Proceeding of the Electrical Engineering Computer Science and Informatics
Vol 4: EECSI 2017

Combining Deep Belief Networks and Bidirectional Long Short-Term Memory

Intan Nurma Yulita (Universitas Padjadjaran)
Mohamad Ivan Fanany (Universitas Indonesia)
Aniati Murni Arymurthy (Universitas Indonesia)

Article Info

Publish Date
01 Nov 2017

Abstract

This paper proposes a new combination of Deep Belief Networks (DBN) and Bidirectional Long Short-Term Memory (Bi-LSTM) for Sleep Stage Classification. Tests were performed using sleep stages of 25 patients with sleep disorders. The recording comes from electroencephalography (EEG), electromyography (EMG), and electrooculography (EOG) represented in signal form. All three of these signals processed and extracted to produce 28 features. The next stage, DBN Bi-LSTM is applied. The analysis of this combination compared with the DBN, DBN HMM (Hidden Markov Models), and Bi-LSTM. The results obtained that DBN Bi-LSTM is the best based on precision, recall, and F1 score.

Copyrights © 2017




Citation Download
RIS
EndNote, Reference Manager, ProCite
BibTex
Latex, Jabref
Full PDF
307.775 KB
Original Source
Download Original
Google Scholar
Check in Google Scholar
Journal Info
Proceeding of the Electrical Engineering Computer Science and Informatics
Website

Abbrev

EECSI

Publisher

Institute of Advanced Engineering and Science

Subject

Computer Science & IT Electrical & Electronics Engineering

Description

Proceeding of the Electrical Engineering Computer Science and Informatics publishes papers of the "International Conference on Electrical Engineering Computer Science and Informatics (EECSI)" Series in high technical standard. The Proceeding is aimed to bring researchers, academicians, scientists, ...