Alice J. Sweeting
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Alice J. Sweeting has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Sam Robertson
Victoria University
10 shared publications - Robert J. Aughey
Institute for Health and Sport, Victoria University, Melbourne, VIC, Australia
5 shared publications - Emily E. Cust
Track, Victoria University, Melbourne, Australia
3 shared publications Bartholomew Spencer
Institute for Health and Sport, Victoria University, Melbourne, Australia
2 shared publications- Ben Teune
Affiliations Institute for Health and Sport (iHeS), Victoria University, Melbourne, Australia, Western Bulldogs, Melbourne, Australia
2 shared publications - Carl Thomas Woods
Victoria University
2 shared publications
Latest Publications
- Open Access
- 29 July 2026
- Published by Elsevier in SSRN Electronic Journal
Assessing the suitability of wearable EMG shorts for measuring lower limb muscle activity using Isokinetic Dynamometry
Wearable surface electromyography (sEMG) shorts offer a practical alternative to traditional laboratory-based sEMG systems for measuring lower limb muscle activity in sporting environments. However, their suitability for accurately reflecting changes in contraction intensity remains largely unexplored. This study evaluated the suitability of wearable sEMG shorts for measuring quadricep (QG) and hamstring (HG) muscle group activity during graded isometric contractions, using concurrent torque measures obtained via isokinetic dynamometry. Six participants performed isometric knee extension and flexion contractions at 100%, 60% and 30% of maximal voluntary isometric contraction (MVIC) at two joint angles (60o and 30o) on a HUMAC isokinetic dynamometer. Strong positive associations were observed between normalised sEMG and torque across all contractions, with pooled correlations ranging from r = 0.86 to 0.98 and within-participant correlations from rmcorr r = 0.89 to 0.99. Bland-Altman analysis showed strongest agreement at 100% MVIC, with near zero bias and narrow limits of agreement (LoA), while submaximal intensities showed increasingly negative bias and wider LoA. These findings support the suitability of wearable sEMG shorts for quantifying relative QG and HG activity, particularly at higher contraction intensities. This work provides support for their potential application during sporting activities.
- 29 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAssessing the suitability of wearable EMG shorts for measuring lower limb muscle activity using Isokinetic Dynamometry
Wearable surface electromyography (sEMG) shorts offer a practical alternative to traditional laboratory-based sEMG systems for measuring lower limb muscle activity in sporting environments. However, their suitability for accurately reflecting changes in contraction intensity remains largely unexplored. This study evaluated the suitability of wearable sEMG shorts for measuring quadricep (QG) and hamstring (HG) muscle group activity during graded isometric contractions, using concurrent torque measures obtained via isokinetic dynamometry. Six participants performed isometric knee extension and flexion contractions at 100%, 60% and 30% of maximal voluntary isometric contraction (MVIC) at two joint angles (60o and 30o) on a HUMAC isokinetic dynamometer. Strong positive associations were observed between normalised sEMG and torque across all contractions, with pooled correlations ranging from r = 0.86 to 0.98 and within-participant correlations from rmcorr r = 0.89 to 0.99. Bland-Altman analysis showed strongest agreement at 100% MVIC, with near zero bias and narrow limits of agreement (LoA), while submaximal intensities showed increasingly negative bias and wider LoA. These findings support the suitability of wearable sEMG shorts for quantifying relative QG and HG activity, particularly at higher contraction intensities. This work provides support for their potential application during sporting activities.
- Open Access
- 23 July 2025
- Published by Taylor & Francis in Science and Medicine in Football
- Vol. 10 (3) , 1-14
Concurrent validation of foot-mounted inertial measurement units for quantifying Australian Rules football kicking
Wearable inertial measurement units (IMUs) may improve the objective analysis and load monitoring of skilled actions during team-sports, such as Australian Rules football (AF) kicking. This study aimed to determine the concurrent validity of a foot-mounted IMU to detect and quantify AF kicking output. Video footage compared kicks observed with kicks detected within the IMU. This study consisted of two phases; 1) On-Field Phase: Kicking actions were captured from n = 11 male and n = 25 female, professional AF participants throughout nine and five regular training sessions, respectively. 2) Protocol Phase consisted of n = 6 male and n = 8 female, semi-professional AF participants who performed a controlled kicking protocol, during a single testing session. Overall, the IMU exhibited good concurrent validity (Accuracy = 92% and 79%, Sensitivity = 0.92 and 0.79) in the On-Field and Protocol Phases, respectively. Kick intensities ranged from 6.30 m⋅s-1 to 24.30 m⋅s-1. This study demonstrates the potential of the IMU to automate the detection and quantification of kicking output, such as volumes and intensities in AF.
- 23 July 2025
- Published by Taylor & Francis in Science and Medicine in Football
- Vol. 10 (3) , 1-14
Open AccessConcurrent validation of foot-mounted inertial measurement units for quantifying Australian Rules football kicking
Wearable inertial measurement units (IMUs) may improve the objective analysis and load monitoring of skilled actions during team-sports, such as Australian Rules football (AF) kicking. This study aimed to determine the concurrent validity of a foot-mounted IMU to detect and quantify AF kicking output. Video footage compared kicks observed with kicks detected within the IMU. This study consisted of two phases; 1) On-Field Phase: Kicking actions were captured from n = 11 male and n = 25 female, professional AF participants throughout nine and five regular training sessions, respectively. 2) Protocol Phase consisted of n = 6 male and n = 8 female, semi-professional AF participants who performed a controlled kicking protocol, during a single testing session. Overall, the IMU exhibited good concurrent validity (Accuracy = 92% and 79%, Sensitivity = 0.92 and 0.79) in the On-Field and Protocol Phases, respectively. Kick intensities ranged from 6.30 m⋅s-1 to 24.30 m⋅s-1. This study demonstrates the potential of the IMU to automate the detection and quantification of kicking output, such as volumes and intensities in AF.
