Skripsi

PERBANDINGAN LOGISTIC REGRESSION DAN XGBOOST DALAM KLASIFIKASI KONDISI MENTAL BERBASIS SINYAL EEG

---

Accurate mental state identification is important across various fields, and EEG is a biomedical signal widely used for this purpose as it can directly and non-invasively record brain electrical activity. However, the complex, nonlinear, and high-dimensional characteristics of EEG signals require effective classification methods. This study aims to implement and compare the performance of Logistic Regression and XGBoost algorithms in classifying mental states based on EEG signals, using the EEG Brainwave Dataset Mental State consisting of 2,479 data points, 989 features, and three mental state classes: relaxed, neutral, and concentrating. The research stages include feature selection using Mutual Information-SelectKBest (200 best features), data splitting with stratified split (80:20), and evaluation using accuracy, precision, recall, and F1-score. The results show that the best Logistic Regression configuration (C=0.1, lbfgs solver) achieved an accuracy of 86.05%, while the best XGBoost configuration (n_estimators=200, max_depth=5, learning_rate=0.1) achieved an accuracy of 92.39%. XGBoost proved to provide superior classification performance compared to Logistic Regression across all evaluation indicators.

---

Availability

Detail Information

Series Title

-

Call Number

T2010352026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiv, 108 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Algoritma Mesin

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment