26 27 Author Contributions: Conceptualization: J.A.; methodology: J.A.; software: J.A.; validation: J.A.; formal 28 analysis: J.A.; investigation: J.A. and K.M.; resources: J.A.; data curation: J.A.; writing-original draft 29 preparation: J.A. and I.P.S.; writing-review & editing: J.A., M.W., K.M., R.A. and W.S.; visualization: 30 J.A.; supervision: W.S.; project administration: J.A. All authors have read and agreed to the published 31 version of the manuscript. 32 ORCID iD: Abstract 1 This study aims to examine the impact of velocity and acceleration-based differential 2 plyometric jump training on the physical performance of young basketball players. Twenty-six 3 trained young male players (14.5 ± 1.7 years; U14 [n = 14], U16 [n = 5], and U18 [n = 7]) were 4 grouped into experimental and control groups. The experimental group completed two sessions per 5 week of velocity-based differential plyometric training for 14 weeks (3 sets x 5 jumps with 20-s 6 intervals of passive recovery between jumps and 2-min breaks between sets). Before each repetition, 7 participants received verbal instruction to perform a different fluctuation. The control group 8 continued regular training. Bilateral and unilateral Countermovement Jump (CMJ) height, 20 m sprint 9 test, and the Modified 505 Agility (M505) test were evaluated before and after the intervention. The 10 training program yielded statistically significant improvements in the experimental group's CMJ 11 bilateral jump height. Additionally, moderate improvements in the CMJR (Countermovement Jump 12 Right Leg) and M505R (Modified 505 Agility Right) tests (BF10 > 3 to 10) were observed after the 13 training program (δ ranged from 0.66 to 1.12). The control group demonstrated moderate 14 improvements in the M505R (Modified 505 Agility Right) and M505L (Modified 505 Agility Left) 15 tests (BF10 > 3 to 10) (δ = 0.65). Models combining different variables provided the best fit for the 16 data in different physical variables. The results indicate that velocity and acceleration-based 17 differential plyometric training can be a suitable strategy for improving the physical performance of 18 young basketball players. 19

The objective of this study is to assess the efficacy of machine learning (ML) models in predicting different gait speeds using time-normalised vertical ground reaction force (vGRF) data. Time normalisation (e.g., by stance phase) is a common preprocessing step in biomechanics, which aligns data across different recordings and individuals. This is also employed prior to ML classifications. Given that gait speed affects both the duration and vGRF waveforms during the stance phase, with increasing speeds corresponding to reduced stance duration and increased vGRF magnitudes, it is of critical importance to understand the ability of ML methods to model the relationships between gait speed and vGRF.

Background The incorporation of force platform data, i.e., ground reaction force (GRF) and center of pressure (COP), in biomechanical gait analysis requires valid foot contacts on the force platforms. Foot contacts are considered valid if the foot has complete and exclusive contact with a force platform while the other foot does not touch this force platform. Compliance with these criteria is usually assessed subjectively by visual inspection by the person conducting the gait analysis. Research question Can the assessment to distinguish between invalid and valid foot contacts on a force platform during gait analysis be automated using a machine learning model? Methods Twenty healthy participants (10 female and 10 male) underwent gait analysis using GRF and COP measurements during the stance phases on one force platform (Kistler, Switzerland). Six typical cases of invalid foot contacts in force platform measurements were simulated, with simple and difficult valid and invalid foot contacts recorded in each case. Each measurement was classified by two examiners through visual inspection and two video recordings (Qualisys, Sweden) of the lower body. A Support Vector Machine (SVM) was trained to distinguish valid and invalid foot contacts on the force platform based on preprocessed GRF and COP time-series signals. Different combinations of GRF and COP data as input to the SVM were evaluated. Results Using a combination of anterior-posterio and medio-lateral COP as input to the SVM achieved the highest accuracy of 96.6% (100% of simple cases and 93.2% of difficult cases). Significance The development of an automated classification model based on machine learning has the potential to enhance the precision of foot contact assessments on force platforms during gait analysis. This can benefit experimental procedures by improving the quality of data and increasing the usability of (publicly) available datasets through simplified data cleaning.

Despite the development of various motor learning models over many decades, the question of which model is most effective under which conditions to optimize the acquisition of skills remains a heated and recurring debate. This is particularly important in connection with learning sports movements with a high strength component. This study aims to examine the acute effects of various motor learning models on technical efficiency and force production during the Olympic snatch movement. In a within-subject design, sixteen highly active male participants (mean age: 23.13±2.09 years), who were absolute beginners regarding the learning task, engaged in randomized snatch learning bouts, consisting of 36 trials across different learning models: differential learning (DL), contextual interference (serial, sCI; and blocked, bCI), and repetitive learning (RL). Kinematic and kinetic data were collected from three snatch trials executed following each learning bout. Discrete data from the most commonly monitored biomechanical parameters in Olympic weightlifting were analyzed using inferential statistics to identify differences between learning models. The statistical analysis revealed no significant differences between the learning models across all tested parameters, with p-values ranging from 0.236 to 0.99. However, it was observed that only the bouts with an exercise sequence following the DL model resulted in an average antero-posterior displacement of the barbell that matched the optimal displacement. This was characterized by a mean positive displacement towards the lifter during the pulling phases, a negative displacement away from the lifter in the turnover phase, and a return to positive displacement in the catch phase. These findings indicate the limited acute impact of the exercise sequences based on the three motor learning models on Olympic snatch technical efficiency in beginners, yet they hint at a possible slight advantage for the DL model. Coaches might therefore consider incorporating the DL model to potentially enhance technical efficiency, especially during the early stages of skill acquisition. Future research, involving even bigger amounts of exercise noise, longer learning periods, or a greater number of total learning trials and sessions, is essential to verify the potential advantages of the DL model for weightlifting technical efficiency.