- 5 April 2022
- Published by Taylor & Francis
- p. 60-78
Collecting and Presenting Data for Performance Impact in Elite Sport: Finding the Right Balance between Humans and Machines
Data collection and presentation is commonplace in elite sport as a way of assessing, understanding and improving athletic performance. Various methods of data collection and presentation are currently available to sports scientists. Each method has unique constraints that influence the level of impact that data may have on performance. It is consequently imperative that sports science practitioners carefully consider how data is both collected and presented. This chapter will present a simple workflow that details the process and considerations that should be made to ensure data is meaningful in an applied sport context. The first section of this chapter will outline the process and importance of developing a research question. The second section of the chapter will explore the considerations that should be made for data visualisation when working with individual and team sports. The chapter will subsequently provide practical examples from elite sport settings to enhance the reader's understanding of the power of data for performance impact in sport. This chapter will provide insights into performance analysis in elite sport and is of interest to applied sport scientists.
- 5 April 2022
- Published by Taylor & Francis
- p. 60-78
Collecting and Presenting Data for Performance Impact in Elite Sport: Finding the Right Balance between Humans and Machines
Data collection and presentation is commonplace in elite sport as a way of assessing, understanding and improving athletic performance. Various methods of data collection and presentation are currently available to sports scientists. Each method has unique constraints that influence the level of impact that data may have on performance. It is consequently imperative that sports science practitioners carefully consider how data is both collected and presented. This chapter will present a simple workflow that details the process and considerations that should be made to ensure data is meaningful in an applied sport context. The first section of this chapter will outline the process and importance of developing a research question. The second section of the chapter will explore the considerations that should be made for data visualisation when working with individual and team sports. The chapter will subsequently provide practical examples from elite sport settings to enhance the reader's understanding of the power of data for performance impact in sport. This chapter will provide insights into performance analysis in elite sport and is of interest to applied sport scientists.
- Open Access
- 11 August 2021
- Published by Wiley in European Journal of Sport Science
- Vol. 22 (8) , 1268-1275
The influence of environmental and task constraint interaction on skilled behaviour in Australian Football
The design of sports practice environments can be informed through data collected and analysed according to principles of the constraints-led approach. In this study, three manipulated environmental (area per player, number of players and team outnumber) and two task (activity objective and disposal limitations) constraints were measured during professional Australian Football training activities (n = 112) to determine their relationship with skilled behaviour. Linear regression modelling of the five manipulated constraints explained 68% of the variance in disposal frequency but only 22% in skill efficiency. Activities with scoring objectives, limited to kicking or which permitted all disposals, reduced the disposal frequency per player. Activities which permitted all disposals were also weakly, negatively associated with skill efficiency. A Classification Based on Association analysis measured the interaction between manipulated constraints and their relationships with possession time and pressure. When compared to the null model, the analysis improved pressure classification accuracy by 5.9% and did not improve possession time classification accuracy. This indicates skills were often performed under varying spatial and temporal constraints during many of the training activities. This study presents multivariate analytical methods which consider constraint interaction, enhancing how practitioners can evaluate and inform training design in sport.
- 11 August 2021
- Published by Wiley in European Journal of Sport Science
- Vol. 22 (8) , 1268-1275
Open AccessThe influence of environmental and task constraint interaction on skilled behaviour in Australian Football
The design of sports practice environments can be informed through data collected and analysed according to principles of the constraints-led approach. In this study, three manipulated environmental (area per player, number of players and team outnumber) and two task (activity objective and disposal limitations) constraints were measured during professional Australian Football training activities (n = 112) to determine their relationship with skilled behaviour. Linear regression modelling of the five manipulated constraints explained 68% of the variance in disposal frequency but only 22% in skill efficiency. Activities with scoring objectives, limited to kicking or which permitted all disposals, reduced the disposal frequency per player. Activities which permitted all disposals were also weakly, negatively associated with skill efficiency. A Classification Based on Association analysis measured the interaction between manipulated constraints and their relationships with possession time and pressure. When compared to the null model, the analysis improved pressure classification accuracy by 5.9% and did not improve possession time classification accuracy. This indicates skills were often performed under varying spatial and temporal constraints during many of the training activities. This study presents multivariate analytical methods which consider constraint interaction, enhancing how practitioners can evaluate and inform training design in sport.
- Open Access
- 17 February 2021
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 39 (13) , 1548-1554
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.
- 17 February 2021
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 39 (13) , 1548-1554
Open AccessApplication 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.
- 30 December 2020
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 39 (12) , 1330-1338
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.
- 30 December 2020
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 39 (12) , 1330-1338
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.
- 5 March 2019
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 37 (15) , 1699-1707
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.
- 5 March 2019
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 37 (15) , 1699-1707
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.
- 12 February 2019
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 37 (14) , 1600-1608
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.
- 12 February 2019
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 37 (14) , 1600-1608
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.
- Open Access
- 1 January 2019
- Published by INSTICC
- p. 32-37
Biomechanical Characteristics of Elite Female Australian Rules Football Preferred and Non-preferred Drop Punt Kicks
- 1 January 2019
- Published by INSTICC
- p. 32-37
Open AccessBiomechanical Characteristics of Elite Female Australian Rules Football Preferred and Non-preferred Drop Punt Kicks
- Top Cited Papers
- 11 October 2018
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 37 (5) , 568-600
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).
- 11 October 2018
- Published by Taylor & Francis in Journal of Sports Sciences
- Vol. 37 (5) , 568-600
Top Cited PapersMachine 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).