Next Generation GPS/Accelerometer Variables

by Fusion Sport
 | 6th April, 2017

The rise of GPS/accelerometer use in recent years has provided significant insight into the training and match demands of elite sports. As practitioners dig deeper into an individual’s objective workload, a new generation of variables are being extrapolated to further describe demands. Although several GPS validity and reliability concerns remain1,2, particularly for more recent metrics, how are these emerging novel metrics being explored in applied settings?

Painting the Picture

Firstly, we should explore the main objectives of athlete tracking. As described by Buchheit2 these include:

1. Better understanding of practice (provide an objective, a posteriori evaluation of external load and locomotor demands of any given session or match)
2. The optimisation of training load patterns at the team level
3. Individualising athlete training programs to improve performance and prevent injuries (e.g., top-up training vs. un-loading sequences, return to play progression).

Classifying Current Tracking Variables on the Market

There are multiple levels of complexity in which current tracking devices summarise movement. Gray3 has summarised these as 3 operational levels:

Level 1: Time spent and distance covered in different velocity zones (‘old school’ type of analysis, provided by all technologies). Example: 345 m ran above 19.8 km/h.

Level 2: Velocity related events such as accelerations, decelerations and changes of directions (provided with varying degrees of accuracy by some technologies). Example: 45 accelerations over 3 m.s-2, for a total distance of 233 m.

Level 3: Information derived from embedded inertial sensors such as accelerometers, gyroscopes and magnetometers (micro-technology only, so unavailable with camera-derived systems). Examples: 17 impacts above 6 G, Player Load of 456 AU, stride variables (Force load on the ground, contact times), stride imbalances (4% reduced impulse force on the right leg).

Considering the Next Generation of GPS/Accelerometer Metrics

Acceleration/ Deceleration – concerns remain around classifying acceleration/deceleration data into intensity and duration bands. However, preliminary evidence suggests averaging this variable over select periods may be a more appropriate method4.


Contact load (derived from accelerometer) – preliminary evidence to suggest automated tackling algorithms may detect the contact load in rugby league match play5. Further validation is required in other sports but this is an area of interest moving forward.


Force load3,6 (derived from accelerometer) – sum of estimated ground reaction forces during all foot impacts. Evidence to suggest greater cumulative force load volumes may be associated with increased injury risk6.

Stride characteristics7 (derived from accelerometer and gyroscope) – contact and flight time may provide insight into neuromuscular fatigue; a potential mediator8 for injury.


Metabolic power – attempts to calculate the combined energy cost of constant running speed with the cost of accelerating. Still requires significant sport-specific validation1,2 but has the potential to provide a holistic measure of demands.

Consider Actionable Variables – What Questions Will They Answer

Measuring running movement with a wearable device is difficult. Often, those variables perceived to be most important for load monitoring (high speed running, acceleration/deceleration) are much harder to capture. As such, they are typically less valid and reliable than more simple measures2. To counter this, Buchheit2 recommends defining larger, more conservative smallest worthwhile difference/changes when using these variables to guide decisions.

While these new measures might be of larger interest than more simple ones, as with any new metric you must take a cost:benefit approach2;

Cost, ease of use, portability, manpower versus ability to impact on the training program

If you are interested in hearing about how you can analyse your selected GPS/accelerometer variables, do not hesitate to contact us at support@smartabase.com. Did you know that Fusion Sport also offers GPS integrated data analysis? Interested in how we make this possible? Check out SMARTABASE

References

1. Malone JJ, Lovell R, Varely MC, et al. Unpacking the black box: Applications and considerations for using GPS devices in sport. Int J Sports Physiol Perform Published Online First [02/10/16] doi: http://dx.doi.org/10.1123/ijspp.2016-0236.


2. Buchheit M, Simpson BM. Player tracking technology: half-full or half-empty glass?. Int J Sports Physiol Perform 2016; 14:1-23. Available for download here: https://mart1buch.files.wordpress.com/2016/12/buchheit-simpson-tracking-players-with-technology.pdf


3. Athletic Data Innovations (ADI), Sydney, Australia.


4. Delaney JA, Cummins CJ, Thornton HR, et al. Importance, reliability and usefulness of acceleration measures in team sports. J Strength Cond Res 2017. Published Online First [08/02/17] doi: 10.1519/JSC.0000000000001849


5. Hulin BT, Gabbett TJ, Johnston RD, et al. Wearable microtechnology can accurately identify collision events during professional rugby league match-play. J Sci Med Sport 2017. Published Online First [23/01/17]. doi: 10.1016/j.jsams.2016.11.006


6. Colby MJ, Dawson B, Heasman J, et al. Accelerometer and GPS-derived running loads and injury risk in elite Australian footballers. J Strength Cond Res 2014; 28: 2244–2252.


7. Buchheit M, Gray A, Morin J. Assessing Stride Variables and Vertical Stiffness with GPS-Embedded Accelerometers: Preliminary Insights for the Monitoring of Neuromuscular Fatigue on the Field. J Sports Sci Med 2015; 14(4): 698–701.


8. Windt J, Zumbo BD, Sporer B, et al. Why do workload spikes cause injuries, and which athletes are at higher risk? Mediators and moderators in workload–injury investigations. Br J Sports Med Published Online First [08/04/17] doi: http://dx.doi.org/10.1136/bjsports-2016-097255


9. Header image: Dearne Valley College

By Marcus Colby, ‎PhD Candidate at The University of Western Australia