Differentiating movement styles in professional tennis: A machine learning and hierarchical clustering approach

A measure of the importance of moment for ball-strike counts in a baseball plate appearance

This study constructs a discrete-time Markov Chain (DTMC) model for a baseball plate appearance (PA) employing Major League Baseball's pitch-by-pitch dataset. Based on the DTMC model, we propose a novel measure for a baseball PA, termed the Importance of Moment (IOM). The IOM quantifies the criticality of each ball-strike count situation, by assessing the probabilistic difference between the pitcher's and hitter's favourable outcomes (out vs reaching base). If the favours significantly vary right after a particular ball-strike count, then the count is deemed critical and is assigned a high IOM value. We empirically verify that IOM explains pitchers' behaviour of fastball speed. We then further investigate whether the behaviour of ace pitchers differs significantly from the majority. Several interesting properties are found from the analysis. Firstly, the path independence assumption generally holds, with the exception of the ball-strike count of 2B1S. Second, pitchers tend to throw the faster fastball at counts with higher IOM values. Lastly, ace pitchers are capable of pitching even faster fastball in two-strike situations in which IOM is high. The DTMC effectively models the probabilistic structure of a baseball PA, and the proposed IOM measure serves as a useful tool for explaining player behaviour.

Effects of different maturity status on change of direction performance of youth tennis players

The aim of this study was to examine the maturational status (i.e., peak height velocity [PHV]) differences in neuromuscular performance (i.e., vertical jump, linear sprint, change of direction (COD) using different tests, and change of direction deficit [CODD]) of young tennis players. One hundred and two tennis players (70 boys and 52 girls; age 13.9 ± 2.0 years, body mass 53.3 ± 12.7 kg, height 163.1 ± 11.9 cm) participated in the study and were divided into Pre-PHV (n = 26), Circa-PHV (n = 33) and Post-PHV (n = 43) groups. Testing included speed (5, 10, and 20 m), COD tests (i.e., modified 5-0-5, pro-agility and hexagon), and bilateral/unilateral countermovement jump (CMJ). Pre- and Circa-PHV players presented lower levels of performance in jumping ability (i.e., both bilateral and unilateral CMJs; P < 0.001; ES: 0.85 to 0.98), linear sprints (5 to 20 m; P < 0.05 to < 0.001; ES: 0.67 to 1.19) and COD ability tests (modified 5-0-5 test, pro-agility and hexagon) compared to the Post-PHV players. Moreover, Pre-PHV players presented lower CODD% (p < 0.05; ES: 0.68-0.72) than Post-PHV for both forehand and backhand sides, and Circa-PHV showed lower values in the CODD of the rolling situation to the forehand side (p < 0.05; ES: 0.58). Among the COD tests, the pro-agility test seems to be a simple, easy-to-implement and reliable test, which can provide interesting information about the COD with higher entry speeds. Moreover, specific training strategies related to the PHV and focused not only on the neuromuscular training and COD workouts, but also on maximizing motor skill proficiency, should be recommended.

From The Ground Up: Expert Perceptions of Lower Limb Activity Monitoring in Tennis

Understanding on-court movement in tennis allows for enhanced preparation strategies to improve player readiness and performance. Here, we explore expert physical preparation coaches' perceptions of elite training strategies for preparation and performance in tennis, with special reference to lower limb activity. Thirteen world renowned tennis strength and conditioning coaches were interviewed in a semi-structured method that explored four key topic areas of physical preparation for tennis: i) the physical demands; ii) load monitoring practice; iii) the direction of ground reaction forces application during match-play; and iv) the application of strength and conditioning for tennis. Three higher-order themes emerged from these discussions: i) off-court training for tennis should be specific to the demands of the sport, ii) the mechanical understanding of tennis lags our physiological approach, and iii) our understanding of the lower limb's contribution to tennis performance is limited. These findings provide valuable insights into the importance of improving our knowledge relevant to the mechanical demands of tennis movement, whilst highlighting important practical considerations from leading tennis conditioning experts.

Differentiating Stroke and Movement Accelerometer Profiles to Improve Prescription of Tennis Training Drills

ABSTRACT

Perri, T, Reid, M, Murphy, A, Howle, K, and Duffield, R. Differentiating stroke and movement accelerometer profiles to improve prescription of tennis training drills. J Strength Cond Res 37(3): 646-651, 2023-This study compared the movement- and stroke-related accelerometer profiles and stroke counts between common on-court tennis training drills. Ten, junior-elite, male tennis players wore a cervical-mounted global positioning systems, with in-built accelerometer, gyroscope, and magnetometer during hard court training sessions ( n = 189). Individual training drills were classified into 8 categories based on previous research descriptions. Manufacturer software calculated total player load (tPL), while a prototype algorithm detected forehand (FH), backhands (BH), and serves and then calculated a stroke player load (sPL) from individual strokes. Movement player load (mPL) was calculated as the difference between tPL and sPL. Drill categories were compared for relative ( . min -1 ) tPL, sPL, mPL, and stroke counts via a 1-way analysis of variance with effect sizes (Cohen's d ) and 95% confidence intervals. Highest tPL . min -1 existed in accuracy and recovery or defensive drills ( p < 0.05), with lowest tPL·min -1 values observed in match-play simulation ( p < 0.05). For sPL·min -1 , accuracy drills elicited greater values compared with all other drill types ( p < 0.05), partly via greater FH-sPL·min -1 ( p < 0.05), with lowest sPL·min -1 existing for match-play ( p < 0.05). Accuracy, open, and recovery or defensive drills result in greater BH-sPL·min -1 and BH . min -1 ( p < 0.05). Serve-sPL·min -1 is highest in technical and match-play drills ( p < 0.05). Higher mPL·min -1 existed in accuracy, recovery or defensive, 2v1 net, open, and 2v1 baseline ( p < 0.05). Furthermore, mPL·min -1 in points drills was greater than technical and match-play simulation drills ( p < 0.05). Higher hitting-based accelerometer loads (sPL·min -1 ) exist in accuracy drills, whereas technical and match-play drills show the lowest movement demands (mPL·min -1 ). These findings can aid individual drill prescription for targeting movement or hitting load.