Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle-consistent generative adversarial networks.

In recent years, the analysis of movement patterns has increasingly focused on the individuality of movements. After long speculations about weak individuality, strong individuality is now accepted, and the first situation-dependent fine structures within it are already identified. Methodologically, however, only signals of the same movements have been compared so far. The goal of this work is to detect cross-movement commonalities of individual walking, running, and handwriting patterns using data augmentation. A total of 17 healthy adults (35.8 ± 11.1 years, eight women and nine men) each performed 627.9 ± 129.0 walking strides, 962.9 ± 182.0 running strides, and 59.25 ± 1.8 handwritings. Using the conditional cycle-consistent generative adversarial network (CycleGAN), conditioned on the participant's class, a pairwise transformation between the vertical ground reaction force during walking and running and the vertical pen pressure during handwriting was learned in the first step. In the second step, the original data of the respective movements were used to artificially generate the other movement data. In the third step, whether the artificially generated data could be correctly assigned to a person via classification using a support vector machine trained with original data of the movement was tested. The classification F1-score ranged from 46.8% for handwriting data generated from walking data to 98.9% for walking data generated from running data. Thus, cross-movement individual patterns could be identified. Therefore, the methodology presented in this study may help to enable cross-movement analysis and the artificial generation of larger amounts of data.

Resonance Effects in Variable Practice for Handball, Basketball, and Volleyball Skills: A Study on Contextual Interference and Differential Learning.

Effective sports training should be attuned to the athlete's specific conditionings and characteristics. In motor learning research, two often neglected factors that influence this resonance are the learner's athletic background and the structural diversity of exercises (e.g., relative similarity). In the setting of real-word training with higher external validity, this study examines the effects of three learning approaches (i.e., contextual interference (CI), differential learning (DL), and free-play control condition (CO)) on the parallel learning of handball (HB), volleyball (VB), and basketball (BB) skills, considering participants' prior sport backgrounds. Forty-five males (15 HB, 15 VB, and 15 BB players) with a mean age of 22 ± 1.4 years and at least 6 years of experience in the mastered discipline voluntarily participated in this study. A pre-post-retention test design including a 6-week-intervention program was employed. During the intervention period, participants engaged in three training sessions a week, with each one lasting approximately 80 min. Each of the three test sessions involved the execution of ten attempts of BB free-throw shooting, HB three-step goal throwing, and VB underarm passing following a blocked order. In terms of short-term (pre-post) gain, only the DL group significantly improved their performance in both non-mastered disciplines (p = 0.03, ES = 1.58 for the BB free-throw and p = 0.05, ES = 0.9 for the HB shooting tests), with a trend (ES = 0.53) towards an improvement in the performance of the mastered VB underarm-pass skill. In terms of relatively permanent gains, the CI group significantly improved their performances from pre- to retention test only in the non-mastered BB free-throw skill (p = 0.018, ES = 1.17). In contrast, the DL group significantly improved their performance at retention compared to the pre-test in both non-mastered BB (p = 0.004, ES = 1.65) and HB (p = 0.003, ES = 2.15) skills, with a trend (ES = 0.4) towards improvement in the mastered VB test. In both the short-term and relatively long-term, higher composite score gains were observed in DL compared to CI (p = 0.006, ES = 1.11 and 0.049, ES = 1.01) and CO (p = 0.001, ES = 1.73 and <0.0001, ES = 2.67). In conclusion, the present findings provide additional support for the potential advantages of the DL model over those of CI. These findings can serve as the basis for tailored training and intervention strategies and provide a new perspective for addressing various issues related to individual and situational learning.

Learning Multiple Movements in Parallel-Accurately and in Random Order, or Each with Added Noise?

Traditionally, studies on learning have mainly focused on the acquisition and stabilization of only single movement tasks. In everyday life and in sports, however, several new skills often must be learned in parallel. The extent to which the similarity of the movements or the order in which they are learned influences success has only recently begun to attract increased interest. This study aimed to compare the effects of CI in random practice order (high CI) with differential learning (DL) in learning three volleyball skills in parallel. Thirty-two advanced beginners in volleyball (mean age = 24, SD = 2.7) voluntarily participated in the study. Within a pre-, post-, retention test design, an intervention of six weeks and one week retention phase, the effects of three practice protocols of a CI, DL, and control (CO) group were compared. Three different volleyball skills (underhand pass, overhand pass, and overhand serve) were trained with emphasis on accuracy. Results showed statistically significant higher rates of improvement in the acquisition and learning phases for the DL group compared to the CI and CO groups. The differences were associated with moderate to high effect sizes in all individual skills and in the combined skills. The findings show more agreement with DL than with CI theory.

Cognitive Enhancement through Differential Rope Skipping after Math Lesson.

