Scholarlink

Atrial fibrillation is the most common type of cardiac arrhythmia. It is due to abnormal electrical activity within the atria of the heart, causing them to fibrillate. It is characterized by tachyarrhythmia, which means that the heart rate is often high. Several recent studies have been performed that demonstrate the effectiveness of AF detection using photoplethysmography (PPG) signals. This can possibly lead to an affordable and easy-to-wear alternative for AF detection. In this paper, we present a lightweight PPG-based AF detection technique. The proposed approach leverages the scalogram of segmented PPG signals and a lightweight, customized CNN-based network for efficient AF detection. The proposed technique is capable of achieving a notable maximum accuracy of 100% across the set of experiments performed on a public MIMIC Perform dataset.

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

A Lightweight CNN-Based Model for Atrial Fibrillation Detection Using PPG Signal

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Bhupendra Tiwari,
  • Saumya Kumari,
  • Preeti Ghasad,
  • Ankit Bhurane,
  • Vipin Kamble

摘要

Atrial fibrillation is the most common type of cardiac arrhythmia. It is due to abnormal electrical activity within the atria of the heart, causing them to fibrillate. It is characterized by tachyarrhythmia, which means that the heart rate is often high. Several recent studies have been performed that demonstrate the effectiveness of AF detection using photoplethysmography (PPG) signals. This can possibly lead to an affordable and easy-to-wear alternative for AF detection. In this paper, we present a lightweight PPG-based AF detection technique. The proposed approach leverages the scalogram of segmented PPG signals and a lightweight, customized CNN-based network for efficient AF detection. The proposed technique is capable of achieving a notable maximum accuracy of 100% across the set of experiments performed on a public MIMIC Perform dataset.