Quantifying the Contribution of NHL Player Types to Team Performance

Chan, Timothy C. Y.; Cho, Justin A.; Novati, David C.

doi:10.1287/inte.1110.0612

Cited by 28 publications

(21 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Single-leg lateral jump -Asymmetry (SLLJ-A) Percental difference between dominant and non-dominant leg in the singeleg lateral jump. Individual game performance was assessed by applying the Point Share system, which takes the individual contribution of team performance into account when assessing player performance (3,20). The system considers both offensive and defensive contribution, which minimises the differences between positional game demands.…”

Section: Experimental Designmentioning

confidence: 99%

“…The emergence of data analytics in team sports, including ice hockey, have led to more advanced objective metrics regarding the assessment of individual performance in a team environment (18,20,25). Using a Point Share (PS) system, see Figure 1, to analyse the individual performance has been well documented (3,20) and may currently provide the most accurate estimation of player contribution in ice hockey.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physical Performance and the Relationship to Game Performance in Elite Adolescent Ice Hockey

Williams

Grau

2020

IUSCAJ

View full text Add to dashboard Cite

Determining performance indicators within team sports is considerably important as it facilitates the underlying training methodologies of sports performance. The value of understanding individual contribution and the relevant physical factors is of importance when structuring appropriate strength and conditioning training. Therefore, the aim of this study was to analyse the relationships between physical performance and game performance, as well as examining the relationships of physical performance and game performance dependent on competition level. This research project was a case study conducted with a team’s game performance measured across a full season. Twelve elite adolescent male ice hockey players (17.92 ± 0.9 years, 185 ± 8.45 cm, 83.17 ± 8.61 kg) participated in the study after giving informed consent. Physical performance was measured using four tests (horizontal jump, single-leg lateral jump, 15-meter sprint, corner S test), while game performance was calculated through the statistical equation Point Shares. Statistical significance was set at p ≤ 0.05. Physical performance did not depict any strong indications of overall game performance. Instead, results illustrated an inverse relationship between plyometric performance and offensive point shares. However, on-ice agility may be a relevant indicator of game performance dependent on competition level for individuals and sub-groups. Thus, the findings suggest that explaining individual performance within team sports is a highly complex issue that needs further investigation.

show abstract

Section: Experimental Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Physical Performance and the Relationship to Game Performance in Elite Adolescent Ice Hockey

Williams

Grau

2020

IUSCAJ

View full text Add to dashboard Cite

show abstract

“…Chan et al 18 , based on technical variables obtained during the VJ (p < 0.001), indicating that these groups should receive differentiated training for these values; for the AG and %F variables the groups are homogeneous, which did not justify the sub-groups. We can observe the display of the groups through K-mean cluster below concerning position on the field, where no significant difference was evidenced (p = 0.198) between them (tabela 3).…”

Section: Discussionmentioning

confidence: 96%

Distribuição de subgrupos com base nas respostas fisiológicas em jogadores profissionais de futebol pela técnica K Means Cluster

Novack

Nascimento

Salgueirosa

et al. 2013

Rev Bras Med Esporte

View full text Add to dashboard Cite

Introduction: Physical fitness in soccer needs to be constantly updated due to current demands in contemporary soccer. Objective: Therefore, the purpose of this study was to assess the sensitivity of the statistical K-means Clustering in the distribution of groups based on physiological responses relevant to soccer. Methods: The athletes underwent anthropometric evaluations to determine the percentage of fat (%F) and lean mass (LM), treadmill incremental test to obtain the VO 2 maximum (VO 2max ) and ventilatory threshold velocity (VL), as well as testing field for agility (AG) and vertical jump (VJ). Data were analyzed by Kruskal-Wallis and distribution of groups was developed by the technique of Cluster K-means as the similarities of the players with these physiological variables, assuming a significance level of p < 0.05. The results showed that both groups differed significantly only with respect to VJ (p < 0,001), LM (p < 0.001), VL (p = 0.011) and VO 2max (p = 0,029) indicating that the athletes for these variables need to be distributed in groups. However the %F and AG (p = 0.317; p = 0.922) respectively, were not different indicating that these variables can be improved in all athletes collectively. Conclusion: Given these results, we conclude that the distribution of groups by K-means clustering technique can be performed using physiological responses of athletes as well as optimize the training for the professional soccer players can focus on the main training needs that athletes have in common regardless of the tactical function exercised in the field.

show abstract

“…Although hockey games are fascinating to watch, the use of analytical approaches to assess player performance is still at an early age due to the games' low scores [2] and complex dynamics [3,4]. Evaluating the performance of individual players and their contribution to the overall performance of the team [5,6] is a major challenge in the field of sports analysis. Several metrics have been proposed for performance analysis in different team sports, e.g., "Expected-Point-Value" in basketball [7,8] and "Expected-Goal-Value" in soccer [9] and American football [10].…”

Section: Introductionmentioning

confidence: 99%

Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model

Guo

Tao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The accurate detection of ice hockey players and teams during a game is crucial to the tracking of individual players on the rink and team tactical decision making and is therefore becoming an important task for coaches and other analysts. However, hockey is a fluid sport due to its complex situation and the frequent substitutions by both teams, resulting in the players taking various postures during a game. Few player detection models from basketball and soccer take these characteristics into account, especially for team detection without prior annotations. Here, a two-phase cascaded convolutional neural network (CNN) model is designed for the detection of individual ice hockey players, and the jersey color of the detected players is extracted to further identify team affiliations. Our model filters most of the disturbing information, such as the audience and sideline advertising bars, in Phase I and refines the detection of the targeted players in Phase II, resulting in an accurate detection with a precision of 98.75% and a recall of 94.11% for individual players and an average accuracy of 93.05% for team classification with a self-built dataset of collected images from the 2018 Winter Olympics. The results for the regular season games of the 2019-2020 National Hockey League (NHL) covering all 31 teams are also presented to show the robustness of our model. Compared to state-of-the-art approaches, our player detection model achieves the highest accuracy with the self-built dataset.

show abstract

Quantifying the Contribution of NHL Player Types to Team Performance

Cited by 28 publications

References 21 publications

Physical Performance and the Relationship to Game Performance in Elite Adolescent Ice Hockey

Physical Performance and the Relationship to Game Performance in Elite Adolescent Ice Hockey

Distribuição de subgrupos com base nas respostas fisiológicas em jogadores profissionais de futebol pela técnica K Means Cluster

Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model

Contact Info

Product

Resources

About