Skripsi

KLASIFIKASI JENIS EMOSI MENGGUNAKAN DEEP LEARNING BERDASARKAN SINYAL ELECTROENCEPHALOGRAM

---

Penilaian

---

This research focuses on in-depth exploration and analysis of the application of three types of deep learning, namely Convolutional Neural Networks (CNN), Bidirectional LSTM (BI-LSTM) and Deep Neural Network (DNN). The three models are trained with the same parameters, consisting of three layers, using the Relu activation function, and applying 1 dropout level. In order to compare the performance of the three, experiments were carried out using three dataset groups for training and evaluation of performance. The evaluation includes metrics such as accuracy, recall, F1-Score, and areas under the curve (AUC). The dataset used is EEG Emotion which consists of 2458 unique variables. In terms of performance, BI-LSTM succeeded in outperformed the performance of CNN and DNN in the task of classification of emotional data based on EEG signals. On the other hand, CNN and DNN show excess in the acceleration of the training process compared to BI-LSTM. Although the accuracy of the two methods is almost similar in all data distribution, but in the evaluation of the ROC curve, the BI-LSTM model demonstrates superior with a more optimal curve than CNN and DNN.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407001528	T140554	T1405542024	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1405542024

Publisher

Inderalaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer, Universitas Sriwijaya., 2024

Collation

xiii, 61 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Magister Ilmu Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment