Scholarlink

<p>Electrocardiogram (ECG) signals play a crucial role in the internet of medical things (IoMT) by enabling real-time heart health assessment, particularly for cardiovascular disease monitoring and personalized health management in sports and fitness applications. This study proposes a hybrid deep learning model that integrates a long short-term memory (LSTM) network and a convolutional neural network (CNN) to enhance ECG signal classification. The LSTM network captures the temporal dependencies of ECG sequences, while the CNN extracts localized spatial features, allowing for a comprehensive analysis of heart rhythms. By utilizing preprocessed ECG data as input, our model effectively combines feature extraction and classification into a unified framework. We evaluate the proposed approach using a publicly available datase. Experimental results demonstrate that our method achieves high accuracy in distinguishing various heart rhythm patterns, offering a promising solution for automated arrhythmia detection in IoMT applications.</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

Hybrid CNN-LSTM model for ECG-based arrhythmia detection in internet of medical things

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月7日

查看全文
  • Yuwei Wang,
  • Shalli Rani

摘要

Electrocardiogram (ECG) signals play a crucial role in the internet of medical things (IoMT) by enabling real-time heart health assessment, particularly for cardiovascular disease monitoring and personalized health management in sports and fitness applications. This study proposes a hybrid deep learning model that integrates a long short-term memory (LSTM) network and a convolutional neural network (CNN) to enhance ECG signal classification. The LSTM network captures the temporal dependencies of ECG sequences, while the CNN extracts localized spatial features, allowing for a comprehensive analysis of heart rhythms. By utilizing preprocessed ECG data as input, our model effectively combines feature extraction and classification into a unified framework. We evaluate the proposed approach using a publicly available datase. Experimental results demonstrate that our method achieves high accuracy in distinguishing various heart rhythm patterns, offering a promising solution for automated arrhythmia detection in IoMT applications.