BCG Signal Quality Assessment Based on Time-Series Imaging Methods
Sensors · 24.11.2023 · 23 (23) · 9382
DOI: 10.3390/s23239382 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 24.11.2023. Verfasst von Sungtae Shin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Dong-A University, Busan 49315, Republic of Korea. Hauptthemen laut MEDLINE: Algorithms, Ballistocardiography. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, U. S. Office of Naval Research, U.S. Office of Naval Research.
Abstract (Originalsprache)
This paper describes a signal quality classification method for arm ballistocardiogram (BCG), which has the potential for non-invasive and continuous blood pressure measurement. An advantage of the BCG signal for wearable devices is that it can easily be measured using accelerometers. However, the BCG signal is also susceptible to noise caused by motion artifacts. This distortion leads to errors in blood pressure estimation, thereby lowering the performance of blood pressure measurement based on BCG. In this study, to prevent such performance degradation, a binary classification model was created to distinguish between high-quality versus low-quality BCG signals. To estimate the most accurate model, four time-series imaging methods (recurrence plot, the Gramain angular summation field, the Gramain angular difference field, and the Markov transition field) were studied to convert the temporal BCG signal associated with each heartbeat into a 448 × 448 pixel image, and the image was classified using CNN models such as ResNet, SqueezeNet, DenseNet, and LeNet. A total of 9626 BCG beats were used for training, validation, and testing. The experimental results showed that the ResNet and SqueezeNet models with the Gramain angular difference field method achieved a binary classification accuracy of up to 87.5%.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical Engineering, Dong-A University, Busan 49315, Republic of Korea.
- Institute for Digital Antiaging and Healthcare, Inje University, Gimhae 50834, Republic of Korea.
- Department of Mechanical Engineering, University of Maryland, College Park, MD 20742, USA.
- Department of Healthcare Information Technology, Inje University, Gimhae 50834, Republic of Korea.
- Paik Institute for Clinical Research, Inje University, Busan 50834, Republic of Korea.
- Department of Mechatronics Engineering, Incheon National University, Incheon 22012, Republic of Korea.
ORCID-Profile: Sungtae Shin, Azin Sadat Mousavi, Jin-Oh Hahn
Förderung
- National Research Foundation of Korea
- U. S. Office of Naval Research
- U.S. Office of Naval Research
- Ministry of Science and ICT (MIST) of Korea
Zitieren
APA
Shin, S., Choi, S., Kim, C., Mousavi, A. S., Hahn, J. O., Jeong, S., & Jeong, H. (2023). BCG Signal Quality Assessment Based on Time-Series Imaging Methods. Sensors, 23(23), 9382. https://doi.org/10.3390/s23239382
Vancouver
Shin S, Choi S, Kim C, Mousavi AS, Hahn JO, Jeong S, et al. BCG Signal Quality Assessment Based on Time-Series Imaging Methods. Sensors. 2023;23(23):9382. doi:10.3390/s23239382
BibTeX
@article{Shin2023,
author = {Shin, Sungtae and Choi, Soonyoung and Kim, Chaeyoung and Mousavi, Azin Sadat and Hahn, Jin-Oh and Jeong, Sehoon and Jeong, Hyundoo},
title = {BCG Signal Quality Assessment Based on Time-Series Imaging Methods},
journal = {Sensors},
year = {2023},
volume = {23},
number = {23},
pages = {9382},
doi = {10.3390/s23239382}
}
EUVIMED