Incremental Learning of Concept Dri..."
...learning algorithm for imbalanced-nonstationary data streams that does not require access to historical data [106], [107]....
[...]
557 citations
Cites methods from "Incremental Learning of Concept Dri..."
...[119] presented two ensemble methods for learning under concept drift with imbalanced class....
[...]
References
15,813 citations
11,512 citations
10,306 citations
6,320 citations
1,790 citations
"Incremental Learning of Concept Dri..." refers background in this paper
...’s concept adapting very fast decision tree (CVFDT) [20] or Cohen et al....
[...]
...Many of these approaches also include a FLORA-like windowing mechanism, including Hulten et al.’s concept adapting very fast decision tree (CVFDT) [20] or Cohen et al.’s incremental online-information network (IOLIN) algorithms [21], [22]....
[...]