TY - GEN
T1 - Combining deep belief networks and bidirectional long short-term memory case study
T2 - 4th International Conference on Electrical Engineering, Computer Science and Informatics, EECSI 2017
AU - Yulita, Intan Nurma
AU - Fanany, Mohamad Ivan
AU - Arymurthy, Aniati Murni
N1 - Funding Information:
The Author thanks to the Indonesian Endowment Fund for Education (LPDP) and Machine Learning and Computer Vision Laboratory, Universitas Indonesia that contributed and supported the study. This work also supported by Center of Excellence for Higher Education Research Grant funded by Indonesian Ministry of Research and Higher Education. This paper also backed by GPU grant from NVIDIA.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/22
Y1 - 2017/12/22
N2 - 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.
AB - 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.
KW - Bidirectional Long Short-Term Memory
KW - Deep Belief Networks
KW - Hidden Markov Models
KW - Long Short-Term Memory
KW - Sleep Stage Classification
UR - http://www.scopus.com/inward/record.url?scp=85046424130&partnerID=8YFLogxK
U2 - 10.1109/EECSI.2017.8239089
DO - 10.1109/EECSI.2017.8239089
M3 - Conference contribution
AN - SCOPUS:85046424130
T3 - International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)
BT - Proceedings - 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics, EECSI 2017
A2 - Rahmawan, Hatib
A2 - Facta, Mochammad
A2 - Riyadi, Munawar A.
A2 - Stiawan, Deris
PB - Institute of Advanced Engineering and Science
Y2 - 19 September 2017 through 21 September 2017
ER -