Membaca Sinyal Electroencephalogram (EEG) Dalam Menangkap Tingkat Emosi (Berdasarkan Ontologi)

Yudo Devianto; Eko Sediyono; Sri Yulianto Joko Prasetyo; Danny Manongga

doi:10.30998/faktorexacta.v17i2.20878

Membaca Sinyal Electroencephalogram (EEG) Dalam Menangkap Tingkat Emosi (Berdasarkan Ontologi)

Yudo Devianto^(1*), Eko Sediyono⁽²⁾, Sri Yulianto Joko Prasetyo⁽³⁾, Danny Manongga⁽⁴⁾

(1) Universitas Mercu Buana
(2) Universitas Kristen Satya Wacana
(3) Universitas Kristen Satya Wacana
(4) Universitas Kristen Satya Wacana
(*) Corresponding Author

Abstract

Philosophically based EEG (electroencephalography) signal data processing is an engaging interdisciplinary approach and opens up new perspectives in understanding brain function. In this context, it is necessary to examine data from a technical or biological point of view and consider its metaphysical, epistemological and even ontological aspects. Ontology is a branch of metaphysics that deals with objects and the types of objects that exist according to one's metaphysical (or even physical) theory, their properties, and their relationship. This article attempts to provide a philosophical view of science based on ontology for processing EEG signal data, the data source of which is taken from brain waves. With the results of trials using the Artificial Neural Network (ANN) classification, an accuracy value of 46.73 was obtained. The Convolutional Neural Network (CNN) algorithm can also be used to process EEG signal data to determine a person's emotional level; this is proven in research results; although the overall accuracy of emotion recognition has increased significantly, several problems cause low accuracy in the DEAP and DREAMER data sets. There are also results of other experiments carried out using CNN, and the experimental results show that the weight of channels related to emotions is greater than that of different channels. The Continuous Capsule Network (CCN) algorithm and Deep Neural Network (DNN) algorithm can also be used to process EEG signal data to determine the level of emotion.

Full Text:

PDF (Indonesian)

References

S. Okasha, Philosophy of Science Very short Introduction, vol. 7, no. 9. 2016.

W. J. Rapaport, Philosophy of Computer Science. New York, USA, 2019.

M. Danuri, “Perkembangan Dan Transformasi Teknologi Digital,” INFOKAM, vol. XV, no. II, pp. 116–123, 2019.

R. Aviana and F. Fatichatul hidayah, “PENGARUH TINGKAT KONSENTRASI BELAJAR SISWA TERHADAP DAYA PEMAHAMAN MATERI PADA PEMBELAJARAN KIMIA DI SMA NEGERI 2 BATANG,” J. Pendidik. Sains, vol. 03, no. 01, pp. 1–4, 2015.

R. Karmila, E. C. Djamal, and D. Nursantika, “Identifikasi Tingkat Konsentrasi Dari Sinyal EEG Dengan Wavelet dan Adaptive Backpropagation,” Semin. Nas. Apl. Teknol. Inf., vol. 0, no. 0, p. 2016, 2016.

I. M. A. Wirawan, R. Wardoyo, D. Lelono, and S. Kusrohmaniah, “Continuous Capsule Network Method for Improving Electroencephalogram-Based Emotion Recognition,” Emerg. Sci. J., vol. 7, no. 1, pp. 116–134, 2023.

M. A. Hendrawan, “Deteksi Kelelahan Mental Dengan Menggunakan Sinyal Eeg Satu Kanal,” J. Sist. Inf. dan Bisnis Cerdas, vol. 14, no. 2, pp. 78–87, 2021.

F. Siddiqui et al., “Deep Neural Network for EEG Signal-Based Subject-Independent Imaginary Mental Task Classification,” Diagnostics, vol. 13, no. 4, pp. 1–16, 2023.

D. P. Pangestu and E. C. Djamal, “Identifikasi Sinyal Elektroensephalogram Berdasarkan Perhatian Menggunakan Wavelet dan Support Vector Machine,” Pros. SNIJA, pp. 229–232, 2015.

I. Hussain et al., “Quantitative Evaluation of EEG-Biomarkers for Prediction of Sleep Stages,” MDPI SENSORS, vol. 22, no. 8, pp. 1–15, 2022.

J. F. Indonesia, N. F. Saminan, and U. P. Indonesia, “Frekuensi Gelombang Otak dalam Menangkap Ilmu Imajinasi dan Realita ( Berdasarkan Ontologi ),” vol. 3, no. 2, pp. 40–47, 2020.

S. Sanei and J. A. Chambers, EEG SIGNAL PROCESSING. UK: John Wiley & Sons, Ltd, 2007.

K. Sharma, A. Naik, and P. Patel, “Study of Artificial Neural Network,” vol. 2, no. 4, pp. 46–48, 2015.

A. F. Zakiyyah, “Klasifikasi Emosi Untuk Mengetahui Pengalaman Emosional Melalui Sinyal EEG Menggunakan Algoritma Artificial Neural Network,” vol. 3, no. 2, pp. 40–43, 2021.

I. M. A. Wirawan, R. Wardoyo, D. Lelono, and S. Kusrohmaniah, “Modified Weighted Mean Filter to Improve the Baseline Reduction Approach for Emotion Recognition,” Emerg. Sci. J., vol. 6, no. 6, pp. 1255–1273, 2022.

L. Fan, H. Shen, F. Xie, J. Su, Y. Yu, and D. Hu, “DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 1727–1736, 2022.

DOI: http://dx.doi.org/10.30998/faktorexacta.v17i2.20878