Scholarlink

<p>The Internet of Medical Things (IoMT) includes healthcare devices and software that remotely monitor and manage patients. Monitoring electrocardiograms (ECGs) for arrhythmia categorization and recognition is one use of IoMT. IoMT-based ECG monitoring technologies provide continuous monitoring and real-time notifications to help healthcare providers detect arrhythmias early. These methods use a wearable gadget to record the patient’s ECG and send it to a cloud server for analysis. This data is used to train machine learning to detect arrhythmia patterns. These methods classify arrhythmias like atrial fibrillation, ventricular tachycardia, and bradycardia. ECG signals on the IoMT environment are used to construct an IoMT system for arrhythmia detection and classification utilizing African Vulture Optimization with Ensemble Deep Learning (ADC-AVOEDL). ECG signals are used to detect and classify arrhythmia in the ADC-AVOEDL model. The proposed ADC-AVOEDL model has three main functions. The ADC-AVOEDL model preprocesses incoming data into a comprehensible format using a standard scaling mechanism. Additionally, AVOFS is used to produce features. Finally, the ADC-AVOEDL model labels ECG signals using an ensemble classifier including Gated Recurrent Unit, Long Short-Term Memory (LSTM), and BiLSTM. RMSProp optimizer is used to alter ensemble technique parameters. The ADC-AVOEDL experimental outcome analysis is tested using a benchmark dataset.</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

Internet of medical things-based ECG monitoring for arrhythmia classification utilizing metaheuristic optimization with ensemble deep learning model

  • 期刊论文

  • 发表日期：

    2025年6月16日

查看全文
  • K. Ghamya,
  • K. Reddy Madhavi

摘要

The Internet of Medical Things (IoMT) includes healthcare devices and software that remotely monitor and manage patients. Monitoring electrocardiograms (ECGs) for arrhythmia categorization and recognition is one use of IoMT. IoMT-based ECG monitoring technologies provide continuous monitoring and real-time notifications to help healthcare providers detect arrhythmias early. These methods use a wearable gadget to record the patient’s ECG and send it to a cloud server for analysis. This data is used to train machine learning to detect arrhythmia patterns. These methods classify arrhythmias like atrial fibrillation, ventricular tachycardia, and bradycardia. ECG signals on the IoMT environment are used to construct an IoMT system for arrhythmia detection and classification utilizing African Vulture Optimization with Ensemble Deep Learning (ADC-AVOEDL). ECG signals are used to detect and classify arrhythmia in the ADC-AVOEDL model. The proposed ADC-AVOEDL model has three main functions. The ADC-AVOEDL model preprocesses incoming data into a comprehensible format using a standard scaling mechanism. Additionally, AVOFS is used to produce features. Finally, the ADC-AVOEDL model labels ECG signals using an ensemble classifier including Gated Recurrent Unit, Long Short-Term Memory (LSTM), and BiLSTM. RMSProp optimizer is used to alter ensemble technique parameters. The ADC-AVOEDL experimental outcome analysis is tested using a benchmark dataset.