Modelling the Influence of Task Constraints on Goal Kicking Performance in Australian Rules Football.

BACKGROUND: The primary aim of this study was to determine the influence of task constraints, from an ecological perspective, on goal kicking performance in Australian football. The secondary aim was to compare the applicability of three analysis techniques; logistic regression, a rule induction approach and conditional inference trees to achieve the primary aim. In this study, an ecological perspective has been applied to explore the impact of task constraints on shots on goal in the Australian Football League, such as shot type, field location and pressure. Analytical techniques can increase the understanding of competition environments and the influence of constraints on skilled events. Differing analytical techniques can produce varying outputs styles which can impact the applicability of the technique. Logistic regression, Classification Based on Associations rules and conditional inference trees were conducted to determine constraint interaction and their influence on goal kicking, with both the accuracy and applicability of each approach assessed. RESULTS: Each analysis technique had similar accuracy, ranging between 63.5% and 65.4%. For general play shots, the type of pressure and location particularly affected the likelihood of a shot being successful. Location was also a major influence on goal kicking performance from set shots. CONCLUSIONS: When different analytical methods display similar performance on a given problem, those should be prioritised which show the highest interpretability and an ability to guide decision-making in a manner similar to what is currently observed in the organisation.

Methodological Considerations for Furthering the Understanding of Constraints in Applied Sports.

Commonly classified as individual, task or environmental, constraints are boundaries which shape the emergence of functional movement solutions. In applied sport, an ongoing challenge is to improve the measurement, analysis and understanding of constraints to key stakeholders. Methodological considerations for furthering these pursuits should be centred around an interdisciplinary approach. This integration of methodology and knowledge from different disciplines also encourages the sharing of encompassing principles, concepts, methods and data to generate new solutions to existing problems. This narrative review discusses how a number of rapidly developing fields are positioned to help guide, support and progress an understanding of sport through constraints. It specifically focuses on examples from the fields of technology, analytics and perceptual science. It discusses how technology is generating large quantities of data which can improve our understanding of how constraints shape the movement solutions of performers in training and competition environments. Analytics can facilitate new insights from numerous and complex data through enhanced non-linear and multivariate analysis techniques. The role of the perceptual sciences is discussed with respect to generating outputs from analytics that are more interpretable for the end-user. Together, these three fields of technology, analytics and perceptual science may enable a more comprehensive understanding of constraints in sports performance.

Application of a continuous pressure metric for Australian football.

Pressure is an important constraint on sports performance and is typically measured through manual notational analysis. A continuous representation of pressure, along with semi-automated measurement, would serve to improve the efficiency of practice design and analysis, as well as provide additional context to player competition performance. Using spatiotemporal data collected from wearable tracking devices, the present study applied Kernel Density Estimation to estimate the density of players, relative to the ball carrier, at point of skill execution during elite Australian Football training. Two environmental constraints were measured (area per player and number of players) to determine the relationship between these training design manipulations and density. Density was also compared with existing notational analysis measurements of pressure. Results indicated that a higher density on skills was associated with successful skill executions. The opposite relationship was found between notational analysis pressure measurement and skill effectiveness. A strong inverse relationship was found between environmental constraint manipulation and density, whereby increasing field size and playing number decreased the density on skill involvements. The findings offer insight into the continuous measurement of pressure and encourage practitioners to utilize training design manipulations to influence density as a constraint on skills.

Classification of Australian football kick types in-situation via ankle-mounted inertial measurement units.

The utility of inertial measurement units (IMUs) for sporting skill and performance analysis during training and competition is advantageous for enhancing the objectivity of athlete monitoring. This study aimed to classify Australian Rules football (AF) kick types in an applied environment using ankle-mounted IMUs. IMUs and video capture of a controlled protocol, including four kick types at varying distances, were recorded during a single testing session with female AF athletes (n = 20). Processed IMU data were modelled using support vector machine classifier, random forest, and k-nearest neighbour algorithms under a 2-Kick, 4-Kick, and kick distance (10, 20, 30 m) conditions. The random forest model showed the highest results for overall classification accuracy (83% 2-Kick and 80% 4-Kick), test F1-score (0.76 2-Kick and 0.81 4-Kick), and AUC score (0.58 2-Kick and 0.60 4-Kick). Kick distance classification showed a model test and class weighted F1-score of 0.63 and overall accuracy of 64%, respectively. This study highlights the potential for an applied semi-automated AF training kick detection and type classification system using IMUs.

