Scholarlink

This study introduces an innovative approach leveraging Random Forest Regression models to estimate caloric expenditure across various physical activities with high precision. The models were developed and validated using data from ninety-nine volunteers, aged 18 to 65, ensuring a diverse representation of activity levels. Achieving an average accuracy of 96.65%, the proposed models significantly enhance the precision of energy expenditure measurements, which is crucial for effective health and fitness management. This advancement supports robust, reliable estimates essential for the development of IoT-based health monitoring systems. The integration of data from multiple wearable sensors, including accelerometers and heart rate monitors, further refines the accuracy, contributing substantially to the field of health analytics.

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

Advancing Health Analytics: Random Forest Regression Models for Caloric Expenditure in Varied Activities

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ahmed Younes Shdefat,
  • Nour Mostafa,
  • Mohammad Salman,
  • Yehia Kotb,
  • Fahmi Elsayed

摘要

This study introduces an innovative approach leveraging Random Forest Regression models to estimate caloric expenditure across various physical activities with high precision. The models were developed and validated using data from ninety-nine volunteers, aged 18 to 65, ensuring a diverse representation of activity levels. Achieving an average accuracy of 96.65%, the proposed models significantly enhance the precision of energy expenditure measurements, which is crucial for effective health and fitness management. This advancement supports robust, reliable estimates essential for the development of IoT-based health monitoring systems. The integration of data from multiple wearable sensors, including accelerometers and heart rate monitors, further refines the accuracy, contributing substantially to the field of health analytics.