TY - JOUR
T1 - An application of clustering to classify movement patterns in men’s professional grand slam hard court tennis
AU - Armstrong, Cameron
AU - Peeling, Peter
AU - Murphy, Alistair
AU - Reid, Machar
PY - 2024/7/31
Y1 - 2024/7/31
N2 - The movement cycles from Australian Open player tracking data were analysed using the Lloyd k-means clustering algorithm to classify movement patterns that exist in men’s grand-slam tennis. The elbow criterion method identified six movement patterns, and the k-means model allocated each movement cycle into one of these discrete groups. A description of each movement pattern is presented, outlining three inner range and three end range movement patterns, which are distinguishable by distance, direction, time pressure, and starting location. These findings provide objective details for coaches and athletes to understand tennis movement, overcoming vague descriptions of the inner range and end range in tennis vernacular. The amalgam of distance, direction, and time pressure demands that categorise the six movement patterns can enhance the specificity of training drill design and movement evaluation. Furthermore, evaluating the movement patterns a player typically elicits during match-play can inform typical load exposure and be useful in load monitoring practices. Additionally, understanding the prevalence of movement patterns in a typical match may help understand the strategic approaches players use during match-play.
AB - The movement cycles from Australian Open player tracking data were analysed using the Lloyd k-means clustering algorithm to classify movement patterns that exist in men’s grand-slam tennis. The elbow criterion method identified six movement patterns, and the k-means model allocated each movement cycle into one of these discrete groups. A description of each movement pattern is presented, outlining three inner range and three end range movement patterns, which are distinguishable by distance, direction, time pressure, and starting location. These findings provide objective details for coaches and athletes to understand tennis movement, overcoming vague descriptions of the inner range and end range in tennis vernacular. The amalgam of distance, direction, and time pressure demands that categorise the six movement patterns can enhance the specificity of training drill design and movement evaluation. Furthermore, evaluating the movement patterns a player typically elicits during match-play can inform typical load exposure and be useful in load monitoring practices. Additionally, understanding the prevalence of movement patterns in a typical match may help understand the strategic approaches players use during match-play.
KW - data science
KW - Hawkeye
KW - Movement analysis
UR - http://www.scopus.com/inward/record.url?scp=85200202987&partnerID=8YFLogxK
U2 - 10.1080/24748668.2024.2386839
DO - 10.1080/24748668.2024.2386839
M3 - Article
AN - SCOPUS:85200202987
SN - 1474-8185
JO - International Journal of Performance Analysis in Sport
JF - International Journal of Performance Analysis in Sport
ER -