Multi-segmental movement patterns reflect juggling complexity and skill level

Comparison of inter-joint coordination strategies during activities of daily living with prosthetic and anatomical limbs

While healthy individuals have redundant degrees of freedom of the joints, they coordinate their multi-joint movements such that the redundancy is effectively reduced. Achieving high inter-joint coordination may be difficult for upper limb prosthesis users due to the lack of proprioceptive feedback and limited motion of the terminal device. This study compared inter-joint coordination between prosthesis users and individuals without limb loss during different upper limb activities of daily living (ADLs). Nine unilateral prosthesis users (five males) and nine age- and sex-matched controls without limb loss completed three unilateral and three bilateral ADLs. Principal component analysis was applied to the three-dimensional motion trajectories of the trunk and arms to identify coordinative patterns. For each ADL, we quantified the cumulative variance accounted for (VAF) of the first five principal components (pcs), which was the lowest number of pcs that could achieve 90% VAF in control limb movements across all ADLs (5 ≤ n ≤ 9). The VAF was lower for movements involving a prosthesis compared to those completed by controls across all ADLs (p < 0.001). The pc waveforms were similar between movements involving a prosthesis and movements completed by control participants for pc1 (r > 0.78, p < 0.001). The magnitude of the relationship for pc2 and pc3 differed between ADLs, with the strongest correlation for symmetric bilateral ADLs (0.67 ≤ r ≤ 0.97, p < 0.001). Collectively, this study demonstrates that activities of daily living were completed with distinct coordination strategies in prosthesis users compared to individuals without limb loss. Future work should explore how device features, such as the availability of sensory feedback or motorized wrist joints influence multi-joint coordination.

Perspective on "in the wild" movement analysis using machine learning

Recent advances in wearable sensing and machine learning have created ample opportunities for "in the wild" movement analysis in sports, since the combination of both enables real-time feedback to be provided to athletes and coaches, as well as long-term monitoring of movements. The potential for real-time feedback is useful for performance enhancement or technique analysis, and can be achieved by training efficient models and implementing them on dedicated hardware. Long-term monitoring of movement can be used for injury prevention, among others. Such applications are often enabled by training a machine learned model from large datasets that have been collected using wearable sensors. Therefore, in this perspective paper, we provide an overview of approaches for studies that aim to analyze sports movement "in the wild" using wearable sensors and machine learning. First, we discuss how a measurement protocol can be set up by answering six questions. Then, we discuss the benefits and pitfalls and provide recommendations for effective training of machine learning models from movement data, focusing on data pre-processing, feature calculation, and model selection and tuning. Finally, we highlight two application domains where "in the wild" data recording was combined with machine learning for injury prevention and technique analysis, respectively.

Quantitative downhill skiing technique analysis according to ski instruction curricula: A proof-of-concept study applying principal component analysis on wearable sensor data

Downhill skiing technique represents the complex coordinative movement patterns needed to control skiing motion. While scientific understanding of skiing technique is still incomplete, not least due to challenges in objectively measuring it, practitioners such as ski instructors have developed sophisticated and comprehensive descriptions of skiing technique. The current paper describes a 3-step proof-of-concept study introducing a technology platform for quantifying skiing technique that utilizes the practitioners’ expert knowledge. The approach utilizes an inertial measurement unit system (Xsens™) and presents a motion analysis algorithm based on the Principal Movement (PM) concept. In step 1, certified ski instructors skied specified technique elements according to technique variations described in ski instruction curricula. The obtained data was used to establish a PM-coordinate system for skiing movements. In step 2, the techniques parallel and carving turns were compared. Step 3 presents a case study where the technique analysis methodology is applied to advise an individual skier on potential technique improvements. All objectives of the study were met, proving the suitability of the proposed technology for scientific and applied technique evaluations of downhill skiing. The underlying conceptual approach - utilizing expert knowledge and skills to generate tailored variability in motion data (step 1) that then dominate the orientation of the PMs, which, in turn, can serve as measures for technique elements of interest - could be applied in many other sports or for other applications in human movement analyses.

