PERBANDINGAN ALGORITMA XGBOOST, LIGHTGBM DAN RANDOM FOREST UNTUK KLASIFIKASI SINYAL EEG DALAM PENGENALAN EMOSI

ANISYAHFITRI, YOLENDRI and Rini, Dian Palupi and Marieska, Mastura Diana (2024) PERBANDINGAN ALGORITMA XGBOOST, LIGHTGBM DAN RANDOM FOREST UNTUK KLASIFIKASI SINYAL EEG DALAM PENGENALAN EMOSI. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282126075.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021282126075_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (851kB)
	Text RAMA_55201_09021282126075_0023027804_0021038607_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (545kB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (474kB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (371kB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (142kB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (172kB) | Request a copy
	Text RAMA_55201_09021282126075_0023027804_0021038607_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy

Abstract

Emotion recognition based on Electroencephalogram (EEG) signals has become an intriguing research field in human-computer interaction and medical applications with the potential to provide deep insights into patients' mental conditions. This study aimed to compare the performance of three machine learning algorithms, XGBoost, LightGBM, and Random Forest, in classifying EEG signals for emotion recognition. The research was conducted by testing these algorithms using parameter variations such as n_estimators, learning_rate, and max_depth, and different data splits. The evaluation method involved performance metrics including accuracy, precision, recall, and F1-score. Results showed that all three algorithms achieved maximum accuracy of 1.00, with unique characteristics: XGBoost excelled in performance stability, LightGBM stood out in computational efficiency, and Random Forest displayed balanced evaluation metrics. This research contributes to the development of EEG signal classification methods for emotion recognition using machine learning approaches, with recommendations for algorithm selection based on specific research needs while considering potential overfitting in large training datasets.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Klasifikasi Sinyal EEG, Pengenalan Emosi, XGBoost, LightGBM, Random Forest
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Yolendri Anisyahfitri
Date Deposited:	07 Jan 2025 02:35
Last Modified:	07 Jan 2025 02:35
URI:	http://repository.unsri.ac.id/id/eprint/162747

Actions (login required)

View Item