Borderline kernel based over-sampling

Áreas de investigación:

• Methodology - Machine learning

Año:

2013

Tipo de publicación:

Artículo en conferencia

Autores:

• Pérez-Ortiz, María
• Gutiérrez, Pedro Antonio
• Hervás-Martínez, César

Volumen:

8073

Título del libro:

8th International Conference on Hybrid Artificial Intelligence Systems (HAIS2013)

Serie:

Lecture Notes on Computer Science (LNCS)

Páginas:

472-481

Organización:

Salamanca (Spain)

Mes:

11th-13th September

ISBN:

978-3-642-40845-8

BibTex:

@conference{BKO2013, author = "Mar{\'i}a P{\'e}rez-Ortiz and Pedro Antonio Guti{\'e}rrez and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "Nowadays, the imbalanced nature of some real-world data is receiving a lot of attention from the pattern recognition and machine learning communities in both theoretical and practical aspects, giving rise to different promising approaches to handling it. However, preprocessing methods operate in the original input space presenting distortions when combined with kernel classifiers, that operate in the feature space induced by a kernel function. This paper explores the notion of empirical feature space (a Euclidean space which is isomorphic to the feature space and therefore preserves its structure) to derive a kernel-based synthetic over-sampling technique based on borderline instances which are considered as crucial for establishing the decision boundary. Therefore, the proposed methodology would maintain the main properties of the kernel mapping while reinforcing the decision boundaries induced by a kernel machine. The results show that the proposal achieves better results than the same borderline over-sampling method applied in the original input space.", booktitle = "8th International Conference on Hybrid Artificial Intelligence Systems (HAIS2013)", doi = "10.1007/978-3-642-40846-5_47", isbn = "978-3-642-40845-8", month = "11th-13th September", organization = "Salamanca (Spain)", pages = "472--481", series = "Lecture Notes on Computer Science (LNCS)", title = "{B}orderline kernel based over-sampling", url = "doi.org/10.1007/978-3-642-40846-5_47", volume = "8073", year = "2013", }

Abstract:

Nowadays, the imbalanced nature of some real-world data is receiving a lot of attention from the pattern recognition and machine learning communities in both theoretical and practical aspects, giving rise to different promising approaches to handling it. However, preprocessing methods operate in the original input space presenting distortions when combined with kernel classifiers, that operate in the feature space induced by a kernel function. This paper explores the notion of empirical feature space (a Euclidean space which is isomorphic to the feature space and therefore preserves its structure) to derive a kernel-based synthetic over-sampling technique based on borderline instances which are considered as crucial for establishing the decision boundary. Therefore, the proposed methodology would maintain the main properties of the kernel mapping while reinforcing the decision boundaries induced by a kernel machine. The results show that the proposal achieves better results than the same borderline over-sampling method applied in the original input space.