Applications of a working framework for the measurement of representative learning design in Australian football.

Representative learning design proposes that a training task should represent informational constraints present within a competitive environment. To assess the level of representativeness of a training task, the frequency and interaction of constraints should be measured. This study compared constraint interactions and their frequencies in training (match simulations and small sided games) with competition environments in elite Australian football. The extent to which constraints influenced kick and handball effectiveness between competition matches, match simulations and small sided games was determined. The constraints of pressure and time in possession were assessed, alongside disposal effectiveness, through an association rule algorithm. These rules were then expanded to determine whether a disposal was influenced by the preceding disposal. Disposal type differed between training and competition environments, with match simulations yielding greater representativeness compared to small sided games. The subsequent disposal was generally more effective in small sided games compared to the match simulations and competition matches. These findings offer insight into the measurement of representative learning designs through the non-linear modelling of constraint interactions. The analytical techniques utilised may assist other practitioners with the design and monitoring of training tasks intended to facilitate skill transfer from preparation to competition.

Prevalence of interactions and influence of performance constraints on kick outcomes across Australian Football tiers: Implications for representative practice designs.

Representative learning design is a key feature of the theory of ecological dynamics, conceptualising how task constraints can be manipulated in training designs to help athletes self-regulate during their interactions with information-rich performance environments. Implementation of analytical methodologies can support representative designs of practice environments by practitioners recording how interacting constraints influence events, that emerge under performance conditions. To determine key task constraints on kicking skill performance, the extent to which interactions of constraints differ in prevalence and influence on kicking skills was investigated across competition tiers in Australian Football (AF). A data sample of kicks (n = 29,153) was collected during junior, state-level and national league matches. Key task constraints were recorded for each kick, with performance outcome recorded as effective or ineffective. Rules were based on frequency and strength of associations between constraints and kick outcomes, generated using the Apriori algorithm. Univariate analysis revealed that low kicking effectiveness was associated with physical pressure (37%), whereas high efficiency emerged when kicking to an open target (70%). Between-competition comparisons showed differences in constraint interactions through seven unique rules and differences in confidence levels in shared rules. Results showed how understanding of key constraints interactions, and prevalence during competitive performance, can be used to inform representative learning designs in athlete training programmes. Findings can be used to specify how the competitive performance environment differs between competition tiers, supporting the specification of information in training designs, representative of different performance levels.

The relationship of team and individual athlete performances on match quarter outcome in elite women's Australian Rules football.

OBJECTIVES: To evaluate the relationships between the athlete distribution of team performance indicators and quarter outcome in elite women's Australian Rules football matches. DESIGN: Retrospective longitudinal cohort analysis. METHODS: Thirteen performance indicators were obtained from 56 matches across the 2017 and 2018 Australian Football League Women's (AFLW) seasons. Absolute and relative values of 13 performance indicators were obtained for each athlete, in each quarter of all matches. Eleven features were further extracted for each performance indicator, resulting in a total of 169 features. Generalised estimating equations (GEE) and regression decision trees were run across the different feature sets and dependent variables, resulting in 22 separate models. RESULTS: The GEE algorithm produced slightly lower mean absolute errors across all dependent variables and feature sets comparative to the regression decision tree models. Quarter outcome was more accurately explained when considered as total points scored comparative to quarter score margin. Team differential and the 75th percentile of individual athlete Inside 50s were the strongest features included in the models. CONCLUSIONS: Modelling performance statistics by quarter outcomes provides specific practical information for in-game tactics and coaching in relation to athlete performances each quarter. Within the current elite women's Australian Rules football competition, key high performing individual athletes' skilled performances within matches contribute more to success rather than a collective team effort.

The influence of match phase and field position on collective team behaviour in Australian Rules football.

