Fernando Manuel Lourenço Martins

Multilevel Image Segmentation Based on Fractional-Order Darwinian Particle Swarm Optimization

Hyperspectral remote sensing images contain hundreds of data channels. Due to the high dimensionality of the hyperspectral data, it is difficult to design accurate and efficient image segmentation algorithms for such imagery. In this paper, a new multilevel thresholding method is introduced for the segmentation of hyperspectral and multispectral images. The new method is based on fractional-order Darwinian particle swarm optimization (FODPSO) which exploits the many swarms of test solutions that may exist at any time. In addition, the concept of fractional derivative is used to control the convergence rate of particles. In this paper, the so-called Otsu problem is solved for each channel of the multispectral and hyperspectral data. Therefore, the problem of n-level thresholding is reduced to an optimization problem in order to search for the thresholds that maximize the between-class variance. Experimental results are favorable for the FODPSO when compared to other bioinspired methods for multilevel segmentation of multispectral and hyperspectral images. The FODPSO presents a statistically significant improvement in terms of both CPU time and fitness value, i.e., the approach is able to find the optimal set of thresholds with a larger between-class variance in less computational time than the other approaches. In addition, a new classification approach based on support vector machine (SVM) and FODPSO is introduced in this paper. Results confirm that the new segmentation method is able to improve upon results obtained with the standard SVM in terms of classification accuracies.

Using network metrics in soccer: a macro-analysis.

Abstract The aim of this study was to propose a set of network methods to measure the specific properties of a team. These metrics were organised at macro-analysis levels. The interactions between teammates were collected and then processed following the analysis levels herein announced. Overall, 577 offensive plays were analysed from five matches. The network density showed an ambiguous relationship among the team, mainly during the 2nd half. The mean values of density for all matches were 0.48 in the 1st half, 0.32 in the 2nd half and 0.34 for the whole match. The heterogeneity coefficient for the overall matches rounded to 0.47 and it was also observed that this increased in all matches in the 2nd half. The centralisation values showed that there was no ‘star topology’. The results suggest that each node (i.e., each player) had nearly the same connectivity, mainly in the 1st half. Nevertheless, the values increased in the 2nd half, showing a decreasing participation of all players at the same level. Briefly, these metrics showed that it is possible to identify how players connect with each other and the kind and strength of the connections between them. In summary, it may be concluded that network metrics can be a powerful tool to help coaches understand team’s specific properties and support decision-making to improve the sports training process based on match analysis.

Activity Profiles of Soccer Players During the 2010 World Cup

Abstract The main objective of this study was to analyse the distance covered and the activity profile that players presented at the FIFA World Cup in 2010. Complementarily, the distance covered by each team within the same competition was analysed. For the purposes of this study 443 players were analysed, of which 35 were goalkeepers, 84 were external defenders, 77 were central defenders, 182 were midfielders, and 65 were forwards. Afterwards, a thorough analysis was performed on 16 teams that reached the group stage, 8 teams that achieved the round of 16, 4 teams that reached the quarter-finals, and 4 teams that qualified for the semi-finals and finals. A comparison of the mean distance covered per minute among the playing positions showed statistically significant differences (F(4,438) = 559.283; p < 0.001; 2 = 0.836; Power = 1.00). A comparison of the activity time among tactical positions also resulted in statistically significant differences, specifically, low activity (F(4,183.371) = 1476.844; p < 0.001; 2 = 0.742; Power = 1.00), medium activity (F(4,183.370) = 1408.106; p < 0.001; 2 = 0.731; Power = 1.00), and high activity (F(4,182.861) = 1152.508; p < 0.001; 2 = 0.703; Power = 1.00). Comparing the mean distance covered by teams, differences that are not statistically significant were observed (F(3,9.651) = 4.337; p < 0.035; 2 = 0.206; Power = 0.541). In conclusion, the tactical positions of the players and their specific tasks influence the activity profile and physical demands during a match.

Measuring Tactical Behaviour Using Technological Metrics: Case Study of a Football Game

In football, the tactical behaviour of a team is related to the state of ball possession, i.e., the defensive and offensive phases. The aim of this study was to measure the tactical responses of two opposing teams in the moments with and without ball possession, thus trying to identify differences in results arising from tactical metrics such as weighted centroid position, weighted stretch index, surface area and effective area of play. The herein presented results show statistical differences in both teams, either with or without the ball possession, for the -axis centroid (p-value ≤ 0.001), -axis centroid (p-value ≤ 0.001), stretch index (p-value ≤ 0.001), surface area (p-value ≤ 0.001) and effective area of play (p-value ≤ 0.001). Such results confirm that teams react depending upon balls possession, respecting the tactical principles of width and length, as well as the unit in the offensive phase with ball possession, and also the concentration and defensive unit in the moments without ball possession.

