Estimation of Mechanical Power Output Employing Deep Learning on Inertial Measurement Data in Roller Ski Skating.

Md Zia Uddin,Anders E Liverud,Frédéric Meyer,Øyvind Sandbakk,Trine M Seeberg,Jan Kocbach,Victor Gonzalez

doi:10.3390/s21196500

Abstract

The ability to optimize power generation in sports is imperative, both for understanding and balancing training load correctly, and for optimizing competition performance. In this paper, we aim to estimate mechanical power output by employing a time-sequential information-based deep Long Short-Term Memory (LSTM) neural network from multiple inertial measurement units (IMUs). Thirteen athletes conducted roller ski skating trials on a treadmill with varying incline and speed. The acceleration and gyroscope data collected with the IMUs were run through statistical feature processing, before being used by the deep learning model to estimate power output. The model was thereafter used for prediction of power from test data using two approaches. First, a user-dependent case was explored, reaching a power estimation within 3.5% error. Second, a user-independent case was developed, reaching an error of 11.6% for the power estimation. Finally, the LSTM model was compared to two other machine learning models and was found to be superior. In conclusion, the user-dependent model allows for precise estimation of roller skiing power output after training the model on data from each athlete. The user-independent model provides less accurate estimation; however, the accuracy may be sufficient for providing valuable information for recreational skiers.

Highlights

Cross-country (XC) and roller skiing are endurance sports performed in varying terrain with subsequent variations in speed, as well as both external and metabolic power [1,2,3].The varying terrain of the courses used during training and competition induces periods of very high intensity during uphill stints, and the ability to recover in downhill stints [4].In addition, terrain, track and weather conditions influence the opposing forces and constraints for producing power through poles and skis, which have a high impact on skiing speed at a given metabolic intensity [5]
While mechanical power can be directly measured on the bike with force sensors, measurement of power output in XC skiing is more complex, as force magnitude and direction must be measured for both poles and skis [7]
The aim was to understand the influence of including data from the testing subjects in the training of Long Short-Term Memory (LSTM)-based neural networks

Summary

Introduction

Terrain, track and weather conditions influence the opposing forces and constraints for producing power through poles and skis, which have a high impact on skiing speed at a given metabolic intensity [5]. It is, not feasible to compare the performance of athletes from day-to-day or from track-to-track by using speed or segment time, as in many other sports, such as running or cycling. The direct measurement of power output is challenging, and an indirect approach, where the mechanical power is estimated using inertial measurement units (IMUs), has been attempted with several commercial technologies on the market. The proprietary methods used for power estimation in running from IMU data are not published, and the repeatability and concurrent validity of the commercial technologies is found to be low [10,11,12]

Objectives

Methods

Results

Discussion

Conclusion