Institutional Repository of Vilnius University
Gilieji neuroniniai tinklai ir jų taikymas /
Abstract
dc:descriptionThis bachelor's thesis analyzes and compares methods for addressing class imbalance. The aim of the work is to explore solutions to data imbalance problems in classification tasks using a multilayer perceptron. Several different techniques were applied, such as SMOTE, ADASYN, SMOTE-ENN, Tomek links, and their combinations. The study focused on evaluating how these methods affect classification accuracy, particularly the recognition of minority class instances. Additionally, the impact of network depth, number of neurons, cross-validation, and the removal of individual features on the results was examined. The analysis was carried out using several different datasets. This work is relevant to researchers working on classification tasks involving imbalanced data.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Striogaitė, Augustė,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239029614&prefLang=en_US