Scholarlink

The purpose of this research work is to explore the viability of photoplethysmogram (PPG) as a continuous, noninvasive and cuffless method of blood pressure (BP) monitoring. It uses Edge Machine Learning Models to estimate Blood Pressure from PPG Signals in a time sensitive manner. The study reports mean absolute error (MAE) of 5.12 mmHg for Systolic Blood Pressure (SBP) and 2.58 mmHg for Diastolic Blood Pressure (DBP) estimation. This new methodology, however, makes use of Edge ML Models to estimate blood pressure along side Deep Learning models hence bypasses most limitations in Deep learning approaches.

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

Blood Pressure Estimation from Photoplethysmogram Signals: An EdgeML Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nithin Aditya Pradeepkumar,
  • Krishna Karthik Bhaskar

摘要

The purpose of this research work is to explore the viability of photoplethysmogram (PPG) as a continuous, noninvasive and cuffless method of blood pressure (BP) monitoring. It uses Edge Machine Learning Models to estimate Blood Pressure from PPG Signals in a time sensitive manner. The study reports mean absolute error (MAE) of 5.12 mmHg for Systolic Blood Pressure (SBP) and 2.58 mmHg for Diastolic Blood Pressure (DBP) estimation. This new methodology, however, makes use of Edge ML Models to estimate blood pressure along side Deep Learning models hence bypasses most limitations in Deep learning approaches.