Implications of Optimal Feedback Control Theory for Sport Coaching and Motor Learning: A Systematic Review

Best practice in skill acquisition has been informed by motor control theories. The main aim of this study is to screen existing literature on a relatively novel theory, Optimal Feedback Control Theory (OFCT), and to assess how OFCT concepts can be applied in sports and motor learning research. Based on 51 included studies with on average a high methodological quality, we found that different types of training seem to appeal to different control processes within OFCT. The minimum intervention principle (founded in OFCT) was used in many of the reviewed studies, and further investigation might lead to further improvements in sport skill acquisition. However, considering the homogenous nature of the tasks included in the reviewed studies, these ideas and their generalizability should be tested in future studies.

Kinematic patterns during walking in children: Application of principal component analysis

The relative displacements of body segments during walking can be reduced to a small number of multi-joint kinematic patterns, pm_k, through Principal Component Analysis (PCA). These patterns were extracted from two groups of children (n = 8, aged 6-9 years, 4 males, and n = 8, aged 10-13 years, 4 males) and 7 adults (21-29 years, 1 male), walking on a treadmill at various velocities, normalized to body stature (adimensional Froude number, Fr). The three-dimensional coordinates of body markers were captured by an optoelectronic system. Five components (pm₁ to pm₅) explained 99.1% of the original dataset variance. The relationship between the variance explained ("size") of each pm_k and the Fr velocity varied across movement components and age groups. Only pm₁ and pm₂, which described kinematic patterns in the sagittal plane, showed significant differences (at p < 0.05) across pairs of age groups. The time course of the size of all the five components matched various mechanical events of the step cycle at the level of both body system and lower limb joints. Such movement components appeared clinically interpretable and lend themselves as potential markers of neural development of walking.

Decomposing spontaneous sign language into elementary movements: A principal component analysis-based approach

Sign Language (SL) is a continuous and complex stream of multiple body movement features. That raises the challenging issue of providing efficient computational models for the description and analysis of these movements. In the present paper, we used Principal Component Analysis (PCA) to decompose SL motion into elementary movements called principal movements (PMs). PCA was applied to the upper-body motion capture data of six different signers freely producing discourses in French Sign Language. Common PMs were extracted from the whole dataset containing all signers, while individual PMs were extracted separately from the data of individual signers. This study provides three main findings: (1) although the data were not synchronized in time across signers and discourses, the first eight common PMs contained 94.6% of the variance of the movements; (2) the number of PMs that represented 94.6% of the variance was nearly the same for individual as for common PMs; (3) the PM subspaces were highly similar across signers. These results suggest that upper-body motion in unconstrained continuous SL discourses can be described through the dynamic combination of a reduced number of elementary movements. This opens up promising perspectives toward providing efficient automatic SL processing tools based on heavy mocap datasets, in particular for automatic recognition and generation.

Gymnastics Experience Enhances the Development of Bipedal-Stance Multi-Segmental Coordination and Control During Proprioceptive Reweighting

Performance and control of upright bipedal posture requires a constant and dynamic integration of relative contributions of different sensory inputs (i. e., sensory reweighting) to enable effective adaptations as individuals face environmental changes and perturbations. Children with gymnastic experience showed balance performance closer to that of adults during and after proprioceptive alteration than children without gymnastic experience when their center of pressure (COP) was analyzed. However, a particular COP sway can be achieved through performing and coordinating different postural movements. The aim of this study was to assess how children and adults of different gymnastic experience perform and control postural movements while they have to adjust balance during and after bilateral tendon vibration. All participants were equipped with spherical markers attached to their skin and two vibrators strapped over the Achilles tendons. Bipedal stance was performed in three 45-s trials in two visual conditions (eyes open, EO, and eyes closed, EC) ordered randomly in which vibration lasted 10 s. Posture movements were analyzed by a principal component analysis (PCA) calculated on normalized and weighted markers coordinates. The relative standard deviation of each principal movement component (principal position, PP-rSTD) quantified its contribution to the whole postural movements, i.e., quantified the coordinative structure. The first (principal velocities, PV-rSTD) and second (principal accelerations, PA-rSTD) time-derivatives characterized the rate-dependent sensory information associated with and the neuromuscular control of the postural movements, respectively. Children without gymnastic experience showed a different postural coordinative structure and different sensory-motor control characteristics. They used less ankle movements in the anterior-posterior direction but increased ankle movements in medio-lateral direction, presented larger hip and trunk velocities, and exhibited more hip actions. Gymnastic experience during childhood seemed to benefit the development of proprioceptive reweighting processes in children, leading to a more mature form of coordinating and controlling posture similarly to adults.

