Pengenalan Emosi Berdasarkan Sinyal Ecg Dan Eeg Dari Database Dreamer Menggunakan Machine Learning

Rivaldy, Muhammad Fachrul (2023) Pengenalan Emosi Berdasarkan Sinyal Ecg Dan Eeg Dari Database Dreamer Menggunakan Machine Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211940000032-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (6MB) | Request a copy

Abstract

Perubahan emosi merupakan salah satu faktor yang dapat menyebabkan gangguan kesehatan seseorang. Menurut data, sebanyak 5% dari orang dewasa lanjut usia mengalami gangguan kesehatan mental yang dapat menyebabkan disabilitas dan bahkan gangguan. Oleh karena itu diperlukan sistem pengenalan emosi untuk mencegah dampak buruk dari perubahan emosi yang negatif agar dapat mengurangi gangguan kesehatan mental. Emosi yang digunakan adalah emosi senang, marah, sedih dan tenang. Keempat emosi tersebut diklasifikasikan dalam empat kuadran emosi menurut nilai valence dan \emph{arousal}. Untuk dapat mengenali emosi, salah satu cara yang dapat digunakan adalah dengan menganalisis sinyal ECG (Electrocardiograph) dan EEG (Electroencephalograph). Dengan berkembangnya teknologi pada saat ini, proses menganalisis sinyal ECG dan EEG dapat dilakukan dengan metode Machine Learning. Pada tugas akhir ini, terdapat tiga metode Machine Learning, yaitu Gaussian Naive Bayes Classifier, SVM (Support Vector Machine), dan MLP (Multilayer Perceptron) yang digunakan untuk mengenali emosi berdasarkan sinyal ECG dan EEG yang diambil dari database DREAMER. Penelitian ini menghasilkan nilai akurasi dari masing-masing metode yang digunakan, dengan nilai akurasi tertinggi yaitu 62.917% menggunakan metode MLP.
===================================================================================================================================
Emotional changes are one of the factors that can cause a person's health problems. According to data, as many as 5% of elderly adults experience mental health disorders that can cause disability and even impairment. Therefore an emotion recognition system is needed to prevent the adverse effects of negative emotional changes in order to reduce mental health disorders. The emotions used are happy, angry, sad and calm emotions. The four emotions are classified into four emotional quadrants according to valence and arousal values. To be able to recognize emotions, one way that can be used is to analyze the ECG (Electrocardiograph) and EEG (Electroencephalograph) signals. With the development of technology at this time, the process of analyzing ECG and EEG signals can be done using the Machine Learning method. In this final project, there are three Machine Learning methods, namely Gaussian Naive Bayes Classifier, SVM (Support Vector Machine), and MLP (Multilayer Perceptron) which are used to recognize emotions based on ECG and EEG signals taken from the DREAMER database. This study produces an accuracy value of each method used, with the highest accuracy value of 62.917% using the MLP method.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Emosi, Ecg, Eeg, Machine Learning; Emotion, Ecg, Eeg, Machine Learning
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.758 Software engineering Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > T Technology (General) > T58.5 Information technology. IT--Auditing
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Muhammad Fachrul Rivaldy
Date Deposited:	31 Aug 2023 07:37
Last Modified:	31 Aug 2023 07:37
URI:	http://repository.its.ac.id/id/eprint/102288

Actions (login required)

View Item