(ORDO NEWS) — The model created at Saint-Petersburg Electrotechnical University “LETI” will allow with high accuracy to individually calculate the anaerobic threshold for each athlete – the most important indicator for monitoring physical fitness.
The anaerobic threshold is the highest level of intensity that a person can endure for a long time without a significant amount of lactate accumulating in the blood (this reduces the overall physical condition of the body).
Therefore, one of the tasks of professional athletes during the training process is to constantly increase the anaerobic threshold in order to enhance the overall endurance of the body.
However, the exact determination of the anaerobic threshold is a difficult task, since it depends on a large number of factors: the physiological characteristics of a particular athlete and the system of methods and ideas about training on the part of the coaching staff.
“With the help of machine learning methods, we have developed a model that can improve the accuracy of predicting the anaerobic threshold, which is one of the main criteria for monitoring the training of professional athletes.
This development will improve the efficiency of the training process,” says Dmitry Kaplun, Associate Professor of the Department of Automation and Control Processes of St. Petersburg Electrotechnical University “LETI”.
The creation of the model was preceded by data collection, which was carried out by researchers from the Research Institute of Hygiene, Occupational Pathology and Human Ecology and the North-Western State Medical University named after I. I. Mechnikov.
They tested athletes on special devices that simulate the training process and the physiological state when the anaerobic threshold is reached. Data collection (heart rate, blood oxygen saturation, etc.) from the subjects was carried out using sensors. More than 1.2 thousand observations were made to collect data.
Then the data obtained were used by LETI scientists to train a predictive model. To achieve the highest possible accuracy of data analysis, four different machine learning methods were applied, the resulting model is able to determine the physiological indicators (in quantitative terms) that limit the increase in the anaerobic threshold during training. For this, scientists used a special explanatory algorithm LIME (Local Interpretable Model-Agnostic Explanations). The results of the work were published in the scientific journal Biomedical Signal Processing and Control .
“The developed model for determining the anaerobic threshold allows you to identify patterns that affect the test result, and, as a result, predict the course of the training process so that the athlete acts effectively without flaws or overwork, and enters the competition at the peak of his form,” explains Dmitry Kaplun. Now scientists are working on improving the accuracy of the created model by applying other more complex machine learning algorithms.
Contact us: [email protected]