Naslov
Machine Learning Methods for EEG Signal Classification in Affective Disorders

Autori
Skorupan, Ivan

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, preddiplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
30.06

Godina
2020

Stranica
58

Mentor
Cifrek, Mario

Neposredni voditelj
Friganović, Krešimir

Ključne riječi
EEG ; electroencephalography ; machine learning ; imbalanced dataset ; affective disorder ; support vector machine ; k-nearest neighbors algorithm ; AdaBoost

Sažetak
Imbalanced datasets are often found in medical praxis. Classical machine learning algorithms suffer from overfitting on imbalanced datasets, which is why special methods are needed to improve model performance. In this thesis, EEG signal features classification by medical diagnoses was performed on several tables using the support vector machine, k-nearest neighbors, random forest and AdaBoost models. Classification results were analyzed and it was shown that the AdaBoost and linear kernel support vector machine models show the most potential in majority of the examples.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Interdisciplinarne tehničke znanosti

POVEZANOST RADA