แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Suradej Tretriluxana. Effect of class weights on imbalanced classes in bi-directional LSTM training for sleep apnea classification. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2024.
Effect of class weights on imbalanced classes in bi-directional LSTM training for sleep apnea classification
Name: Ukkrit Jansri
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
ukkrit.ja@kmitl.ac.th
Name: Suradej Tretriluxana
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
suradej.tr@kmitl.ac.th
keyword:
Bidirectional Long Short-Term Memory
LCSH:
Sleep apnea syndromes
-- Diagnosis
LCSH:
Machine learning
Abstract:
Sleep apnea, which is defined as the repetitive
cessations of breathing during sleep, is the common disorder
worldwide. The cost and the process of sleep test to obtain the
polysomnogram is not optimal for sleep apnea screening in the
large population. A deep learning model was developed to
classify the normal and apnea events in a single time-series
signal exported from the US National Institute of Health (NIH)
sponsored database. Our challenge was to train the model with
imbalanced dataset between normal and abnormal respiratory
events. Three different methods, Synthetic Minority Oversampling
Technique (SMOTE), Random Under-Sampling
(RUS), and the Class Weights (CW) were chosen to improve the
model performance over the original data on five selected
signals from polysomnographic dataset. The binary
classification outputs were evaluated by four metrics. Our
results showed (1) Matthews Correlation Coefficient was highest
(MCC = 0.1385) in the Class Weights method on the nasal
airflow signal. (2) Cohens Kappa score, was highest (k = 0.0819)
in SMOTE technique on the abdominal signal, followed by the
Class Weights method on the abdominal signal (k = 0.0687) and
RUS technique on nasal airflow signal (k = 0.0441). (3) F1-score
was highest (F1 = 11.89 %) in SMOTE technique on the
abdominal signal, followed by the Class Weights method on
nasal airflow signal (F1 = 11.17 %) and RUS technique on nasal
airflow signal (F1 = 9.16 %). The findings suggest that the Class
Weights method on nasal airflow and the Class Weights method
on abdominal signal were the two combinations to be used in the
DL model
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2024
Modified:
2025-01-24
Issued:
2025-01-24
บทความ/Article
application/pdf
BibliograpyCitation :
In Rajamangala University of Technology Krungthep. 12th International Electrical Engineering Congress (iEECON 2024) (pp.323-328). Bangkok : Rajamangala University of Technology Krungthep
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.017744 วินาที
Ukkrit Jansri
| Title | Contributor | Type |
|---|---|---|
| Effect of class weights on imbalanced classes in bi-directional LSTM training for sleep apnea classification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ukkrit Jansri;Suradej Tretriluxana | บทความ/Article | |
| Effect of resampling techniques on deep learning model training in sleep apnea classification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ukkrit Jansri;Suradej Tretriluxana | บทความ/Article |
Suradej Tretriluxana
| Title | Contributor | Type |
|---|---|---|
| Effect of class weights on imbalanced classes in bi-directional LSTM training for sleep apnea classification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ukkrit Jansri;Suradej Tretriluxana | บทความ/Article | |
| Effect of resampling techniques on deep learning model training in sleep apnea classification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ukkrit Jansri;Suradej Tretriluxana | บทความ/Article |