Publication:
Studying the perturbation-based oversampling technique for imbalanced classification problems

Date

2023

Authors

Saalim, Mehsun Ihtiyan

Publisher

Acceso abierto / Sarbide irekia
Trabajo Fin de Grado / Gradu Amaierako Lana

Project identifier

Abstract

This study aims to implement, analyze, and compare the effectiveness of a novel technique known as Perturbation-Based Oversampling (POS). This technique is designed to address class imbalance in machine learning by augmenting the minority class instances by strategically perturbing features using a hyperparameter ā€™pā€™. Two additional variations, namely POS 1.0 and POS 2.0, have been proposed as extensions of the original POS approach. Detailed experiments have been conducted across diverse datasets, presenting a comprehensive performance evaluation in terms of precision when compared to a selection of established methods designed to tackle unbalanced classification challenges.

Description

Keywords

Classification, Imbalanced problems, Oversampling, Features, Imbalanced ratio, Perturbation

Department

Faculty/School

Escuela TĆ©cnica Superior de IngenierĆ­a Industrial, InformĆ”tica y de TelecomunicaciĆ³n / Industria, Informatika eta Telekomunikazio Ingeniaritzako Goi Mailako Eskola Teknikoa

Degree

Graduado o Graduada en IngenierĆ­a InformĆ”tica por la Universidad PĆŗblica de Navarra (Programa Internacional), Informatika Ingeniaritzan Graduatua Nafarroako Unibertsitate Publikoan (Nazioarteko Programa)

Doctorate program

item.page.cita

item.page.rights

Los documentos de Academica-e estƔn protegidos por derechos de autor con todos los derechos reservados, a no ser que se indique lo contrario.