This study investigated the influence of match phase and field position on collective team behaviour in Australian Rules football (AF). Data from professional male athletes (years 24.4 ± 3.7; cm 185.9 ± 7.1; kg 85.4 ± 7.1), were collected via 10 Hz global positioning system (GPS) during a competitive AFL match. Five spatiotemporal metrics (x-axis centroid, y-axis centroid, length, width, and surface area), occupancy maps, and Shannon Entropy (ShannEn) were analysed by match phase (offensive, defensive, and contested) and field position (defensive 50, defensive midfield, forward midfield, and forward 50). A multivariate analysis of variance (MANOVA) revealed that field position had a greater influence on the x-axis centroid comparative to match phase. Conversely, match phase had a greater influence on length, width, and surface area comparative to field position. Occupancy maps revealed that players repositioned behind centre when the ball was in their defensive half and moved forward of centre when the ball was in their forward half. Shannon Entropy revealed that player movement was more variable during offence and defence (ShannEn = 0.82-0.93) compared to contest (ShannEn = 0.68-0.79). Spatiotemporal metrics, occupancy maps, and Shannon Entropy may assist in understanding the game style of AF teams.

A change point approach to analysing the match activity profiles of team-sport athletes.

In team-sport, physical and skilled output is often described via aggregate parameters including total distance and number of skilled involvements. However, the degree to which these output change throughout a team-sport match, as a function of time, is relatively unknown. This study aimed to identify and describe segments of physical and skilled output in team-sport matches with an example in Australian Football. The relationship between the number of change points and level of similarity was also quantified. A binary segmentation algorithm was applied to the velocity time series, collected via wearable sensors, of 37 Australian football players (age: 23 ± 4 years, height: 187 ± 8 cm, mass: 86 ± 9 kg). A change point quotient of between 1 and 15 was used. For these quotients, descriptive statistics, spectral features and a sum of skilled involvements were extracted. Segment similarity for each quotient was evaluated using a random forest model. The strongest classification features in the model were spectral entropy and skewness. Offensive and defensive involvements were the weakest features for classification, suggesting skilled output is dependent on match circumstances. The methodology presented may have application in comparing the specificity of training to matches and designing match rotation strategies.

Longitudinal Analysis of Tactical Strategy in the Men's Division of the Ultimate Fighting Championship.

This study explored longitudinal changes in contemporary mixed martial arts (MMA) combat within the Ultimate Fighting Championship (UFC). A secondary aim was to investigate how bout duration influences the contribution of performance indicators on outcome. Data were acquired via the official analytics provider to the UFC (FightMetric). Male fights with a winner from between 2000 and 2015 (n = 2,831) were examined, with 13 common performance indicators attained during each round for each participant along with duration (min) and year of fight. Non-metric dimensional scaling (nMDS) was used to examine bout characteristics by year. The Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm was run to determine a set of rules to explain bout outcome. The nMDS displayed that winning bout performance indicator attributes were dissimilar across the years. Eight rules were generated from the RIPPER, with fight duration featuring in three of eight rules. Distinct shifts occurred (albeit without linear trend) in performance indicator characteristics during the observed period. This was characterized by a more diverse combat style in the years following 2008. However, offensive grappling has remained a key factor regardless of year, and is influenced by bout duration.

Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance.

Objective assessment of an athlete's performance is of importance in elite sports to facilitate detailed analysis. The implementation of automated detection and recognition of sport-specific movements overcomes the limitations associated with manual performance analysis methods. The object of this study was to systematically review the literature on machine and deep learning for sport-specific movement recognition using inertial measurement unit (IMU) and, or computer vision data inputs. A search of multiple databases was undertaken. Included studies must have investigated a sport-specific movement and analysed via machine or deep learning methods for model development. A total of 52 studies met the inclusion and exclusion criteria. Data pre-processing, processing, model development and evaluation methods varied across the studies. Model development for movement recognition were predominantly undertaken using supervised classification approaches. A kernel form of the Support Vector Machine algorithm was used in 53% of IMU and 50% of vision-based studies. Twelve studies used a deep learning method as a form of Convolutional Neural Network algorithm and one study also adopted a Long Short Term Memory architecture in their model. The adaptation of experimental set-up, data pre-processing, and model development methods are best considered in relation to the characteristics of the targeted sports movement(s).

Weak Relationships between Stint Duration, Physical and Skilled Match Performance in Australian Football.