Multi-segmental postural control patterns in down syndrome

BACKGROUND

Patients with Down Syndrome (DS) exhibit less efficient and unstable standing postural control. The specificities of somatosensorial deficits might result in a different utilization of resources and in distinct whole-body kinematic patterns, to date still unexplored. In this paper we aim at addressing multi-segmental coordination patterns in people with DS while maintaining standing balance under different visual conditions (open and closed eyes).

METHODS

This cross-sectional observational cohort study involved two groups of 23 patients with DS and 12 healthy controls. A 30-s standing balance test allowed to extract (i) the length of the trajectory of the center-of-pressure sway and 95% confidence ellipse area from Ground Reaction forces, and (ii) Principal Movement (PM) components from full-body motion kinematics; the latter were obtained exploiting a Principal Component Analysis-based approach, also embracing a motor-control perspective through the evaluation of the number of modifications applied by the neuromuscular controller on segments' acceleration.

FINDINGS

Trajectory length was significantly higher in patients; 95% ellipse confidence area did not differ between groups/condition. Postural movement components differed in people with DS from healthy controls not only in the "observable", behavioural phenotype (PM3 and PM8), but also in the amount of activation of the associated control (PM1 to PM8, over-activated in DS) in all spatial directions.

INTERPRETATION

Results reinforced the prevalence of a medio-lateral hip strategy (instead of an ankle strategy) in maintaining postural stability. Most important, they revealed a less frequent activation of postural patterns in all spatial directions.

Modularity in Motor Control: Similarities in Kinematic Synergies Across Varying Locomotion Tasks

Kinematic synergies (kSYN) provide an approach to quantify the covariation of joint motions and to explain the mechanisms underlying human motor behavior. A low-dimensional control strategy by means of the activation of a moderate number of kSYN would simplify the performance of complex motor tasks. The purpose of this study was to examine similarities between the kSYN of varying locomotion tasks: straight-line walking, walking a 90° spin turn and walking upstairs. Task-specific kSYN were extracted from full body kinematic recordings of 13 participants by principal component analysis. The first five kSYN accounting for most of the variance within each task were selected for further analysis following previous studies. The similarities between the kSYN of the three different locomotion tasks were quantified by calculating cosine similarities (SIM), as a vector-based similarity measure ranging from 0 (no similarity) to 1 (high similarity), between absolute principal component loading vectors. A SIM between two kSYN > 0.8 was interpreted as highly similar. Two to three highly similar kSYN were identified when comparing two individual tasks with each other. One kSYN, primarily characterized by anteversion and retroversion of the arms and legs, were found to be similar in all three tasks. Additional kSYN that occurred between individual tasks reflected mainly an upwards/downwards movement of the body or a countercyclical knee flexion/extension. The results demonstrate that the three investigated locomotion tasks are characterized by kSYN and that certain kSYN repeatedly occur across the three locomotion tasks. PCA yields kSYN which are in descent order according to their amount of total variance accounted for. Referring to the placing of a kSYN within the order as priorization, we found a change in priorization of repeatedly occurring kSYN across the individual tasks. The findings support the idea that movements can be efficiently performed through a flexible combination of a lower number of control-relevant variables.

Task Demand Changes Motor Control Strategies in Vertical Jumping

The purpose of this study was to examine the motor control strategies employed to control the degrees of freedom when performing a lower limb task with constraints applied at the hip, knee, and ankle. Thirty-five individuals performed vertical jumping tasks: hip flexed, no knee bend, and plantar flexed. Joint moment data from the hip, knee, and ankle were analyzed using principal component analysis (PCA). In all PCA performed, a minimum of two and maximum of six principal components (PC) were required to describe the movements. Similar reductions in dimensionality were observed in the hip flexed and no knee bend conditions (3PCs), compared to the plantar flexed condition (5PCs). A proximal to distal reduction in variability was observed for the hip flexed and no knee bend conditions but not for the plantar flexed condition. Collectively, the results suggest a reduction in the dimensionality of the movement occurs despite the constraints imposed within each condition and would suggest that dimensionality reduction and motor control strategies are a function of the task demands.

