ECSS Paris 2023: CP-BM14
INTRODUCTION: Big Air training relies heavily on video-based methods. While video analysis provides rich qualitative information, it requires multiple camera setups, expert interpretation, and time for processing and analysis, limiting its use during independent training sessions. Wearable inertial sensors offer a complementary approach by enabling automated, objective, and easy-to-use analysis without external infrastructure. The aim of this study is to evaluate whether jump types in elite Big Air can be classified using boot-mounted IMU data. METHODS: Five professional male freestyle skiers performed Big Air jumps during training sessions. IMU data were collected bilaterally using the connected boot system [1], complemented by synchronized video recordings from four cameras. Differences in jump difficulty and athlete ability resulted in a skewed class distribution within the dataset. Jump types performed fewer than four times were excluded, resulting in a dataset comprising seven jump classes (straight, 360, cork 3, cork 5, switch cork 5, cork 7, lincoln loop). From each jump, statistical time-domain features were extracted, including mean, sd, min., max., RMS, 25th, 50th and 75th percentiles, and IQR. Models emphasizing interpretability and robustness to imbalance were evaluated, including Balanced Random Forest, XGBoost, and Extremely Randomized Trees. Hyperparameters were optimized using random search with 100 iterations and group 5-fold cross-validation. Model evaluation was performed using leave-one-participant-out cross-validation. Performance metrics included balanced accuracy (BA), weighted F1-score (wF1), and Cohen's kappa (κ), reported as mean and sd across folds. Feature importance was assessed using impurity-based and permutation-importance methods. RESULTS: Models achieved meaningful classification performance despite strong class imbalance. The Balanced Random Forest (BA=0.72, wF1=0.69, κ=0.6) showed the most stable results, while XGBoost (BA=0.66, wF1=0.66, κ=0.6) and Extremely Randomized Trees (BA=0.75, wF1=0.69, κ=0.66) achieved comparable peak performance. Misclassifications occurred predominantly between biomechanically similar jump types, such as 360 and cork 3. Gyroscope-derived features, particularly those related to rotation around the vertical and mediolateral axes, and variability-based descriptors dominated feature importance across all models, highlighting the relevance of rotational dynamics. CONCLUSION: IMU data provide a promising way for classification of Big Air ski jump types in elite athletes, even under imbalanced conditions. These findings support the use of wearable sensors as a practical tool for objective jump analysis in freestyle skiing training and performance monitoring, with future potential to extend towards scoring-related quality metrics, error detection, and more targeted feedback for motor learning and performance evaluation. [1] Snyder et al., Sensors, 2021
Read CV Sebastian MayrECSS Paris 2023: CP-BM14
INTRODUCTION: Freestyle snowboard halfpipe involves complex aerial rotations requiring precise in-flight control. Trampolines provide a safe off-snow environment to develop and stabilize these skills. Biomechanical analyses have shown distinct execution strategies and phase-dependent variability in snowboard aerials [1]. Research on expertise suggests that skill level influences how movement variability is organised and controlled [2]. This study investigates execution variability during trampoline-based snowboard rotations across different skill levels to identify differences between novice and elite athletes and explore indicators of movement consistency that may improve readiness for progression to on-snow training. METHODS: Four elite male snowboard halfpipe athletes (23 ± 4 years; 74 ± 8.8 kg; 178 ± 7.8 cm; 10 ± 9 years experience), members of the German national team competing at an international level (World Cup), performed a total of 181 tricks with rotations of 360° in different directions on a freestyle trampoline using a bounce board. Twelve novices (4 female, 8 male; 23 ± 3 years; 66 ± 6.9 kg; 174 ± 7.9 cm) with an artistic gymnastics background but no halfpipe experience performed 783 trick rotations under the same conditions. The novices learned different 360° rotational tricks through standardised video-based instruction. Body kinematics were captured using inertial motion capture (Xsens, 18 IMUs, 240 Hz). RESULTS: Analyses showed performance-level differences