Machine Learning Applications for In-School Physical Activity Data Using IMUs in Children and Adolescents: A Systematic Review for Health Promotion

Key Points

• The research aims to explore how machine learning can enhance monitoring of physical activity using data from wearable sensors in children and adolescents.
• Systematic review of literature on machine learning applications for physical activity data
• Focus on inertial measurement units (IMUs) in school settings
• Assessment of data accuracy and monitoring effectiveness
• Reported accuracies of physical activity monitoring ranged from 70% to 99%
• Wearable sensor data combined with machine learning shows strong potential for assessment
• Implications for health promotion in school environments are significant