Analysis of Postural Control Using Principal Component Analysis: The Relevance of Postural Accelerations and of Their Frequency Dependency for Selecting the Number of Movement Components

One criterion when selecting the number of principal components (PCs) to be considered in a principal component analysis (PCA) is the fraction of overall variance that each PC represents. When applying a PCA to kinematic marker data in postural control research, this criterion relates to the amplitude of postural changes, recently often called "principal (postural) positions" (PPs). However, in the assessment of postural control, important aspects are also how fast posture changes and the acceleration of postural changes, i.e., "principal accelerations" (PAs). The current study compared how much of the total position variance each PP explained (PP_rVAR) and how much of the total acceleration variance each PA explained (PA_rVAR). Furthermore, the frequency content of PP and PA signals were evaluated. Postural movements of 26 participants standing on stable ground or balancing on a multiaxial balance board were analyzed by applying a PCA on 90 marker coordinates. For each PC, PP_rVAR, PA_rVAR, and the Fourier transformations of the PP and PA time series were calculated. The PP_rVAR and the PA_rVAR-distributions differed substantially. The PP-frequency domain was observed well below 5 Hz, the PA-frequency domain up to 5 Hz for stable standing and up to 10 Hz on the balance board. These results confirm that small-amplitude but fast movement components can have a higher impact on postural accelerations-and thus on the forces active in the system-than large-amplitude but slow lower-order movement components. Thus, PA variance and its dependence on filter frequencies should be considered in dimensionality reduction decisions.

Evaluation of Pattern Recognition Methods for Head Gesture-Based Interface of a Virtual Reality Helmet Equipped with a Single IMU Sensor

The motivation of this paper is to examine the effectiveness of state-of-the-art and newly proposed motion capture pattern recognition methods in the task of head gesture classifications. The head gestures are designed for a user interface that utilizes a virtual reality helmet equipped with an internal measurement unit (IMU) sensor that has 6-axis accelerometer and gyroscope. We will validate a classifier that uses Principal Components Analysis (PCA)-based features with various numbers of dimensions, a two-stage PCA-based method, a feedforward artificial neural network, and random forest. Moreover, we will also propose a Dynamic Time Warping (DTW) classifier trained with extension of DTW Barycenter Averaging (DBA) algorithm that utilizes quaternion averaging and a bagged variation of previous method (DTWb) that utilizes many DTW classifiers that perform voting. The evaluation has been performed on 975 head gesture recordings in seven classes acquired from 12 persons. The highest value of recognition rate in a leave-one-out test has been obtained for DTWb and it equals 0.975 (0.026 better than the best of state-of-the-art methods to which we have compared our approach). Among the most important applications of the proposed method is improving life quality for people who are disabled below the neck by supporting, for example, an assistive autonomous power chair with a head gesture interface or remote controlled interfaces in robotics.

Improving Human Motion Classification by Applying Bagging and Symmetry to PCA-Based Features

This paper proposes a method for improving human motion classification by applying bagging and symmetry to Principal Component Analysis (PCA)-based features. In contrast to well-known bagging algorithms such as random forest, the proposed method recalculates the motion features for each “weak classifier” (it does not randomly sample a feature set). The proposed classification method was evaluated on a challenging (even to a human observer) motion capture recording dataset of martial arts techniques performed by professional karate sportspeople. The dataset consisted of 360 recordings in 12 motion classes. Because some classes of these motions might be symmetrical (which means that they are performed with a dominant left or right hand/leg), an analysis was conducted to determine whether accounting for symmetry could improve the recognition rate of a classifier. The experimental results show that applying the proposed classifiers’ bagging procedure increased the recognition rate (RR) of the Nearest-Neighbor (NNg) and Support Vector Machine (SVM) classifiers by more than 5% and 3%, respectively. The RR of one trained classifier (SVM) was higher when we did not use symmetry. On the other hand, the application of symmetry information for bagged NNg improved its recognition rate compared with the results without symmetry information. We can conclude that symmetry information might be helpful in situations in which it is not possible to optimize the decision borders of the classifier (for example, when we do not have direct information about class labels). The experiment presented in this paper shows that, in this case, bagging and mirroring might help find a similar object in the training set that shares the same class label. Both the dataset that was used for the evaluation and the implementation of the proposed method can be downloaded, so the experiment is easily reproducible.

