Identifying patterns in trunk/head/elbow changes of riders and non-riders: A cluster analysis approach.

Correct rider oscillation and position are the basics for a good horseback riding performance. In this paper, we propose a framework for the automatic analysis of athletes behaviour based on cluster analysis. Two groups of athletes (riders vs non-riders) were assigned to a horseback riding simulator exercise. The participants exercised four different incremental horse oscillation frequencies. This paper studies the postural coordination, by computing the different discrete relative phases of head-horse, elbow-horse and trunk-horse oscillations. Two clustering algorithms are then applied to automatically identify the change of rider and non-rider behaviour in terms of postural coordination. The results showed that the postural coordination was influenced by the level of rider expertise. More diverse behaviour was observed for non-riders. At the opposite, riders produced lower postural displacements and deployed more efficient postural control. The postural coordination for both groups was also influenced by the oscillation frequencies.

Evaluating transfer prediction using machine learning for skill acquisition study under various practice conditions.

Recent research highlighted the interest in 1) investigating the effect of variable practice on the dynamics of learning and 2) modeling the dynamics of motor skill learning to enhance understanding of individual pathways learners. Such modeling has not been suitable for predicting future performance, both in terms of retention and transfer to new tasks. The present study attempted to quantify, by means of a machine learning algorithm, the prediction of skill transfer for three practice conditions in a climbing task: constant practice (without any modifications applied during learning), imposed variable practice (with graded contextual modifications, i.e., the variants of the climbing route), and self-controlled variable practice (participants were given some control over their variant practice schedule). The proposed pipeline allowed us to measure the fitness of the test to the dataset, i.e., the ability of the dataset to be predictive of the skill transfer test. Behavioral data are difficult to model with statistical learning and tend to be 1) scarce (too modest data sample in comparison with the machine learning standards) and 2) flawed (data tend to contain voids in measurements). Despite these adversities, we were nevertheless able to develop a machine learning pipeline for behavioral data. The main findings demonstrate that the level of learning transfer varies, according to the type of practice that the dynamics pertain: we found that the self-controlled condition is more predictive of generalization ability in learners than the constant condition.

Affordance Realization in Climbing: Learning and Transfer.

The aim of this study was to investigate how the affordances of an indoor climbing wall changed for intermediate climbers following a period of practice during which hold orientation was manipulated within a learning and transfer protocol. The learning protocol consisted of four sessions, in which eight climbers randomly ascended three different routes of fixed absolute difficulty (5c on the French scale), as fluently as possible. All three routes were 10.3 m in height and composed of 20 hand-holds at the same locations on an artificial climbing wall; only hold orientations were altered: (i) a horizontal-edge route (H) was designed to afford horizontal hold grasping, (ii) a vertical-edge route (V) afforded vertical hold grasping, and (iii), a double-edge route (D) was designed to afford both horizontal and vertical hold grasping. Five inertial measurement units (IMU) (3D accelerometer, 3D gyroscope, 3D magnetometer) were attached to the hip, feet and forearms to analyze the vertical acceleration and direction (3D unitary vector) of each limb and hip in ambient space during the entire ascent. Segmentation and classification processes supported detection of movement and stationary phases for each IMU. Depending on whether limbs and/or hip were moving, a decision tree distinguished four states of behavior: stationary (absence of limb and hip motion), hold exploration (absence of hip motion but at least one limb in motion), hip movement (hip in motion but absence of limb motion) and global motion (hip in motion and at least one limb in motion). Results showed that with practice, the learners decreased the relative duration of hold exploration, suggesting that they improved affordance perception of hold grasp-ability. The number of performatory movements also decreased as performance increased during learning sessions, confirming that participants' climbing efficacy improved as a function of practice. Last, the results were more marked for the H route, while the D route led to longer relative stationary duration and a shorter relative duration of performatory states. Together, these findings emphasized the benefit of manipulating task constraints to promote safe exploration during learning, which is particularly relevant in extreme sports involving climbing tasks.

Spotting L3 slice in CT scans using deep convolutional network and transfer learning.

In this article, we present a complete automated system for spotting a particular slice in a complete 3D Computed Tomography exam (CT scan). Our approach does not require any assumptions on which part of the patient's body is covered by the scan. It relies on an original machine learning regression approach. Our models are learned using the transfer learning trick by exploiting deep architectures that have been pre-trained on imageNet database, and therefore it requires very little annotation for its training. The whole pipeline consists of three steps: i) conversion of the CT scans into Maximum Intensity Projection (MIP) images, ii) prediction from a Convolutional Neural Network (CNN) applied in a sliding window fashion over the MIP image, and iii) robust analysis of the prediction sequence to predict the height of the desired slice within the whole CT scan. Our approach is applied to the detection of the third lumbar vertebra (L3) slice that has been found to be representative to the whole body composition. Our system is evaluated on a database collected in our clinical center, containing 642 CT scans from different patients. We obtained an average localization error of 1.91±2.69 slices (less than 5 mm) in an average time of less than 2.5 s/CT scan, allowing integration of the proposed system into daily clinical routines.

