Scholarlink

Integrating the Internet of Things (IoT) technology and deep learning algorithms in vital sign monitoring heralds a transformative paradigm in healthcare. In today’s technological landscape, there is a growing impetus to harness scientific breakthroughs to increase treatment efficacy and prevent diseases. There is a concerted effort to create cost-effective and user-friendly solutions endowed with high predictive accuracy, especially in mitigating diseases prone to sudden recurrence and enduring complications such as stroke and coronary artery disease. This study proposes a combination of IoT and deep learning to develop a mobile vital sign monitoring system that could detect early and prognosticate cardiovascular abnormalities. This proposed system focused on integrating IoT sensors within wearable devices, enabling continuous monitoring of vital metrics, such as heart rate and heart electrical activity, as captured by electrocardiography (ECG) and photoplethysmography (PPG). The real-time data emanating from these sensors are relayed to a central server or a cloud platform for exhaustive analysis. Deep learning algorithms were then deployed to decipher the troves of data collected from these sensors. Using sophisticated deep learning techniques, these algorithms decipher nuanced patterns indicative of potential cardiovascular irregularities in the preliminary results as a demonstration. The algorithm’s discernment is clear in discerning irregular heart rhythms, anomalies in ECG and PPG waveforms, or other pivotal cardiac indicators. The mobile architecture empowers users with timely alerts and notifications, which are seamlessly transmitted to their smartphones or connected devices upon detecting anomalies. This proactive monitoring system is an advance that prompts people to seek the necessary medical attention or adopt lifestyle modifications to prevent serious health problems. By providing real-time information on cardiovascular health, this innovative amalgamation has the potential to accelerate early intervention.

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

Developing a Mobile Vital Sign Monitoring System with Deep Learning Algorithms

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tien Chuong Tran Nguyen,
  • Tat Binh Dong,
  • Duc Khang Nguyen,
  • Gia Khang Ly,
  • Viet Thai Le Viet,
  • Dang Khoa Trinh Vo,
  • Hai Anh Nguyen Thi,
  • Tan Loc Huynh,
  • Huy Bao Bui Minh,
  • Minh Quan Cao Dinh,
  • Quoc Tuan Nguyen Diep,
  • Anh Tu Tran,
  • Trung Nghia Tran

摘要

Integrating the Internet of Things (IoT) technology and deep learning algorithms in vital sign monitoring heralds a transformative paradigm in healthcare. In today’s technological landscape, there is a growing impetus to harness scientific breakthroughs to increase treatment efficacy and prevent diseases. There is a concerted effort to create cost-effective and user-friendly solutions endowed with high predictive accuracy, especially in mitigating diseases prone to sudden recurrence and enduring complications such as stroke and coronary artery disease. This study proposes a combination of IoT and deep learning to develop a mobile vital sign monitoring system that could detect early and prognosticate cardiovascular abnormalities. This proposed system focused on integrating IoT sensors within wearable devices, enabling continuous monitoring of vital metrics, such as heart rate and heart electrical activity, as captured by electrocardiography (ECG) and photoplethysmography (PPG). The real-time data emanating from these sensors are relayed to a central server or a cloud platform for exhaustive analysis. Deep learning algorithms were then deployed to decipher the troves of data collected from these sensors. Using sophisticated deep learning techniques, these algorithms decipher nuanced patterns indicative of potential cardiovascular irregularities in the preliminary results as a demonstration. The algorithm’s discernment is clear in discerning irregular heart rhythms, anomalies in ECG and PPG waveforms, or other pivotal cardiac indicators. The mobile architecture empowers users with timely alerts and notifications, which are seamlessly transmitted to their smartphones or connected devices upon detecting anomalies. This proactive monitoring system is an advance that prompts people to seek the necessary medical attention or adopt lifestyle modifications to prevent serious health problems. By providing real-time information on cardiovascular health, this innovative amalgamation has the potential to accelerate early intervention.