Principal Component Analysis Reveals the Proximal to Distal Pattern in Vertical Jumping Is Governed by Two Functional Degrees of Freedom

The successful completion of motor tasks requires effective control of multiple degrees of freedom (DOF), with adaptations occurring as a function of varying performance constraints. In this study we sought to compare the emergent coordination strategies employed in vertical jumping under different task constraints [countermovement jump (CMJ) with arm swing-CMJas and no arm swing-CMJnas]. In order to achieve this, principal component analysis (PCA) was conducted on joint moment waveform data from the hip, knee and ankle. This statistical approach has the advantage of analyzing the whole movement within a time series and reduces multidimensional datasets to lower dimensions for analysis. Both individual and group analyses were conducted. For individual analysis, PCA was conducted on combined hip, knee, and ankle joint moment data for each individual across both CMJnas (thirty-eight participants), and CMJas (twenty-two participants) conditions. PCA was also performed comparing all data from each individual across CMJnas and CMJas conditions. The results revealed a maximum of three principal components (PC) explained over 90% of the variance in the data sets for both conditions and within individual and group analyses. For individual analysis, no more than 2PCs were required for both conditions. For group analysis, CMJas required 3PCs to explain over 90% of the variance within the dataset and CMJnas only required 2PCs. Reconstruction of the original NJM waveforms from the PCA output demonstrates a greater loading of hip and knee joint moments to PC1, with PC2 showing a greater loading to ankle joint moment. The reduction in dimensions of the original data shows the proximal to distal extension pattern in the sagittal plane, typical of vertical jumping tasks, is governed by only 2 functional DOF, at both a group, and individual level, rather than the typically reported 3 mechanical DOF in some forms of jumping.

Down Syndrome: Gait Pattern Alterations in Posture Space Kinematics

Gait characteristics in Down syndrome (DS) are documented in terms of discrete kinematic variables. However, such features are strictly interrelated and reflect neurological and developmental delays. A phenotypical, quantitative assessment of how multi-joint walking patterns are activated and controlled during gait would enhance the understanding of locomotor mechanisms in such patients. We adopted an analysis framework based on principal component analysis: the gait kinematics of 221 patients aged 6-45 were expressed in terms of a reduced set of one-dimensional movement components. Their time course during the gait cycle was described by score vectors, here called principal positions; its second time derivative, called principal acceleration, characterized the activity of the neuromuscular controller on each component. Outcomes were compared to an age-matched group of 49 healthy individuals. After controlling for the effect of walking speed, we observed that the main alterations in gait patterns emerged in the fourth component which is mostly devoted to stability management (group differences, p < 0.001). Rather, the main sagittal-plane locomotor patterns showed only subtle differences from the control group. Using statistical parametrical mapping, we found when (step-to-step transitions) and how (interrelated joints motion) the fourth movement deviated from normal: in particular, an excessive hip adduction and trunk inclination during the transition between single and double support phases. These findings match the neurological and sensorimotor trait of DS and suggest the promotion of targeted rehabilitative interventions. Furthermore, this paper opens to the adoption of principal positions and principal accelerations to investigate the neuromuscular control of movement patterns during locomotion.

PManalyzer: A Software Facilitating the Study of Sensorimotor Control of Whole-Body Movements

Motion analysis is used to study the functionality or dysfunctionality of the neuromuscular system, as human movements are the direct outcome of neuromuscular control. However, motion analysis often relies on measures that quantify simplified aspects of a motion, such as specific joint angles, despite the well-known complexity of segment interactions. In contrast, analyzing whole-body movement patterns may offer a new understanding of movement coordination and movement performance. Clinical research and sports technique evaluations suggest that principal component analysis (PCA) provides novel and valuable insights into control aspects of the neuromuscular system and how they relate to coordinative patterns. However, the implementation of PCA computations are time consuming, and require mathematical knowledge and programming skills, drastically limiting its application in current research. Therefore, the aim of this study is to present the Matlab software tool "PManalyzer" to facilitate and encourage the application of state-of-the-art PCA concepts in human movement science. The generalized PCA concepts implemented in the PManalyzer allow users to apply a variety of marker set independent PCA-variables on any kinematic data and to visualize the results with customizable plots. In addition, the extracted movement patterns can be explored with video options that may help testing hypotheses related to the interplay of segments. Furthermore, the software can be easily modified and adapted to any specific application.

