SVBO: Support Vector-Based Oversampling for Handling Class Imbalance in k-NN
Publish place: 20th Iranian Conference on Electric Engineering
Publish Year: 1391
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,296
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEE20_034
تاریخ نمایه سازی: 14 مرداد 1391
Abstract:
We propose a novel algorithm for handling class imbalance in the k-NN classifier. Class imbalance is a problem occurring in some valuable data such as medical diagnosis,fraud detection, oil spills and etc. The problem influences all supervised classification algorithms therefore a large amount ofresearch is being done. We tackle the problem by preprocessing the data using oversampling techniques. A two phase algorithm, based on Support Vector Data Description (SVDD) is proposed.SVDD is a tool for data description. In our approach we firstly describe data from the minority class i.e. the class with lessdata using SVDD. This is followed by oversampling of the support vectors, which is suitable for k-NN. We evaluate ourmethod using real world datasets with different imbalance ratios and compare it with four other oversampling methods namely SMOTE, Borderline SMOTE, random oversampling and cluster based sampling. The results show that the proposed algorithm is a suitable preprocessing method for the k-NN classifier
Keywords:
Authors
Adel Ghazikhani
PhD student, Ferdowsi University of Mashhad and Lecturer at Imam Reza University Mashhad
Reza Monsefi
Assistant professor, Computer Engineering Department, Ferdowsi University of Mashhad
Hadi Sadoghi Yazdi
Associate professor, Computer Engineering Department, Ferdowsi University of Mashhad
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :