IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data
Imbalanced datasets pose significant challenges in the field of machine learning, as they consist of samples where one class (majority) dominates over the other class (minority). Although AdaBoost is a popular ensemble method known for its good performance in addressing various problems, it fails wh...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2023/2176891 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545238166536192 |
|---|---|
| author | SeyedEhsan Roshan Jafar Tanha Farzad Hallaji Mohammad-reza Ghanbari |
| author_facet | SeyedEhsan Roshan Jafar Tanha Farzad Hallaji Mohammad-reza Ghanbari |
| author_sort | SeyedEhsan Roshan |
| collection | DOAJ |
| description | Imbalanced datasets pose significant challenges in the field of machine learning, as they consist of samples where one class (majority) dominates over the other class (minority). Although AdaBoost is a popular ensemble method known for its good performance in addressing various problems, it fails when dealing with imbalanced data sets due to its bias towards the majority class samples. In this study, we propose a novel weighting factor to enhance the performance of AdaBoost (called IMBoost). Our approach involves computing weights for both minority and majority class samples based on the performance of classifier on each class individually. Subsequently, we resample the data sets according to these new weights. To evaluate the effectiveness of our method, we compare it with six well-known ensemble methods on 30 imbalanced data sets and 4 synthetic data sets using ROC, precision-eecall AUC, and G-mean metrics. The results demonstrate the superiority of IMBoost. To further analyze the performance, we employ statistical tests, which confirm the excellence of our method. |
| format | Article |
| id | doaj-art-6b83de44e72a409ea13b8f57bf5d6bbb |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-6b83de44e72a409ea13b8f57bf5d6bbb2025-02-03T07:26:21ZengWileyComplexity1099-05262023-01-01202310.1155/2023/2176891IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced DataSeyedEhsan Roshan0Jafar Tanha1Farzad Hallaji2Mohammad-reza Ghanbari3Faculty of Electrical and Computer EngineeringFaculty of Electrical and Computer EngineeringFaculty of Electrical and Computer EngineeringFaculty of Electrical and Computer EngineeringImbalanced datasets pose significant challenges in the field of machine learning, as they consist of samples where one class (majority) dominates over the other class (minority). Although AdaBoost is a popular ensemble method known for its good performance in addressing various problems, it fails when dealing with imbalanced data sets due to its bias towards the majority class samples. In this study, we propose a novel weighting factor to enhance the performance of AdaBoost (called IMBoost). Our approach involves computing weights for both minority and majority class samples based on the performance of classifier on each class individually. Subsequently, we resample the data sets according to these new weights. To evaluate the effectiveness of our method, we compare it with six well-known ensemble methods on 30 imbalanced data sets and 4 synthetic data sets using ROC, precision-eecall AUC, and G-mean metrics. The results demonstrate the superiority of IMBoost. To further analyze the performance, we employ statistical tests, which confirm the excellence of our method.http://dx.doi.org/10.1155/2023/2176891 |
| spellingShingle | SeyedEhsan Roshan Jafar Tanha Farzad Hallaji Mohammad-reza Ghanbari IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data Complexity |
| title | IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data |
| title_full | IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data |
| title_fullStr | IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data |
| title_full_unstemmed | IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data |
| title_short | IMBoost: A New Weighting Factor for Boosting to Improve the Classification Performance of Imbalanced Data |
| title_sort | imboost a new weighting factor for boosting to improve the classification performance of imbalanced data |
| url | http://dx.doi.org/10.1155/2023/2176891 |
| work_keys_str_mv | AT seyedehsanroshan imboostanewweightingfactorforboostingtoimprovetheclassificationperformanceofimbalanceddata AT jafartanha imboostanewweightingfactorforboostingtoimprovetheclassificationperformanceofimbalanceddata AT farzadhallaji imboostanewweightingfactorforboostingtoimprovetheclassificationperformanceofimbalanceddata AT mohammadrezaghanbari imboostanewweightingfactorforboostingtoimprovetheclassificationperformanceofimbalanceddata |