Scholarlink

<p>Respiration Rate (RR) is a crucial physiological measure for evaluating health and detecting early signs of respiratory distress in both clinical and home settings. Traditional RR estimation methods often require specialized equipment, whereas photoplethysmography (PPG) is a noninvasive and cost-effective alternative. However, noise interference and signal quality variations pose challenges in accurately estimating RR from PPG signals. This study proposes an enhanced method that improves the accuracy and robustness of estimation by optimizing the temporal window for segmentation and integrating preprocessing techniques, such as Chebyshev filtering and signal quality indices (SQI).This approach determines the optimal window sizes for precise RR calculation from PPG signals. To validate its effectiveness, the proposed method was evaluated on two datasets: the in-house TMCH dataset and the publicly available BIDMC dataset. On the BIDMC dataset, comprising 53 patients, the method achieved a Mean Absolute Error (MAE) of 2.07 bpm and a Root Mean Square Error (RMSE) of 1.95 bpm using a 120-second window. In the TMCH dataset, which included 524 participants, a 40-second window yielded an RMSE of 0.93 bpm and an MAE of 0.73 bpm. The results highlight the importance of selecting the optimal window size to balance accuracy and real-time performance for continuous and accurate RR estimation. The codes used during the research work are available at link: <a href="https://github.com/Ganz2077/Respiration-Rate-Estimation-using-PPG-Signals-and-Windows-Effect">https://github.com/Ganz2077/Respiration-Rate-Estimation-using-PPG-Signals-and-Windows-Effect</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Toward accurate estimation of respiratory rate from the photoplethysmogram: effect of different window period of PPG signals

  • 期刊论文

  • 发表日期：

    2025年6月30日

查看全文
  • M. S. Ganeshmurthy,
  • R. Periyasamy,
  • Deepak Joshi

摘要

Respiration Rate (RR) is a crucial physiological measure for evaluating health and detecting early signs of respiratory distress in both clinical and home settings. Traditional RR estimation methods often require specialized equipment, whereas photoplethysmography (PPG) is a noninvasive and cost-effective alternative. However, noise interference and signal quality variations pose challenges in accurately estimating RR from PPG signals. This study proposes an enhanced method that improves the accuracy and robustness of estimation by optimizing the temporal window for segmentation and integrating preprocessing techniques, such as Chebyshev filtering and signal quality indices (SQI).This approach determines the optimal window sizes for precise RR calculation from PPG signals. To validate its effectiveness, the proposed method was evaluated on two datasets: the in-house TMCH dataset and the publicly available BIDMC dataset. On the BIDMC dataset, comprising 53 patients, the method achieved a Mean Absolute Error (MAE) of 2.07 bpm and a Root Mean Square Error (RMSE) of 1.95 bpm using a 120-second window. In the TMCH dataset, which included 524 participants, a 40-second window yielded an RMSE of 0.93 bpm and an MAE of 0.73 bpm. The results highlight the importance of selecting the optimal window size to balance accuracy and real-time performance for continuous and accurate RR estimation. The codes used during the research work are available at link: https://github.com/Ganz2077/Respiration-Rate-Estimation-using-PPG-Signals-and-Windows-Effect.