PerSoccer 2013 Abstracts


Full Papers
Paper Nr: 3
Title:

Combining Video and Player Telemetry for Evidence-based Decisions in Soccer

Authors:

Håvard D. Johansen, Svein Arne Pettersen, Pål Halvorsen and Dag Johansen

Abstract: Technology is changing how soccer clubs train and interact with their supporters. Systems that provide acquisition and visualization of low-level player telemetry, like distance covered and speed, are already being widely adopted. A key observation is that such data when correlated with actual in-game video footage is a powerful tool for evidence-based decisions. As data volume and complexity grow, efficient tools for automated high-precision retrieval become essential. This paper describes the unique combination of a radio-based sensor platform and several custom video retrieval systems in operational use at TIL, a Norwegian premier league soccer club. The systems have been developed using an experimental computer-science method where several prototypes were built and deployed for evaluation in close collaboration with the intended users. Although our method of computer-system prototyping has not yielded commercial quality products, it has enabled us to construct several novel systems combining low-level player telemetry with video retrieval, annotations, and user-centric security.

Paper Nr: 5
Title:

Monitoring the Mental Status of Football Players

Authors:

Elena Smets, Pieter Joosen, Joachim Taelman, Vasileios Exadaktylos and Daniel Berckmans

Abstract: This work has tested heart rate to measure anxiety during a penalty shootout. Until now, anxiety is measured through questionnaires, where online monitoring is not possible. Therefore there is a need for physiological parameters to represent anxiety online. Since it is proven that the level of anxiety is a good predictor of penalty outcome, it was hypothesised that this outcome can be estimated with heart rate and activity. To test this hypothesis an experiment has been conducted with 54 participants (age= 23±4,54 years). They each performed three sessions of a penalty shootout, where heart rate and activity were measured. An adapted version of the State-Trait Anxiety Inventory was used as reference for anxiety level. The data have been analysed using a static and dynamic approach. These resulted in parameters that were used to predict the anxiety level and penalty performance of the participant with a multinomial logistic regression model. The results show that 47,11% of the participants were correctly classified into three classes of anxiety. Based on a classification into penalty performance 55,11 % of the participants were correctly classified. It can be concluded that heart rate in combination with activity shows promising results as predictor for anxiety.

Short Papers
Paper Nr: 1
Title:

Towards the Reflective Soccer Coach from Qualitative Approach

Authors:

Mohar Kassim

Abstract: This study is the first attempt from qualitative approach in order to elucidate the behaviour with respect to performance of coaches especially at grass root level. This study also involves the Chief Coach (n=2), the Assistant Coach (n=2), the Youth Department Officer (n=1), the Executive Secretary of the Forest Football Academy (n=1) and the Players (n=40). The study applied a qualitative methodology to get a better results and data from the interview analysis. The findings of this study revealed that i) the environment factors highly influence the coaches behaviour; iii) the component of professionalism, knowledge, behaviour and players performance were related and each of the component has influenced from other factors such as organization, significant experience, environment, training and competition. The findings also shows that the behavioural aspect, is to show their strong commitment to make the players follow the activities constructed. Hence, the coaches had successfully demonstrated positive behaviour by emphasizing fun and enjoyment that helped the players enjoy their training sessions and this shows that the coaches’ behaviour is important in imparting knowledge to the players. In conclusion, the findings of the present study thus offer significant contribution to the existing literature and conceptual development on coaching by looking at the relationship between the coaches' behaviour during the coaching process.

Paper Nr: 2
Title:

Performance Analysis Challenges in Professional Football Practice

Authors:

Chris Carling

Abstract: Over recent years, the progressive bridging of the gap between sports science and applied football coaching practice has led to greater recognition of the need for and subsequent benefits of objective systematic processes for monitoring player performance in training and competition (Strudwick, 2013). The on-going assessment of performance in competition notably using performance analysis techniques such as match and time motion analyses provides opportunities for the design and prescription of evidence-based practice frameworks for optimising training and match preparation (James, 2006). Many professional clubs now formally employ performance analysts and sports scientists to provide factual and permanent records of events underpinning both individual and team technical, tactical and physical performance in competition. Innovative state-of-the-art computer software and video technologies are used to generate unprecedented masses of data to profile and benchmark match-play performance. Analysis of how teams and individuals perform in competition aids in identifying specific strengths and weakness and over a period of time can create a benchmark against which instances of future performance can be compared in order to pinpoint positive and negative trends in play (Carling and Court, 2012).

Paper Nr: 4
Title:

The Differential Effect of the Evolving Game Status in the Passing Sequences of Top-Level European Football Teams

Authors:

Paulo Paixão, J. Sampaio and R. Duarte

Abstract: 1 OBJECTIVES In recent years there have been several studies seeking to understand how contextual variables such as game location, the level of the opponent and the evolving game status typically influence football teams’ performances. Usually, investigations examine the effects of these situational variables on physical/conditioning, technical, tactical and mental performance in football (Taylor, Mellalieu, James & Shearer, 2008). The evolving game status (winning, losing or drawing) is one of the most relevant situational variables influencing performance in Association Football (Lago, 2009). Hughes and Reed (2005) reported that game status affected the frequency of shots, with less incidence of shots associated to losing status. On the other hand, other studies demonstrated that ball possession depends on the evolution of the score-line, with teams having greater possession when they are losing compared to when they are winning or drawing (Lago et al. 2007, 2009). However, some studies have highlighted the importance to consider and examine each team individually since their different identities may moderate the impact of the situational variables (Hughes & Reed, 2005; Collet, 2013). The purpose of this study was to examine the differential effect of the evolving game status in the passing sequences leading to a shot at goal, of four top-level European association football teams. 2 METHODS A total of 20 matches of the final stage of UEFA Champions League (2008-2009) were analysed and 222 passing sequences from 4 different teams (FC Barcelona, Manchester United FC, Chelsea FC, Arsenal FC) were selected for further analysis. As inclusion criteria, all the passing sequences that ended with a shot at goal were selected in order to capture the way how each team created goal-scoring opportunities. These teams were selected as the most successful ones since them reached the semi-finals of the competition. The dependent variable studied in each sequence was the number of passes per shot ratio (Hughes & Franks, 2005; Collet, 2013). For each team, the passing sequences were distributed by winning, losing and drawing game episodes. We performed an automatic cluster classification analysis (Two Step cluster) with the overall data, which allowed identifying three groups of passing sequences divided by their substantial differences. Secondly we applied another automatic cluster classification (Two Step Cluster) to identify differences within each game status and to compare for differences between groups of long and short sequences. Finally we applied the Chi-square test with contingency tables (between -1.5 and 1.5) comparing the four teams with the evolving game status. 3 RESULTS The results revealed that Barcelona was the team with large number of passing sequences, while Chelsea showed the lowest total number of passing sequences. When teams were losing there was a tendency for an absence of short passing sequences, while winning teams increased the relative number of these short sequences. Data also revealed important differences between teams, with Barcelona and Manchester United showing superior capacity to increase retention of possession when drawing than when winning. 4 DISCUSSION Generally, in the overall data the number of passing sequences identified in each game status increased with a higher favourable scoreline. This data somewhat contradicts Lago et al. (2012), who found a decreasing likelihood of reaching the scoring zone as the status of the game was more favourable. The four teams investigated in this study used preferentially long passing sequences when they were losing or drawing, and short passing sequences when they were winning, which agrees with Lago and Martin (2007) and Lago (2009) who found greater possession when teams were losing. The results obtained emphasise the idea of Lago (2009), for whom the strategies in football are influenced by the scoreline and teams change their style of play during the match accordingly. The results revealed also substantial differences of passing sequences length between teams and game status. These findings mean that different teams distinctively adapt themselves to changes in relevant performance constraints such as the evolving game status, which reveal what Hughes and Reed (2005) called team’s signatures of play.