Combining deep belief networks and bidirectional long short-term memory case study: Sleep stage classification

Intan Nurma Yulita, Mohamad Ivan Fanany, Aniati Murni Arymurthy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings - 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics, EECSI 2017
EditorsHatib Rahmawan, Mochammad Facta, Munawar A. Riyadi, Deris Stiawan
PublisherInstitute of Advanced Engineering and Science
ISBN (Electronic)9781538605486
DOIs
Publication statusPublished - 22 Dec 2017
Event4th International Conference on Electrical Engineering, Computer Science and Informatics, EECSI 2017 - Yogyakarta, Indonesia
Duration: 19 Sept 201721 Sept 2017

Publication series

NameInternational Conference on Electrical Engineering, Computer Science and Informatics (EECSI)
Volume2017-December
ISSN (Print)2407-439X

Conference

Conference4th International Conference on Electrical Engineering, Computer Science and Informatics, EECSI 2017
Country/TerritoryIndonesia
CityYogyakarta
Period19/09/1721/09/17

Keywords

  • Bidirectional Long Short-Term Memory
  • Deep Belief Networks
  • Hidden Markov Models
  • Long Short-Term Memory
  • Sleep Stage Classification

Fingerprint

Dive into the research topics of 'Combining deep belief networks and bidirectional long short-term memory case study: Sleep stage classification'. Together they form a unique fingerprint.

Cite this