Related Experiment Videos
Anaerobic threshold measurement using dynamic neural network models.
1School of Electronic Engineering, Dublin City University, Glasnevin, Ireland. ringwoodj@eeng.dcu.ie
Computers in Biology and Medicine
|August 10, 1999
Summary
This study introduces a novel method for measuring anaerobic threshold in athletes using dynamic data and neural networks. This approach accurately determines the steady-state heart-rate/work-rate curve, improving non-invasive athletic performance analysis.
Area of Science:
- Sports Science
- Biomedical Engineering
- Computational Physiology
Background:
- Accurate anaerobic threshold (AT) measurement is crucial for optimizing training in aerobic and aerobic/anaerobic sports.
- Traditional AT determination methods include invasive procedures or non-invasive techniques relying on steady-state heart-rate/work-rate data.
- Non-invasive methods offer convenience but face challenges in acquiring reliable steady-state information.
Observation:
- Steady-state data acquisition in non-invasive AT testing can be problematic and time-consuming.
- Dynamical physiological data contains valuable information about the athlete's metabolic state.
- Neural network dynamic models can effectively process complex, time-varying physiological signals.
Findings:
- This paper presents a novel method utilizing dynamical data to accurately determine the steady-state heart-rate/work-rate (SSHW) curve.
- Neural network dynamic models are employed to model the relationship between heart rate and work rate from non-steady-state data.
- The proposed technique enables precise AT determination without requiring specialized equipment or invasive procedures.
Implications:
- This method offers a more accessible and accurate approach to AT assessment for athletes and coaches.
- Improved AT measurement can lead to more effective and personalized training program design.
- The findings have potential applications in sports performance monitoring and clinical exercise physiology.