Scholarlink

<p>An ECG monitors the electrical activity of the heart, which is used to assess the heart’s health and rhythm. It has also been demonstrated that a person’s emotions can influence their heart’s electrical activity. Therefore, it is simple to assess a person’s mental and physical well-being by examining their heart’s electrical activity. Many papers dealing with the automatic classification of cardiac abnormalities using ECG signals have been published in recent years. This study focuses on automatic emotion recognition methods using ECG data, human abnormality classification, and noise reduction in ECG signals. The linking of physical objects, referred to as things, to the Internet is known as the Internet of Things (IoT). Biomedical sensing devices are the foundation of a plethora of IoT applications for health monitoring that track various health issues. Health Conditions The use of diagnosis systems to assist medical professionals (clinicians) in making decisions about disease diagnosis and treatment is now being investigated. This could improve the standard of care while lowering costs. This study addresses the challenge of accurate emotion recognition and health monitoring in elderly individuals, leveraging Internet of Things (IoT) and machine learning (ML) techniques. The aim is to develop a reliable and efficient system for real-time health monitoring and emotion recognition, addressing the limitations of existing approaches that rely on manual analysis and are prone to errors. A novel CNN-based RBF model is proposed, integrating IoT-enabled ECG signals and ML algorithms to classify emotions and detect cardiac abnormalities. The performance of the proposed model is evaluated using metrics such as accuracy, latency, and reaction time, demonstrating promising results. The results obtained demonstrate that the proposed CNN-based RBF model achieves an accuracy of 95.6% in detecting coronary artery disease, with a latency of 0.5&#xa0;s and reaction time of 1.2&#xa0;s. These values are significant in emergency situations, as timely detection and intervention can be crucial in preventing cardiac arrests and improving patient outcomes.</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

Chronic heart disease detection of elder patient’s using machine learning technology integrated with internet of things

  • 期刊论文

  • 发表日期：

    2025年9月27日

查看全文
  • B. Sathyasri,
  • Aanandha Saravanan,
  • G. Aloy Anuja Mary,
  • S. Vanaja,
  • K. C. Sriharipriya

摘要

An ECG monitors the electrical activity of the heart, which is used to assess the heart’s health and rhythm. It has also been demonstrated that a person’s emotions can influence their heart’s electrical activity. Therefore, it is simple to assess a person’s mental and physical well-being by examining their heart’s electrical activity. Many papers dealing with the automatic classification of cardiac abnormalities using ECG signals have been published in recent years. This study focuses on automatic emotion recognition methods using ECG data, human abnormality classification, and noise reduction in ECG signals. The linking of physical objects, referred to as things, to the Internet is known as the Internet of Things (IoT). Biomedical sensing devices are the foundation of a plethora of IoT applications for health monitoring that track various health issues. Health Conditions The use of diagnosis systems to assist medical professionals (clinicians) in making decisions about disease diagnosis and treatment is now being investigated. This could improve the standard of care while lowering costs. This study addresses the challenge of accurate emotion recognition and health monitoring in elderly individuals, leveraging Internet of Things (IoT) and machine learning (ML) techniques. The aim is to develop a reliable and efficient system for real-time health monitoring and emotion recognition, addressing the limitations of existing approaches that rely on manual analysis and are prone to errors. A novel CNN-based RBF model is proposed, integrating IoT-enabled ECG signals and ML algorithms to classify emotions and detect cardiac abnormalities. The performance of the proposed model is evaluated using metrics such as accuracy, latency, and reaction time, demonstrating promising results. The results obtained demonstrate that the proposed CNN-based RBF model achieves an accuracy of 95.6% in detecting coronary artery disease, with a latency of 0.5 s and reaction time of 1.2 s. These values are significant in emergency situations, as timely detection and intervention can be crucial in preventing cardiac arrests and improving patient outcomes.