en-es
en-fr
en-sl
en
0.25
0.5
0.75
1.25
1.5
1.75
2
Resampling Approaches for Handling Imbalanced Regression Tasks
Published on Jan 23, 20172299 Views
Imbalanced classification tasks have been studied by the research community for a long time. Numerous problems have been identified with standard approaches and new proposals have been put forward fo
Related categories
Chapter list
Resampling Strategies for Regression00:00
Predictive Modeling with Imbalanced Distributions00:19
Imbalanced Distributions in Regression01:42
Problem Definition - 103:19
Problem Definition - 204:03
Imbalanced Domains07:05
Problems created by imbalanced distributions09:16
A Taxonomy of strategies for handling Imbalanced Domains10:44
Strategies for Handling Imbalanced Domains - 111:29
Strategies for Handling Imbalanced Domains - 212:22
Strategies for Handling Imbalanced Domains - 313:03
Relevance Function13:47
Resampling Strategies for Regression Tasks14:46
The R Package UBL15:20
Random Undersampling - 115:51
Random Undersampling in UBL - 116:54
Impact of different settings of Random Undersampling - 118:43
Random Oversampling - 219:59
Random Oversampling using UBL - 220:33
Impact of different settings of Random Undersampling - 220:39
Introduction of Gaussian Noise20:57
Introduction of Gaussian Noise in UBL22:00
Impact of different settings of Gaussian Noise22:06
Further examples with Gaussian Noise22:18
The impact of changing the parameter pert22:31
SmoteR - SMOTE for Regression Tasks22:42
Using the SmoteR Algorithm24:36
The impact of the parameters on SmoteR25:19
WEighted Relevance-based Combination Strategy (WERCS)25:31
WERCS in UBL27:10
The impact of the parameters on WERCS - 128:01
The impact of the parameters on WERCS - 228:06
Experimental Analysis of the Methods28:16
A summary of the results29:43
Summary/Conclusions/Recommendations31:07