Numerous studies have shown cognitive enhancement through sport and physical exercise. Despite the variety of studies, the extent to which physical activity before or after a cognitive learning session leads to more effective cognitive enhancement remains largely unresolved. Moreover, little attention has been paid to the dependence of the motor learning approach then applied. In this study, we compare the influence of differential with uniformly rope skipping directly succeeding an acquisition phase in arithmetic mathematics. For three weeks 26 pupils, 14 female, 12 male, and 13.9 ± 0.7 years old, completed nine 15 min exercises in arithmetic math, each followed by 3 min rope skipping with heart rate measurement. Arithmetic performance was tested in a pre-, post- and retention test design. The results showed a statistically significant difference between the differential and the control groups within the development of arithmetic performance, especially in the retention test. There was no statistical difference in heart rate. It is suggested that the results provide evidence for sustainable improvements of cognitive learning performance by means of highly variable rope skipping.

Repetition without Repetition or Differential Learning of Multiple Techniques in Volleyball?

A variety of approaches have been proposed for teaching several volleyball techniques to beginners, ranging from general ball familiarization to model-oriented repetition to highly variable learning. This study compared the effects of acquiring three volleyball techniques in parallel with three approaches. Female secondary school students (N = 42; 15.6 ± 0.54 years) participated in a pretest for three different volleyball techniques (underhand pass, overhand pass, and overhead serve) with an emphasis on accuracy. Based on their results, they were parallelized into three practice protocols, a repetitive learning group (RG), a differential learning group (DG), and a control group (CG). After a period of six weeks with 12 intervention sessions, all participants attended a posttest. An additional retention test after two weeks revealed a statistically significant difference between DG, RG, and CG for all single techniques as well as the combined multiple technique. In each technique-the overhand pass, the underhand pass, the overhand service, and the combination of the three techniques-DG performed best (each p < 0.001).

Fatigue-Related and Timescale-Dependent Changes in Individual Movement Patterns Identified Using Support Vector Machine.

The scientific and practical fields-especially high-performance sports-increasingly request a stronger focus be placed on individual athletes in human movement science research. Machine learning methods have shown efficacy in this context by identifying the unique movement patterns of individuals and distinguishing their intra-individual changes over time. The objective of this investigation is to analyze biomechanically described movement patterns during the fatigue-related accumulation process within a single training session of a high number of repeated executions of a ballistic sports movement-specifically, the frontal foot kick (mae-geri) in karate-in expert athletes. The two leading research questions presented for consideration are (1) Can characteristics of individual movement patterns be observed throughout the entire training session despite continuous changes, i.e., even as fatigue-related processes increase? and (2) How do intra-individual movement patterns change as fatigue-related processes increase throughout a training session? Sixteen expert karatekas performed 606 frontal foot kicks directed toward an imaginary target. The kicks were performed in nine sets at 80% (K-80) of the self-experienced maximal intensity. In addition, six kicks at maximal intensity (K-100) were performed after each of the nine sets. Between the sets, the participants took a 90-s break. Three-dimensional full-body kinematic data of all kicks were recorded with 10 infrared cameras. The normalized waveforms of nine upper- and lower-body joint angles were classified using a supervised machine learning method (support vector machine). The results of the classification revealed a disjunct distinction between the kinematic movement patterns of individual athletes. The identification of unique movement patterns of individual athletes was independent of the intensity and the degree of fatigue-related processes. In other words, even with the accumulation of fatigue-related processes, the unique movement patterns of an individual athlete can be clearly identified. During the training session, changes in intra-individual movement patterns could also be detected, indicating the occurrence of adaptations in individual movement patterns throughout the fatigue-related accumulation process. The results suggest that these adaptations can be modeled in terms of changes in patterns rather than increasing variance. Practical consequences are critically discussed.

Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Performance of Gait Classifications Using Machine Learning.

Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Therefore, the future of human movement analysis requires procedures that enhance the classification of movement patterns into relevant groups and support practitioners in their decisions. In this regard, the use of data-driven techniques seems to be particularly suitable to generate classification models. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution, e.g., in increasing the classification performance. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification performance. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification performance of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy participants performed 6 sessions of 15 gait trials for 1 day. For each trial, two force plates recorded the three-dimensional ground reaction forces (GRFs). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each preprocessing step were analyzed by comparing their prediction performance in a six-session classification using Support Vector Machines, Random Forest Classifiers, Multi-Layer Perceptrons, and Convolutional Neural Networks. The results indicate that filtering GRF data and a supervised data reduction (e.g., using Principal Components Analysis) lead to increased prediction performance of the machine-learning classifiers. Interestingly, the weight normalization and the number of data points (above a certain minimum) in the time normalization does not have a substantial effect. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.