Scholarlink

The aim of our proposed model is to develop an efficient system which capable of automatically classifying various ECG arrhythmias. By manipulating the important feature extraction capabilities of the InceptionNet architecture, the framework goals to enhance the accuracy and reliability of arrhythmia detection which compared to traditional systems. The model will be trained on a dataset of ECG signals to ensure its external validity and applicability across different patient attributes and arrhythmia variations. Additionally, the model seeks to reduce the computational complexity and processing time which makes suitable for real-time systems in clinical sector. Ultimately, the aim is to aid healthcare sectors in early and better diagnosis, boosting patient outcomes and streamlining workflow in medical areas. Subsequently model checks comprehensive measurement like accuracy, confusion matrix analysis, classification report, F1-score, and ROC curve analysis. The study achieved a 92.30% accuracy in classifying ECG signals, demonstrating the effectiveness of the proposed approach and its potential to enhance medical diagnostics and improve patient care.

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

InceptionNet-Enhanced Deep Learning Framework for ECG Arrhythmia Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Soumen Ghosh,
  • Satish Chander

摘要

The aim of our proposed model is to develop an efficient system which capable of automatically classifying various ECG arrhythmias. By manipulating the important feature extraction capabilities of the InceptionNet architecture, the framework goals to enhance the accuracy and reliability of arrhythmia detection which compared to traditional systems. The model will be trained on a dataset of ECG signals to ensure its external validity and applicability across different patient attributes and arrhythmia variations. Additionally, the model seeks to reduce the computational complexity and processing time which makes suitable for real-time systems in clinical sector. Ultimately, the aim is to aid healthcare sectors in early and better diagnosis, boosting patient outcomes and streamlining workflow in medical areas. Subsequently model checks comprehensive measurement like accuracy, confusion matrix analysis, classification report, F1-score, and ROC curve analysis. The study achieved a 92.30% accuracy in classifying ECG signals, demonstrating the effectiveness of the proposed approach and its potential to enhance medical diagnostics and improve patient care.