MODELING REALITY: REVISITING CALVERT'S FITNESS SIMULATION.

Area of Science:

• Sports Science
• Biomedical Engineering
• Data Science

Background:

• Wearable sensors are popular for health monitoring but lack clinically validated models for decision support.
• Individual sensor data (e.g., EKG, heart rate) offer limited insights; a comprehensive approach requires integrated data.
• Existing models for training effects on physical performance need updating to incorporate modern data sources.

Purpose of the Study:

• To reconfigure the 1976 Calvert systems model using contemporary wearable sensor data.
• To develop a hybrid simulation model integrating Perl's Performance-Potential model and Calvert's transfer function approach.
• To create an agile platform for simulating fitness and exploring causality between training and physical performance.

Main Methods:

• Utilizing clinical trial data from wearable sensors.
• Supplementing the Calvert systems model with wearable sensor data.
• Nesting Perl's Performance-Potential model within Calvert's transfer function for system simulation.

Main Results:

• Development of a hybrid model combining existing theoretical frameworks with real-world wearable data.
• Establishment of a simulation platform for analyzing fitness and training effects.
• Demonstration of a more agile approach to modeling physical performance.

Conclusions:

• The developed platform enables strategic integration of diverse wearable sensor data.
• This approach enhances support for post-injury and return-to-sport decision-making.
• The research lays the foundation for more sophisticated analysis of training impacts on physical performance.