Climbing skill and complexity of climbing wall design: assessment of jerk as a novel indicator of performance fluency.

This study investigated a new performance indicator to assess climbing fluency (smoothness of the hip trajectory and orientation of a climber using normalized jerk coefficients) to explore effects of practice and hold design on performance. Eight experienced climbers completed four repetitions of two, 10-m high routes with similar difficulty levels, but varying in hold graspability (holds with one edge vs holds with two edges). An inertial measurement unit was attached to the hips of each climber to collect 3D acceleration and 3D orientation data to compute jerk coefficients. Results showed high correlations (r = .99, P < .05) between the normalized jerk coefficient of hip trajectory and orientation. Results showed higher normalized jerk coefficients for the route with two graspable edges, perhaps due to more complex route finding and action regulation behaviors. This effect decreased with practice. Jerk coefficient of hip trajectory and orientation could be a useful indicator of climbing fluency for coaches as its computation takes into account both spatial and temporal parameters (ie, changes in both climbing trajectory and time to travel this trajectory).

Neurobiological degeneracy and affordance perception support functional intra-individual variability of inter-limb coordination during ice climbing.

This study investigated the functional intra-individual movement variability of ice climbers differing in skill level to understand how icefall properties were used by participants as affordances to adapt inter-limb coordination patterns during performance. Seven expert climbers and seven beginners were observed as they climbed a 30 m icefall. Movement and positioning of the left and right hand ice tools, crampons and the climber's pelvis over the first 20 m of the climb were recorded and digitized using video footage from a camera (25 Hz) located perpendicular to the plane of the icefall. Inter-limb coordination, frequency and types of action and vertical axis pelvis displacement exhibited by each climber were analysed for the first five minutes of ascent. Participant perception of climbing affordances was assessed through: (i) calculating the ratio between exploratory movements and performed actions, and (ii), identifying, by self-confrontation interviews, the perceptual variables of environmental properties, which were significant to climbers for their actions. Data revealed that experts used a wider range of upper and lower limb coordination patterns, resulting in the emergence of different types of action and fewer exploratory movements, suggesting that effective holes in the icefall provided affordances to regulate performance. In contrast, beginners displayed lower levels of functional intra-individual variability of motor organization, due to repetitive swinging of ice tools and kicking of crampons to achieve and maintain a deep anchorage, suggesting lack of perceptual attunement and calibration to environmental properties to support climbing performance.

A dynamical system perspective to understanding badminton singles game play.

By altering the task constraints of cooperative and competitive game contexts in badminton, insights can be obtained from a dynamical systems perspective to investigate the underlying processes that results in either a gradual shift or transition of playing patterns. Positional data of three pairs of skilled female badminton players (average age 20.5±1.38years) were captured and analyzed. Local correlation coefficient, which provides information on the relationship of players' displacement data, between each pair of players was computed for angle and distance from base position. Speed scalar product was in turn established from speed vectors of the players. The results revealed two patterns of playing behaviors (i.e., in-phase and anti-phase patterns) for movement displacement. Anti-phase relation was the dominant coupling pattern for speed scalar relationships among the pairs of players. Speed scalar product, as a collective variable, was different between cooperative and competitive plays with a greater variability in amplitude seen in competitive plays leading to a winning point. The findings from this study provide evidence for increasing stroke variability to perturb existing stable patterns of play and highlights the potential for speed scalar product to be a collective variable to distinguish different patterns of play (e.g., cooperative and competitive).

Data modelling reveals inter-individual variability of front crawl swimming.

OBJECTIVES: In accordance with dynamical systems theory, which assumes that motor behaviour emerges from interacting constraints (task, organismic, environmental), this study explored the functional role of inter-individual variability in inter-limb coordination. DESIGN: 63 front crawl swimmers with a range of characteristics (gender, performance level, specialty) performed seven intermittent graded speed bouts of 25m in front crawl. METHODS: Each bout was video-taped with a side-view camera from which speed, stroke rate, stroke length and index of arm coordination (IdC) were analysed for three cycles. Cluster analysis was used to classify the swimmers through speed and IdC values. RESULTS: Cluster analysis and validation showed four profiles of IdC management expressing the swimmers' characteristics as cluster 1: mainly national distance male swimmers, cluster 2: mainly international male sprinters, cluster 3: distinguished by female characteristics, and cluster 4: swimmers with the lowest level of performance. CONCLUSIONS: These profiles generated different IdC-speed regression models, which (i) showed how the swimmers adapted their motor behaviour to overcome task constraints and (ii) supported the key idea that there is not a single ideal expert model to be imitated, but rather adapted behaviour emerging from individually encountered constraints.