in airtime variability and movement amplitudes, with elite athletes displaying lower coefficients of variation (CV: 5–7%) than novices (CV: 11–17%). Rotational amplitudes were more variable in novices than elites for head motion (CV: 90–152% vs 54–90%) and hip motion (CV: 95–106% vs 79–95%), whereas flexion/extension amplitudes were lower (head: 40–56% vs 26–40%; hip: 34–42% vs 27–34%), indicating more stable coordination in elite athletes. Linear models revealed group effects for hip rotation and flexion/extension amplitudes (all p<0.01), while head amplitudes showed no group differences; peak timing occurred earlier in novices and showed strong group effects for hip and head with additional trick effects (p<0.01). CONCLUSION: Lower execution variability in elite athletes suggests more stable coordination during flight. Quantifying execution stability during trampoline training may support skill learning regarding readiness to progress to on-snow practice. [1] Bacik, B., Kurpas, W., Marszałek, W., Wodarski, P., Sobota, G., Starzyński, M., & Gzik, M. (2020). Movement variability during the flight phase in a single back sideflip (wildcat) in snowboarding. Journal of Human Kinetics, 72(1), 29–38. https://doi.org/10.2478/hukin-2019-0006 [2] Wagner, H., Pfusterschmied, J., Klous, M., von Duvillard, S. P., & Müller, E. (2012). Movement variability and skill level of various throwing techniques. Human Movement Science, 31(1), 78–90. https://doi.org/10.1016/j.humov.2011.05.005
Read CV Lina FayECSS Paris 2023: CP-BM14
INTRODUCTION: Lateral snapping hip syndrome (LSHS) is prevalent in ballet dancers due to repetitive, extreme hip movements. Altered hip control and excessive soft-tissue loading often impair performance in demanding tasks such as the developpe a la seconde. While traditional hip-focused strengthening is common, its impact on dance-specific performance is unclear. Pilates-based training, emphasizing postural alignment and controlled movement, may offer superior support for complex ballet mechanics. This study compared the effects of an 8-week mat Pilates program versus a hip-focused exercise program on muscle stiffness and functional performance in dancers with LSHS. METHODS: In this preliminary randomized controlled trial, four classical ballet dancers with visible or palpable IT band/gluteus maximus snapping over the greater trochanter were assigned to either a mat Pilates group (PG, n=2) or a hip-focused exercise group (HG, n=2). Both groups trained three sessions per week for eight weeks. Assessments included tensor fasciae latae (TFL) stiffness via MyotonPRO, hip muscle strength (handheld dynamometer), TFL flexibility (Ober’s test), lower abdominal endurance, and Dance Functional Outcome Survey (DFOS), and objective kinematics (relative developpe a la seconde angle) using IMU sensors. Data were analyzed using paired t-tests for within-group changes and independent samples t-tests for between-group change scores (p < 0.05). RESULTS: Both groups exhibited leg-specific strength adaptations. Gluteus medius strength increased more in the gesture leg than the support leg for both PG (Delta= 63.5 +/- 44.8 N vs. Delta=36.2+/- 5.6 N) and HG (Delta= 52.2+/-11.1 N vs. Delta=37.9+/- 38.1 N). Between-group differences in strength were not significant. TFL flexibility showed a greater improvement trend in PG (Delta= 9.50 +/- 2.12 deg) compared to HG (Delta= 2.67+/- 1.42 deg; p = 0.078). Crucially, the objective relative developpe a la seconde angle significantly increased in the Pilates group (Delta= 10.49 +/-0.11 deg, p = 0.005), while no significant change occurred in HG (Delta= -16.27 +/- 12.95 deg, p = 0.326). TFL stiffness decreased in both groups (PG: Delta= 157.7 +/-73.1 N/m, p = 0.202; HG: Delta= 108.3 +/-17.0 N/m, p = 0.070) without significant between-group differences (p=0.511). DFOS scores showed descriptive improvements, with PG demonstrating a larger mean increase (Delta= 10.0 +/- 5.7 points) than HG (Delta= 2.5 +/- 0.7 points), though p > 0.05. CONCLUSION: Both interventions appear beneficial for dancers with LSHS. However, Pilates-based training led to a significant improvement in dance-specific kinematics (relative developpe angle) and a trend toward better TFL flexibility compared to hip-focused exercises. These preliminary findings suggest that Pilates may more effectively translate strength gains into functional ballet performance. Larger cohorts are needed to confirm these results.
Read CV CHUAN-JU LIECSS Paris 2023: CP-BM14