Australian Rules football comprises physical and skilled performance for more than 90 min of play. The cognitive and physiological fatigue experienced by participants during a match may reduce performance. Consequently, the length of time an athlete is on the field before being interchanged (known as a stint), is a key tactic which could maximize the skill and physical output of the Australian Rules athlete. This study developed two methods to quantify the relationship between athlete time on field, skilled and physical output. Professional male athletes (n = 39) from a single elite Australian Rules football club participated, with physical output quantified via player tracking systems across 22 competitive matches. Skilled output was calculated as the sum of involvements performed by each athlete, collected from a commercial statistics company. A random intercept and slope model was built to identify how a team and individuals respond to physical outputs and stint lengths. Stint duration (mins), high intensity running (speeds >14.4 km · hr-1) per minute, meterage per minute and very high intensity running (speeds >25 km·hr-1) per minute had some relationship with skilled involvements. However, none of these relationships were strong, and the direction of influence for each player was varied. Three conditional inference trees were computed to identify the extent to which combinations of physical parameters altered the anticipated skilled output of players. Meterage per minute, player, round number and duration were all related to player involvement. All methods had an average error of 10 to 11 involvements, per player per match. Therefore, other factors aside from physical parameters extracted from wearable technologies may be needed to explain skilled output within Australian Rules football matches.

When Is a Sprint a Sprint? A Review of the Analysis of Team-Sport Athlete Activity Profile.

The external load of a team-sport athlete can be measured by tracking technologies, including global positioning systems (GPS), local positioning systems (LPS), and vision-based systems. These technologies allow for the calculation of displacement, velocity and acceleration during a match or training session. The accurate quantification of these variables is critical so that meaningful changes in team-sport athlete external load can be detected. High-velocity running, including sprinting, may be important for specific team-sport match activities, including evading an opponent or creating a shot on goal. Maximal accelerations are energetically demanding and frequently occur from a low velocity during team-sport matches. Despite extensive research, conjecture exists regarding the thresholds by which to classify the high velocity and acceleration activity of a team-sport athlete. There is currently no consensus on the definition of a sprint or acceleration effort, even within a single sport. The aim of this narrative review was to examine the varying velocity and acceleration thresholds reported in athlete activity profiling. The purposes of this review were therefore to (1) identify the various thresholds used to classify high-velocity or -intensity running plus accelerations; (2) examine the impact of individualized thresholds on reported team-sport activity profile; (3) evaluate the use of thresholds for court-based team-sports and; (4) discuss potential areas for future research. The presentation of velocity thresholds as a single value, with equivocal qualitative descriptors, is confusing when data lies between two thresholds. In Australian football, sprint efforts have been defined as activity >4.00 or >4.17 m·s-1. Acceleration thresholds differ across the literature, with >1.11, 2.78, 3.00, and 4.00 m·s-2 utilized across a number of sports. It is difficult to compare literature on field-based sports due to inconsistencies in velocity and acceleration thresholds, even within a single sport. Velocity and acceleration thresholds have been determined from physical capacity tests. Limited research exists on the classification of velocity and acceleration data by female team-sport athletes. Alternatively, data mining techniques may be used to report team-sport athlete external load, without the requirement of arbitrary or physiologically defined thresholds.

Discovering frequently recurring movement sequences in team-sport athlete spatiotemporal data.

Athlete external load is typically analysed from predetermined movement thresholds. The combination of movement sequences and differences in these movements between playing positions is also currently unknown. This study developed a method to discover the frequently recurring movement sequences across playing position during matches. The external load of 12 international female netball athletes was collected by a local positioning system during four national-level matches. Velocity, acceleration and angular velocity were calculated from positional (X, Y) data, clustered via one-dimensional k-means and assigned a unique alphabetic label. Combinations of velocity, acceleration and angular velocity movement were compared using the Levenshtein distance and similarities computed by the longest common substring problem. The contribution of each movement sequence, according to playing position and relative to the wider data set, was then calculated via the Minkowski distance. A total of 10 frequently recurring combinations of movement were discovered, regardless of playing position. Only the wing attack, goal attack and goal defence playing positions are closely related. We developed a technique to discover the movement sequences, according to playing position, performed by elite netballers. This methodology can be extended to discover the frequently recurring movements within other team sports and across levels of competition.

Variations in Hypoxia Impairs Muscle Oxygenation and Performance during Simulated Team-Sport Running.

