Scholarlink

This paper presents a comparative study between Long Short-Term Memory (LSTM) networks and Recurrent Neural Networks (RNNs) for the classification of electrocardiogram (ECG) signals. ECG signals are crucial for diagnosing cardiac conditions, and the advent of deep learning methods has revolutionized automated analysis. LSTM and RNN models were trained on a public ECG dataset, achieving 90% and 99% accuracy, respectively. This study highlights the strengths and limitations of each approach and proposes future directions to enhance ECG classification performance, with the potential to improve clinical diagnostic tools.

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

Classifying ECG Signals Using LSTM and RNN

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Said Ziani,
  • Mohamed El Ghmary,
  • Hassan Echoukairi

摘要

This paper presents a comparative study between Long Short-Term Memory (LSTM) networks and Recurrent Neural Networks (RNNs) for the classification of electrocardiogram (ECG) signals. ECG signals are crucial for diagnosing cardiac conditions, and the advent of deep learning methods has revolutionized automated analysis. LSTM and RNN models were trained on a public ECG dataset, achieving 90% and 99% accuracy, respectively. This study highlights the strengths and limitations of each approach and proposes future directions to enhance ECG classification performance, with the potential to improve clinical diagnostic tools.