首页|University of Waterloo Reports Findings in Cardiovascular Diseases and Conditions (Heart rate prediction with contactless active assisted living technology: a smart home approach for older adults)

University of Waterloo Reports Findings in Cardiovascular Diseases and Conditions (Heart rate prediction with contactless active assisted living technology: a smart home approach for older adults)

扫码查看
New research on Cardiovascular Diseases and Conditions is the subject of a report. According to news reporting out of Waterloo, Canada, by NewsRx editors, research stated, “As global demographics shift toward an aging population, monitoring their heart rate becomes essential, a key physiological metric for cardiovascular health. Traditional methods of heart rate monitoring are often invasive, while recent advancements in Active Assisted Living provide non-invasive alternatives.” Our news journalists obtained a quote from the research from the University of Waterloo, “This study aims to evaluate a novel heart rate prediction method that utilizes contactless smart home technology coupled with machine learning techniques for older adults. The study was conducted in a residential environment equipped with various contactless smart home sensors. We recruited 40 participants, each of whom was instructed to perform 23 types of predefined daily living activities across five phases. Concurrently, heart rate data were collected through Empatica E4 wristband as the benchmark. Analysis of data involved five prominent machine learning models: Support Vector Regression, K-nearest neighbor, Random Forest, Decision Tree, and Multilayer Perceptron. All machine learning models achieved commendable prediction performance, with an average Mean Absolute Error of 7.329. Particularly, Random Forest model outperformed the other models, achieving a Mean Absolute Error of 6.023 and a Scatter Index value of 9.72%. The Random Forest model also showed robust capabilities in capturing the relationship between individuals’ daily living activities and their corresponding heart rate responses, with the highest value of 0.782 observed during morning exercise activities. Environmental factors contribute the most to model prediction performance. The utilization of the proposed non-intrusive approach enabled an innovative method to observe heart rate fluctuations during different activities. The findings of this research have significant implications for public health. By predicting heart rate based on contactless smart home technologies for individuals’ daily living activities, healthcare providers and public health agencies can gain a comprehensive understanding of an individual’s cardiovascular health profile.”

WaterlooCanadaNorth and Central AmericaCardiologyCardiovascularCardiovascular Diseases and ConditionsCardiovascular ResearchCyborgsEmerging TechnologiesHealth and MedicineHeart RateHemodynamicsMachine LearningPublic HealthRisk and PreventionTechnology

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Feb.9)
  • 41