can derive other biomechanical metrics describing the jump performance, such as force, power, velocity, and center-of-mass position. Force data derived from inertial sensors have been shown to agree well with simultaneously recorded force plate data. 16 However, although jump heights derived from
Malachy P. McHugh, Tom Clifford, Will Abbott, Susan Y. Kwiecien, Ian J. Kremenic, Joseph J. DeVita and Glyn Howatson
David Whiteside, Olivia Cant, Molly Connolly and Machar Reid
Quantifying external workload is fundamental to training prescription in sport. In tennis, global positioning data are imprecise and fail to capture hitting loads. The current gold standard (manual notation) is time intensive and often not possible given players’ heavy travel schedules.
To develop an automated stroke-classification system to help quantify hitting load in tennis.
Nineteen athletes wore an inertial measurement unit (IMU) on their wrist during 66 video-recorded training sessions. Video footage was manually notated such that known shot type (serve, rally forehand, slice forehand, forehand volley, rally backhand, slice backhand, backhand volley, smash, or false positive) was associated with the corresponding IMU data for 28,582 shots. Six types of machine-learning models were then constructed to classify true shot type from the IMU signals.
Across 10-fold cross-validation, a cubic-kernel support vector machine classified binned shots (overhead, forehand, or backhand) with an accuracy of 97.4%. A second cubic-kernel support vector machine achieved 93.2% accuracy when classifying all 9 shot types.
With a view to monitoring external load, the combination of miniature inertial sensors and machine learning offers a practical and automated method of quantifying shot counts and discriminating shot types in elite tennis players.
Rienk M.A. van der Slikke, Daan J.J. Bregman, Monique A.M. Berger, Annemarie M.H. de Witte and Dirk-Jan (H.) E.J. Veeger
on performance and to explore the relationship between match and best performance, a single outcome measure should be used in both conditions. A recently introduced method based on inertial sensors allows for objective performance estimations in both match and best conditions in a reliable and
Rienk M.A. van der Slikke, Annemarie M.H. de Witte, Monique A.M. Berger, Daan J.J. Bregman and Dirk Jan H.E.J. Veeger
accurate and objective measures. To quote a wheelchair basketball coach: “you can’t improve it, if you lack information.” In preceding research, a method using inertial sensors proved reliable and accurate 4 in measuring WMP and discriminated well between athletes of different classification and
Paul G. Montgomery and Brendan D. Maloney
global positioning system (GPS), inertial sensor, and physiological data to determine the response to each game. As the number of tournament game increases from pool games to quarterfinal (QF), semifinal (SF), and championship (CH) games, the hypothesis was that these parameters would decrease over a
Robert J. Aughey
Global positioning system (GPS) technology was made possible after the invention of the atomic clock. The first suggestion that GPS could be used to assess the physical activity of humans followed some 40 y later. There was a rapid uptake of GPS technology, with the literature concentrating on validation studies and the measurement of steady-state movement. The first attempts were made to validate GPS for field sport applications in 2006. While GPS has been validated for applications for team sports, some doubts continue to exist on the appropriateness of GPS for measuring short high-velocity movements. Thus, GPS has been applied extensively in Australian football, cricket, hockey, rugby union and league, and soccer. There is extensive information on the activity profile of athletes from field sports in the literature stemming from GPS, and this includes total distance covered by players and distance in velocity bands. Global positioning systems have also been applied to detect fatigue in matches, identify periods of most intense play, different activity profiles by position, competition level, and sport. More recent research has integrated GPS data with the physical capacity or fitness test score of athletes, game-specific tasks, or tactical or strategic information. The future of GPS analysis will involve further miniaturization of devices, longer battery life, and integration of other inertial sensor data to more effectively quantify the effort of athletes.
Matthias W. Hoppe, Christian Baumgart and Jürgen Freiwald
To investigate differences in running activities between adolescent and adult tennis players during match play. Differences between winning and losing players within each age group were also examined.
Forty well-trained male players (20 adolescents, 13 ± 1 y; 20 adults, 25 ± 4 y) played a simulated singles match against an opponent of similar age and ability. Running activities were assessed using portable devices that sampled global positioning system (10 Hz) and inertial-sensor (accelerometer, gyroscope, and magnetometer; 100 Hz) data. Recorded data were examined in terms of velocity, acceleration, deceleration, metabolic power, PlayerLoad, and number of accelerations toward the net and the forehand and backhand corners.
Adult players spent more time at high velocity (≥4 m/s2), acceleration (≥4 m/s2), deceleration (≤–4 m/s2), and metabolic power (≥20 W/kg) (P ≤ .009, ES = 0.9–1.5) and performed more accelerations (≥2 m/s2) toward the backhand corner (P < .001, ES = 2.6–2.7). No differences between adolescent winning and losing players were evident overall (P ≥ .198, ES = 0.0–0.6). Adult winning players performed more accelerations (2 to <4 m/s2) toward the forehand corner (P = .026, ES = 1.2), whereas adult losing players completed more accelerations (≥2 m/s2) toward the backhand corner (P ≤ .042, ES = 0.9).
This study shows that differences in running activities between adolescent and adult tennis players exist in high-intensity measures during simulated match play. Furthermore, differences between adolescent and adult players, and also between adult winning and losing players, are present in terms of movement directions. Our findings may be helpful for coaches to design different training drills for both age groups of players.
Ryan M. Chambers, Tim J. Gabbett and Michael H. Cole
a Catapult OptimEye S5 device (Catapult Sports, Melbourne, Australia) positioned between the players’ shoulder blades in a purpose-built vest. Each device contained an array of inertial sensors (eg, triaxial accelerometer, gyroscope, magnetometer) that captured data at 100 Hz during a series of
Paul G. Montgomery and Brendan D. Maloney
, particularly in field-based sports, where access to global positioning system (GPS) information is not a limiting factor. Combined with inertial-sensor data, wearable technology can assist in defining the external loads players experience during training and competition. Traditionally, basketball, as an indoor
Live S. Luteberget, Benjamin R. Holme and Matt Spencer
indoors, thus not useable for indoors sports such as team handball. In recent years, an inertial measurement unit (IMU) has been integrated into GPS devices, to provide additional information relating to physical loads during games and training. IMUs consist of the inertial sensors accelerometers and