PPG-Based Heart Rate Estimation Using Unsupervised Domain Adaptation

被引:0
作者
Kim, Jihyun [1 ]
Lee, Minjung [2 ]
Cho, Hansam [1 ]
Kim, Seoung Bum [1 ]
机构
[1] Korea Univ, Seoul, South Korea
[2] Elect & Telecommun Res Inst, Daejeon, South Korea
来源
ADVANCES AND TRENDS IN ARTIFICIAL INTELLIGENCE: THEORY AND APPLICATIONS, IEA-AIE 2024 | 2024年 / 14748卷
关键词
PPG Sensors; Heart Rate Estimation; Unsupervised Domain Adaptation; Deep Learning; Regression;
D O I
10.1007/978-981-97-4677-4_24
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recent advancements in wireless sensors have introduced photoplethysmography (PPG) sensors for heart rate estimation. However, accurate estimation remains a challenge because of motion artifacts affecting signal precision. While deep learning-based approaches show promise in addressing MAs, they often require subject-specific training or fine-tuning to address inter-subject variability within PPG sensors, demanding extensive labeled data collection for each new subject. Therefore, this study explores the application of unsupervised domain adaptation (UDA) techniques to mitigate inter-subject variability within PPG sensors and enhance prediction performance on new subjects without individual labeling. Implementing five state-of-the-art UDA methods, we demonstrate their effectiveness in heart rate estimation compared to supervised learning methods. Moreover, we analyze and interpret these results based on the characteristics of each UDA method.
引用
收藏
页码:291 / 296
页数:6
相关论文
共 9 条
  • [1] CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment
    Biswas, Dwaipayan
    Everson, Luke
    Liu, Muqing
    Panwar, Madhuri
    Verhoef, Bram-Ernst
    Patki, Shrishail
    Kim, Chris H.
    Acharyya, Amit
    Van Hoof, Chris
    Konijnenburg, Mario
    Van Helleputte, Nick
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS, 2019, 13 (02) : 282 - 291
  • [2] Q-PPG: Energy-Efficient PPG-Based Heart Rate Monitoring on Wearable Devices
    Burrello, Alessio
    Pagliari, Daniele Jahier
    Risso, Matteo
    Benatti, Simone
    Macii, Enrico
    Benini, Luca
    Poncino, Massimo
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS, 2021, 15 (06) : 1196 - 1209
  • [3] Cortes C, 2011, LECT NOTES ARTIF INT, V6925, P308, DOI 10.1007/978-3-642-24412-4_25
  • [4] Ganin Y, 2015, PR MACH LEARN RES, V37, P1180
  • [5] Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks
    Reiss, Attila
    Indlekofer, Ina
    Schmidt, Philip
    Van Laerhoven, Kristof
    [J]. SENSORS, 2019, 19 (14)
  • [6] Unsupervised Multi-source Domain Adaptation for Regression
    Richard, Guillaume
    de Mathelin, Antoine
    Hebrail, Georges
    Mougeot, Mathilde
    Vayatis, Nicolas
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2020, PT I, 2021, 12457 : 395 - 411
  • [7] Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
    Saito, Kuniaki
    Watanabe, Kohei
    Ushiku, Yoshitaka
    Harada, Tatsuya
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 3723 - 3732
  • [8] Tan Chang Wei, 2020, Zenodo, DOI 10.5281/ZENODO.3902710
  • [9] Tzeng E, 2014, Arxiv, DOI arXiv:1412.3474