Scholarlink

The potential to revolutionize the detection of cardiovascular disorders is with the use of advanced pattern recognizers from the field of artificial intelligence (AI). The advent of AI presents a promising avenue for achieving real-time detection, heralding a new era in healthcare. This study centers on recurrent neural networks (RNN) harnessing for the problem of time-series predictions, with optimization facilitated by the particle swarm optimization (PSO) metaheuristic algorithm. Specifically, this work aims to identify anomalies within electrocardiogram (ECG) signals, thereby enabling the timely detection and prevention of cardiovascular illnesses. The use of RNNs and PSO optimization has great potential for producing robust and efficient outcomes. For the assessment of the effectiveness of our approach, a comprehensive comparative analysis is conducted, evaluating its performance against other high-performing algorithms in identical conditions. By merging the capabilities of AI, RNNs, and PSO, this research not only contributes to the advancement of cardiovascular disorder detection but also underscores the potential for transformative improvements in patient care. Early identification of cardiac irregularities through ECG analysis has the potential to save lives and reduce the burden on healthcare systems, making it a critical area of study for researchers and practitioners alike.

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

Anomaly Detection in Electrocardiogram Data by Applying Metaheuristics Tuned Time-Series Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Aleksandar Petrovic,
  • Luka Jovanovic,
  • K. Venkatachalam,
  • Miodrag Zivkovic,
  • Nebojsa Bacanin,
  • Nebojsa Budimirovic

摘要

The potential to revolutionize the detection of cardiovascular disorders is with the use of advanced pattern recognizers from the field of artificial intelligence (AI). The advent of AI presents a promising avenue for achieving real-time detection, heralding a new era in healthcare. This study centers on recurrent neural networks (RNN) harnessing for the problem of time-series predictions, with optimization facilitated by the particle swarm optimization (PSO) metaheuristic algorithm. Specifically, this work aims to identify anomalies within electrocardiogram (ECG) signals, thereby enabling the timely detection and prevention of cardiovascular illnesses. The use of RNNs and PSO optimization has great potential for producing robust and efficient outcomes. For the assessment of the effectiveness of our approach, a comprehensive comparative analysis is conducted, evaluating its performance against other high-performing algorithms in identical conditions. By merging the capabilities of AI, RNNs, and PSO, this research not only contributes to the advancement of cardiovascular disorder detection but also underscores the potential for transformative improvements in patient care. Early identification of cardiac irregularities through ECG analysis has the potential to save lives and reduce the burden on healthcare systems, making it a critical area of study for researchers and practitioners alike.