The aim of this study was to adapt a treadmill-developed method for determination of inner-cycle parameters in cross-country roller ski skating for a field application. The method is based on detecting initial and final ground-contact of poles and skis during cyclic movements. Eleven athletes skied four laps of 2.5 km at low and high endurance-intensity, using two types of skis with different rolling coefficients. Participants were equipped with inertial measurement units (IMUs) attached to their wrists and skis, while insoles with pressure sensors and poles with force measurements were used as reference systems. The method based on IMUs was able to detect more than 97% of the temporal events compared to the reference system. The inner-cycle temporal parameters had a precision ranging from 49 to 59 ms, corresponding to 3.9% to 13.7% of the corresponding inner-cycle duration. Overall, this study showed good reliability of using IMUs on athlete’s wrists and skis to determine temporal events, inner-cycle parameters and the performed sub-techniques in cross-country roller ski skating in field-conditions.

Purpose To compare performance, physiological and biomechanical responses between double poling (DP) and diagonal stride (DIA) during treadmill roller skiing in elite male cross-country skiers. Method Twelve skiers (VO2peak DIAup; 74.7 ± 3.7 ml kg−1 min−1) performed two DP conditions at 1° (DPflat) and 8° (DPup) incline, and one DIA condition, 8° (DIAup). Submaximal gross efficiency (GE) and maximal 3.5 min time-trial (TT) performance, including measurements of VO2peak and maximal accumulated O2-deficit (MAOD), were determined. Temporal patterns and kinematics were assessed using 2D video, while pole kinetics were obtained from pole force. Results DIAup induced (mean, [95% confidence interval]) 13% [4, 22] better 3.5-min TT performance, 7%, [5, 10]) higher VO2peak and 3% points [1, 5] higher GE compared to DPup (all P < 0.05). DPup induced 120% higher MAOD compared to DPflat, while no significant differences were observed for VO2peak or GE between DPflat and DPup. There was a large correlation between performance and GE in DP and a large correlation between performance and VO2peak for DIAup (all r = 0.7–0.8, P < 0.05). No correlations were found between performance and VO2peak for any of the DP conditions, nor between performance and GE for DIAup (r = 0.0–0.2, P > 0.1). Conclusion At 8º uphill roller skiing, DIAup induce higher VO2peak, GE, and superior time-trial performance than DPup in elite male skiers. There was no difference between VO2peak or GE between DPflat and DPup. A large correlation was observed between DIAup performance and DIAupVO2peak, while DP performance was best correlated to submaximal GE.

Objective: The aim of this study was to provide a new machine learning method to determine temporal events and inner-cycle parameters (e.g., cycle, poles and skis contact and swing time) in cross-country roller ski skating on the field, using a single deported inertial measurement unit (IMU). Methods: The developed method is based on long short-term memory neural networks to detect poles and skis initial and final contact with the ground during the cyclic movements. Eleven athletes skied four laps of 2.5 km at low and high intensity using skis with two different rolling coefficients. They were equipped with IMUs attached to the upper back, lower back and to the sternum. Data from force insoles and force poles were used as reference system. Results: The IMU placed on the upper back provided the best results, as the LSTM network was able to determine the temporal events with an accuracy ranging from 49 to 55 ms and the corresponding inner-cycles parameters were calculated with a precision of 63 to 68 ms. The method detected 95% of the events for the poles and 87% of the events for the skis. Conclusion: The proposed LSTM method provides a promising tool for assessing temporal events and inner-cycle phases in roller ski skating showing the potential of using a deported IMU to estimate different spatio-temporal parameters of human locomotion.

Objective: The aim of this study was to provide a new machine learning method to determine temporal events and inner-cycle parameters (e.g., cycle, pole and ski contact and swing time) in cross-country roller-ski skating on the field, using a single inertial measurement unit (IMU). Methods: The developed method is based on long short-term memory neural networks to detect the initial and final contact of the poles and skis with the ground during the cyclic movements. Eleven athletes skied four laps of 2.5 km at a low and high intensity using skis with two different rolling coefficients. They were equipped with IMUs attached to the upper back, lower back and to the sternum. Data from force insoles and force poles were used as the reference system. Results: The IMU placed on the upper back provided the best results, as the LSTM network was able to determine the temporal events with a mean error ranging from −1 to 11 ms and had a standard deviation (SD) of the error between 64 and 70 ms. The corresponding inner-cycle parameters were calculated with a mean error ranging from −11 to 12 ms and an SD between 66 and 74 ms. The method detected 95% of the events for the poles and 87% of the events for the skis. Conclusion: The proposed LSTM method provides a promising tool for assessing temporal events and inner-cycle phases in roller-ski skating, showing the potential of using a single IMU to estimate different spatiotemporal parameters of human locomotion.

The aim of this study was to test and adapt a treadmill-developed method for determination of inner-cycle parameters and sub-technique in cross-country roller ski skating for a field application. The method is based on detecting initial and final ground contact of poles and skis during cyclic movements. Eleven athletes skied 4 laps of 2.5 km at low- and high-endurance intensities, using 2 types of skis with different rolling coefficients. Participants were equipped with inertial measurement units attached to their wrists and skis, and insoles with pressure sensors and poles with force measurements were used as reference systems. The method based on inertial measurement units was able to detect >97% of the temporal events detected with the reference system. The inner-cycle temporal parameters had a precision ranging from 49 to 59 milliseconds, corresponding to 3.9% to 13.7% of the corresponding inner-cycle duration. Overall, this study showed good reliability of using inertial measurement units on athletes’ wrists and skis to determine temporal events, inner-cycle parameters, and the performed sub-techniques in cross-country roller ski skating in field conditions.