KLASIFIKASI SINYAL ELEKTROENSEFALOGRAM (EEG) UNTUK MENGENALI JENIS EMOSI MENGUNAKAN MACHINE LEARNING

HIDAYATTULLAH, ROBBY and Rini, Dian Palupi and Rodiah, Desty (2025) KLASIFIKASI SINYAL ELEKTROENSEFALOGRAM (EEG) UNTUK MENGENALI JENIS EMOSI MENGUNAKAN MACHINE LEARNING. Undergraduate thesis, Sriwijaya University.

	Image RAMA_55201_09021182126002_COVER.pdf - Cover Image Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_55201_09021182126002.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021182126002_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_55201_09021182126002_0023027804_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (684kB)
	Text RAMA_55201_09021182126002_0023027804_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (242kB) | Request a copy
	Text RAMA_55201_09021182126002_0023027804_0021128905_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_09021182126002_0023027804_0021128905_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_09021182126002_0023027804_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (142kB) | Request a copy
	Text RAMA_55201_09021182126002_0023027804_0021128905_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (81kB) | Request a copy
	Text RAMA_55201_09021182126002_0023027804_0021128905_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (83kB) | Request a copy
	Text RAMA_55201_09021182126002_0023027804_0021128905_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy

Abstract

Human emotion recognition can be done through facial expressions, voice, body posture, and physiological signals. However, these approaches tend to be subjective as individuals may consciously hide or manipulate their emotional expressions. As a more objective method, electroencephalogram signals can provide a more accurate understanding of a person's emotional state. In this regard, this research aims to develop a machine learning-based emotion classification model using electroencephalogram signals, which record brain electrical activity as a representation of emotional states. The dataset used consists of 2132 rows and 2549 features, including 2548 numerical data and one emotion label, namely positive, negative, and neutral. Three classification algorithms of Decision Tree, K-Nearest Neighbors, and Support Vector Machine are applied with data normalization method to improve the model performance. The experimental results show that Support Vector Machine with Quantile Transformer provides the highest accuracy of 99.76%, followed by Decision Tree 96.95% and K-Nearest Neighbors 96.01%. These findings suggest that machine learning approaches to EEG signals can be an effective method for human emotion classification.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Emotion Recognition, Electroencephalogram Signals, Decision Tree, K-Nearest Neighbors, Support Vector Machine, Data Normalization
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Robby Hidayattullah
Date Deposited:	26 Jun 2025 01:21
Last Modified:	26 Jun 2025 01:21
URI:	http://repository.unsri.ac.id/id/eprint/175983

Actions (login required)

View Item