The Effect of Cognitive Resource Competition Due to Dual-Tasking on the Irregularity and Control of Postural Movement Components

Postural control research suggests a non-linear, n-shaped relationship between dual-tasking and postural stability. Nevertheless, the extent of this relationship remains unclear. Since kinematic principal component analysis has offered novel approaches to study the control of movement components (PM) and n-shapes have been found in measures of sway irregularity, we hypothesized (H1) that the irregularity of PMs and their respective control, and the control tightness will display the n-shape. Furthermore, according to the minimal intervention principle (H2) different PMs should be affected differently. Finally, (H3) we expected stronger dual-tasking effects in the older population, due to limited cognitive resources. We measured the kinematics of forty-one healthy volunteers (23 aged 26 ± 3; 18 aged 59 ± 4) performing 80 s tandem stances in five conditions (single-task and auditory n-back task; n = 1–4), and computed sample entropies on PM time-series and two novel measures of control tightness. In the PM most critical for stability, the control tightness decreased steadily, and in contrast to H3, decreased further for the younger group. Nevertheless, we found n-shapes in most variables with differing magnitudes, supporting H1 and H2. These results suggest that the control tightness might deteriorate steadily with increased cognitive load in critical movements despite the otherwise eminent n-shaped relationship.

Age Effects in Postural Control Analyzed via a Principal Component Analysis of Kinematic Data and Interpreted in Relation to Predictions of the Optimal Feedback Control Theory

Optimal feedback control theory suggests that control of movement is focused on movement dimensions that are important for the task's success. The current study tested the hypotheses that age effects would emerge in the control of only specific movement components and that these components would be linked to the task relevance. Fifty healthy volunteers, 25 young and 25 older adults, performed a 80s-tandem stance while their postural movements were recorded using a standard motion capture system. The postural movements were decomposed by a principal component analysis into one-dimensional movement components, PM_k, whose control was assessed through two variables, N_k and σ_k, which characterized the tightness and the regularity of the neuro-muscular control, respectively. The older volunteers showed less tight and more irregular control in PM₂ (N₂: -9.2%, p = 0.007; σ₂: +14.3.0%, p = 0.017) but tighter control in PM₈ and PM₉ (N₈: +4.7%, p = 0.020; N₉: +2.5%, p = 0.043; σ₉: -8.8%, p = 0.025). These results suggest that aging effects alter the postural control system not as a whole, but emerge in specific, task relevant components. The findings of the current study thus support the hypothesis that the minimal intervention principle, as described in the context of optimal feedback control (OFC), may be relevant when assessing aging effects on postural control.

Cross-country skiing movement factorization to explore relationships between skiing economy and athletes' skills

We investigated the relationships between the biomechanics of the double poling (DP) technique in cross-country skiing, its economy, and athletes' skill. To this aim, skiers' motion has been factorized into components through principal component analysis (PCA). Eight high-level (HL) and eight regional level (RL) male cross-country skiers performed a 5-minute submaximal DP trial while roller skiing on a treadmill at 14 km h^-1 and 2° incline. Whole-body kinematics was recorded with a motion capture system. PCA was applied to markers coordinates to extract principal movements (PM_k ), which were ranked by their variance. Energy cost (EC) of locomotion was calculated from ergospirometric measurements. Results showed that 96.7%±0.6% of total skiing pattern variance can be described with the first three PM_k. (Shoulder and trunk flexion-extension are described PM₁ and PM₂ and elbow flexion-extension are mainly represented in PM₂ and PM_3. The variance of further components, consisting of residual movements (eg, slow postural changes or high-frequency vibrations), was greater for the RL than the HL skiers (4.0%±0.5% vs 2.6%±0.3%; P<.001) and was positively correlated with EC (R² =.646; P<.001). PCA permitted to describe the biomechanics of the DP technique through a limited set of principal movements. Skiing skills and economy appeared to be related to a skier's ability to simplify movement complexity, suggesting that an efficient skier is better able to reduce superfluous movement components during DP.