Abstract
One of widespread breath disruption that takes place during sleep is apnea, during this anomaly people are not able to get enough oxygen. The article describes method for breathing analyses that is based on neural network that allows recognition of breath patterns and predicting anomalies that may occur. Class of machine learning algorithms includes lots of models, widespread feed forward networks are able to solve task of classification, but are not quite suitable for processing time-series data. The paper describes results of teaching and testing several types of dynamic or recurrent networks: NARX, Elman, distributed and focused time delay.
| Original language | English |
|---|---|
| Title of host publication | Communications in Computer and Information Science |
| Publisher | Springer Verlag |
| Pages | 556-567 |
| Number of pages | 12 |
| Volume | 466 CCIS |
| ISBN (Print) | 9783319118536 |
| DOIs | |
| Publication status | Published - 2014 |
| Event | 11th Joint Conference on Knowledge-Based Software Engineering, JCKBSE 2014 - Volgograd, Russian Federation Duration: 17 Sep 2014 → 20 Sep 2014 |
Publication series
| Name | Communications in Computer and Information Science |
|---|---|
| Volume | 466 CCIS |
| ISSN (Print) | 18650929 |
Other
| Other | 11th Joint Conference on Knowledge-Based Software Engineering, JCKBSE 2014 |
|---|---|
| Country | Russian Federation |
| City | Volgograd |
| Period | 17.9.14 → 20.9.14 |
Fingerprint
Keywords
- breath pattern
- recurrent neural network
- Sleep apnea
ASJC Scopus subject areas
- Computer Science(all)
Cite this
Sleep Apnea Detection Based on Dynamic Neural Networks. / Devjatykh, Dmitry; Gerget, Olga Mikhaylovna; Berestneva, Olga G.
Communications in Computer and Information Science. Vol. 466 CCIS Springer Verlag, 2014. p. 556-567 (Communications in Computer and Information Science; Vol. 466 CCIS).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Sleep Apnea Detection Based on Dynamic Neural Networks
AU - Devjatykh, Dmitry
AU - Gerget, Olga Mikhaylovna
AU - Berestneva, Olga G.
PY - 2014
Y1 - 2014
N2 - One of widespread breath disruption that takes place during sleep is apnea, during this anomaly people are not able to get enough oxygen. The article describes method for breathing analyses that is based on neural network that allows recognition of breath patterns and predicting anomalies that may occur. Class of machine learning algorithms includes lots of models, widespread feed forward networks are able to solve task of classification, but are not quite suitable for processing time-series data. The paper describes results of teaching and testing several types of dynamic or recurrent networks: NARX, Elman, distributed and focused time delay.
AB - One of widespread breath disruption that takes place during sleep is apnea, during this anomaly people are not able to get enough oxygen. The article describes method for breathing analyses that is based on neural network that allows recognition of breath patterns and predicting anomalies that may occur. Class of machine learning algorithms includes lots of models, widespread feed forward networks are able to solve task of classification, but are not quite suitable for processing time-series data. The paper describes results of teaching and testing several types of dynamic or recurrent networks: NARX, Elman, distributed and focused time delay.
KW - breath pattern
KW - recurrent neural network
KW - Sleep apnea
UR - http://www.scopus.com/inward/record.url?scp=84907339520&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84907339520&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-11854-3_48
DO - 10.1007/978-3-319-11854-3_48
M3 - Conference contribution
AN - SCOPUS:84907339520
SN - 9783319118536
VL - 466 CCIS
T3 - Communications in Computer and Information Science
SP - 556
EP - 567
BT - Communications in Computer and Information Science
PB - Springer Verlag
ER -