Purpose: To quantify the effect of acute hypoxia on muscle oxygenation and power during simulated team-sport running. Methods: Seven individuals performed repeated and single sprint efforts, embedded in a simulated team-sport running protocol, on a non-motorized treadmill in normoxia (sea-level), and acute normobaric hypoxia (simulated altitudes of 2,000 and 3,000 m). Mean and peak power was quantified during all sprints and repeated sprints. Mean total work, heart rate, blood oxygen saturation, and quadriceps muscle deoxyhaemoglobin concentration (assessed via near-infrared spectroscopy) were measured over the entire protocol. A linear mixed model was used to estimate performance and physiological effects across each half of the protocol. Changes were expressed in standardized units for assessment of magnitude. Uncertainty in the changes was expressed as a 90% confidence interval and interpreted via non-clinical magnitude-based inference. Results: Mean total work was reduced at 2,000 m (-10%, 90% confidence limits ±6%) and 3,000 m (-15%, ±5%) compared with sea-level. Mean heart rate was reduced at 3,000 m compared with 2,000 m (-3, ±3 min-1) and sea-level (-3, ±3 min-1). Blood oxygen saturation was lower at 2,000 m (-8, ±3%) and 3,000 m (-15, ±2%) compared with sea-level. Sprint mean power across the entire protocol was reduced at 3,000 m compared with 2,000 m (-12%, ±3%) and sea-level (-14%, ±4%). In the second half of the protocol, sprint mean power was reduced at 3,000 m compared to 2,000 m (-6%, ±4%). Sprint mean peak power across the entire protocol was lowered at 2,000 m (-10%, ±6%) and 3,000 m (-16%, ±6%) compared with sea-level. During repeated sprints, mean peak power was lower at 2,000 m (-8%, ±7%) and 3,000 m (-8%, ±7%) compared with sea-level. In the second half of the protocol, repeated sprint mean power was reduced at 3,000 m compared to 2,000 m (-7%, ±5%) and sea-level (-9%, ±5%). Quadriceps muscle deoxyhaemoglobin concentration was lowered at 3,000 m compared to 2,000 m (-10, ±12%) and sea-level (-11, ±12%). Conclusions: Simulated team-sport running is impaired at 3,000 m compared to 2,000 m and sea-level, likely due to a higher muscle deoxygenation.

Heavy Resistance Training in Hypoxia Enhances 1RM Squat Performance.

Purpose: To determine if heavy resistance training in hypoxia (IHRT) is more effective at improving strength, power, and increasing lean mass than the same training in normoxia. Methods: A pair-matched, placebo-controlled study design included 20 resistance-trained participants assigned to IHRT (FIO2 0.143) or placebo (FIO2 0.20), (n = 10 per group). Participants were matched for strength and training. Both groups performed 20 sessions over 7 weeks either with IHRT or placebo. All participants were tested for 1RM, 20-m sprint, body composition, and countermovement jump pre-, mid-, and post-training and compared via magnitude-based inferences. Presentation of Results: Groups were not clearly different for any test at baseline. Training improved both absolute (IHRT: 13.1 ± 3.9%, effect size (ES) 0.60, placebo 9.8 ± 4.7%, ES 0.31) and relative 1RM (IHRT: 13.4 ± 5.1%, ES 0.76, placebo 9.7 ± 5.3%, ES 0.48) at mid. Similarly, at post both groups increased absolute (IHRT: 20.7 ± 7.6%, ES 0.74, placebo 14.1 ± 6.0%, ES 0.58) and relative 1RM (IHRT: 21.6 ± 8.5%, ES 1.08, placebo 13.2 ± 6.4%, ES 0.78). Importantly, the change in IHRT was greater than placebo at mid for both absolute [4.4% greater change, 90% Confidence Interval (CI) 1.0:8.0%, ES 0.21, and relative strength (5.6% greater change, 90% CI 1.0:9.4%, ES 0.31 (relative)]. There was also a greater change for IHRT at post for both absolute (7.0% greater change, 90% CI 1.3:13%, ES 0.33), and relative 1RM (9.2% greater change, 90% CI 1.6:14.9%, ES 0.49). Only IHRT increased countermovement jump peak power at Post (4.9%, ES 0.35), however the difference between IHRT and placebo was unclear (2.7, 90% CI -2.0:7.6%, ES 0.20) with no clear differences in speed or body composition throughout. Conclusion: Heavy resistance training in hypoxia is more effective than placebo for improving absolute and relative strength.