A Pruning-Based Approach for Searching Precise and Generalized Region for Synthetic Minority Over-Sampling

Puntumapon, Kamthorn; Waiyamai, Kitsana

doi:10.1007/978-3-642-30220-6_31

Cited by 20 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem leads to misclassification of majority class examples into minority class and increases the false positive rate of the learning algorithms. In order to overcome the SMOTE difficulties, many researches are proposed in literature [6], [18], [25], [30], [42]; however, all these techniques are designed for two-class problems and their performances have not been evaluated on multi-class problems.…”

Section: Related Workmentioning

confidence: 99%

“…The performance of proposed algorithms is evaluated on two-class imbalance problems and the results are compared with SMOTE, Borderline-SMOTE, ROS, and ADASYN algorithms. Although MSYN tries to avoid overgeneralization, it uses all features to select a synthetic example [42].…”

Section: Related Workmentioning

confidence: 99%

“…In order to overcome SMOTE and MSYN difficulties, Puntumapon and Waiyamai proposed a method, named TRIM [42], to select precise seed subsets of particular features. TRIM searches for a precise minority class regions and iteratively filters out irrelevant majority data.…”

Section: Related Workmentioning

confidence: 99%

“…Since in these data sets overlapping between class regions may be very high, the border line examples should be recognized accurately. Borderline-SMOTE also suffers from over-generalization problem [42].…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

To Combat Multi-Class Imbalanced Problems by Means of Over-Sampling Techniques

Abdi

Hashemi

2016

IEEE Trans. Knowl. Data Eng.

321

108

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

To Combat Multi-Class Imbalanced Problems by Means of Over-Sampling Techniques

Abdi

Hashemi

2016

IEEE Trans. Knowl. Data Eng.

321

108

View full text Add to dashboard Cite

“…In [8], we proposed a pruning based procedure for searching a precised and generalized region for synthetic minority over-sampling. This paper adds a second step called the Cluster Connection…”

Section: Introductionmentioning

confidence: 99%

Cluster-Based Minority Over-Sampling for Imbalanced Datasets

Puntumapon

Rakthamamon

Waiyamai

2016

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Kamthorn PUNTUMAPON†a) , Student Member, Thanawin RAKTHAMAMON †b) , Nonmember, and Kitsana WAIYAMAI †c) , Member SUMMARY Synthetic over-sampling is a well-known method to solve class imbalance by modifying class distribution and generating synthetic samples. A large number of synthetic over-sampling techniques have been proposed; however, most of them suffer from the over-generalization problem whereby synthetic minority class samples are generated into the majority class region. Learning from an over-generalized dataset, a classifier could misclassify a majority class member as belonging to a minority class. In this paper a method called TRIM is proposed to overcome the over-generalization problem. The idea is to identify minority class regions that compromise between generalization and overfitting. TRIM identifies all the minority class regions in the form of clusters. Then, it merges a large number of small minority class clusters into more generalized clusters. To enhance the generalization ability, a cluster connection step is proposed to avoid over-generalization toward the majority class while increasing generalization of the minority class. As a result, the classifier is able to correctly classify more minority class samples while maintaining its precision. Compared with SMOTE and extended versions such as Borderline-SMOTE, experimental results show that TRIM exhibits significant performance improvement in terms of F-measure and AUC. TRIM can be used as a preprocessing step for synthetic over-sampling methods such as SMOTE and its extended versions. key words: imbalanced data, cluster-based minority over-sampling, synthetic minority over-sampling

show abstract