TY - GEN
T1 - An Investigation of Dynamic Features Influence in ECG-Apnea Using Detrended Fluctuation Analysis
AU - Fahruzi, Iman
AU - Purnama, I. Ketut Eddy
AU - Purnomo, Mauridhi H.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/16
Y1 - 2018/10/16
N2 - Heart Rate Variability(HRV), which can be defined merely as an investigation of the deviation in a time interval of RR between successive cardiac beats(recordings consist of 21326 normal beats event and 6899 apnea beats event) in time duration about 20 minutes ECG-Apnea signal. An Electrocardiogram(ECG), which more information dynamic features, can generate from the extraction process. This paper presents a feature extraction technique in HRV where ECG signal extraction is considered essential to obtain statistical and geometrical HRV for each recording. Dynamic features derived from ECG using two components, HRV analysis, and DFA, were deeply examined and validated its effectiveness to distinguish apnea from the normal signal. Before commencing feature extraction, the ECG signal which is still contaminated by noise needs to be eliminated using pre-processing in the form of noise suppression, and baseline wander removing. Experiment results indicate that suitable for recognizing detail extraction of ECG-Normal and ECG-Apnea events.
AB - Heart Rate Variability(HRV), which can be defined merely as an investigation of the deviation in a time interval of RR between successive cardiac beats(recordings consist of 21326 normal beats event and 6899 apnea beats event) in time duration about 20 minutes ECG-Apnea signal. An Electrocardiogram(ECG), which more information dynamic features, can generate from the extraction process. This paper presents a feature extraction technique in HRV where ECG signal extraction is considered essential to obtain statistical and geometrical HRV for each recording. Dynamic features derived from ECG using two components, HRV analysis, and DFA, were deeply examined and validated its effectiveness to distinguish apnea from the normal signal. Before commencing feature extraction, the ECG signal which is still contaminated by noise needs to be eliminated using pre-processing in the form of noise suppression, and baseline wander removing. Experiment results indicate that suitable for recognizing detail extraction of ECG-Normal and ECG-Apnea events.
KW - ECG
KW - apnea
KW - dfa
KW - dynamic feature
KW - hrv
UR - https://www.scopus.com/pages/publications/85056893516
U2 - 10.1109/ICoIAS.2018.8493925
DO - 10.1109/ICoIAS.2018.8493925
M3 - Conference contribution
AN - SCOPUS:85056893516
T3 - 2018 International Conference on Intelligent Autonomous Systems, ICoIAS 2018
SP - 23
EP - 27
BT - 2018 International Conference on Intelligent Autonomous Systems, ICoIAS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 International Conference on Intelligent Autonomous Systems, ICoIAS 2018
Y2 - 1 March 2018 through 3 March 2018
ER -