Dynamical Stability and Predictability of Football Players: The Study of One Match

The game of football demands new computational approaches to measure individual and collective performance. Understanding the phenomena involved in the game may foster the identification of strengths and weaknesses, not only of each player, but also of the whole team. The development of assertive quantitative methodologies constitutes a key element in sports training. In football, the predictability and stability inherent in the motion of a given player may be seen as one of the most important concepts to fully characterise the variability of the whole team. This paper characterises the predictability and stability levels of players during an official football match. A Fractional Calculus (FC) approach to define a player’s trajectory. By applying FC, one can benefit from newly considered modeling perspectives, such as the fractional coefficient, to estimate a player’s predictability and stability. This paper also formulates the concept of attraction domain, related to the tactical region of each player, inspired by stability theory principles. To compare the variability inherent in the player’s process variables (e.g., distance covered) and to assess his predictability and stability, entropy measures are considered. Experimental results suggest that the most predictable player is the goalkeeper while, conversely, the most unpredictable players are the midfielders. We also conclude that, despite his predictability, the goalkeeper is the most unstable player, while lateral defenders are the most stable during the match.

Measuring Collective Behaviour in Football Teams: Inspecting the impact of each half of the match on ball possession

The aim of this study was to inspect the influence of each half of match and the ball possession status on the players’ spatio-temporal relationships. Three official matches of a professional football team were analysed. From the players’ locations were collected the team’s wcentroid, wstretch index, surface area and effective area of play at 9218 play instants. The results suggested that the values of teams’ dispersion and average position on the field decreases during the 2nd half of the match. In sum, this study showed that the half of match and the ball possession status influenced players’ spatio-temporal relationships, in a way that significantly contributes to the collective understanding of football teams.

General network analysis of national soccer teams in FIFA World Cup 2014

This study analyzed the network characteristics of successful and unsuccessful national teams that participated in FIFA World Cup 2014. The relationship between the variables of overall team performance and the network characteristics measured on the basis of the passes between teammates was also investigated. A dataset of 37,864 passes between teammates in 64 soccer matches enabled the study on network structure and team performance of 32 national soccer teams. Our results showed significant differences in the dependent variables of network density (F4,123 = 2.72; p = 0.03; η2p = 0.04; small effect size) and total links (F4,123 = 2.73; p = 0.03; η2p = 0.04; small effect size) between the teams that reached the later stages of the tournament. Goals scored presented a small positive correlation with total links (r = 0.24; p = 0.001), network density (r = 0.24; p = 0.001), and clustering coefficient (r = 0.17; p > 0.050). High levels of goals scored were associated with high levels of total links, network density, and clustering coefficient. This study showed that successful teams have a high level of network density, total links, and clustering coefficient. Thus, large values of connectivity between teammates are associated with better overall team performance.

Introducing the fractional order robotic Darwinian PSO

The Darwinian Particle Swarm Optimization (DPSO) is an evolutionary algorithm that extends the Particle Swarm Optimization using natural selection to enhance the ability to escape from sub-optimal solutions. An extension of the DPSO to multi-robot applications has been recently proposed and denoted as Robotic Darwinian PSO (RDPSO), benefiting from the dynamical partitioning of the whole population of robots, hence decreasing the amount of required information exchange among robots. This paper further extends the previously proposed algorithm using fractional calculus concepts to control the convergence rate, while considering the robot dynamical characteristics. Moreover, to improve the convergence analysis of the RDPSO, an adjustment of the fractional coefficient based on mobile robot constraints is presented and experimentally assessed with 2 real platforms. Afterwards, this novel fractional-order RDPSO is evaluated in 12 physical robots being further explored using a larger population of 100 simulated ...

Developing Aerobic and Anaerobic Fitness Using Small-Sided Soccer Games: Methodological Proposals

ABSTRACT SOCCER COACHES HAVE BEEN INCREASING THE USE OF SMALL-SIDED GAMES IN SOCCER TRAINING. THESE SMALL-SIDED GAMES SHOW A SIMILAR EFFICIENCY AS TRADITIONAL RUNNING METHODS (WITHOUT THE USE OF A BALL) IN DEVELOPING PHYSICAL FITNESS IN SOCCER PLAYERS. MOREOVER, SMALL-SIDED GAMES ENABLE THE DEVELOPMENT OF BOTH TECHNICAL SKILLS AND TACTICAL ACTIONS. HOWEVER, THERE IS LITTLE KNOWLEDGE ABOUT THE PROPER ORGANIZATION THAT IS NECESSARY FOR SMALL-SIDED GAMES TO ACHIEVE THE DESIRED EFFECTS IN SOCCER PLAYERS. THIS REVIEW AIMS TO SUMMARIZE THE PHYSIOLOGICAL EFFECTS ON SOCCER PLAYERS PROMOTED BY SMALL-SIDED GAMES AND TO DEVELOP A METHODOLOGICAL SCHEMATIZATION FOR ORGANIZING SMALL-SIDED GAMES.

Physical Activity Patterns in University Students: Do They Follow the Public Health Guidelines?

Physical activity is associated with health. The aim of this study was (a) to access if Portuguese university students meet the public health recommendations for physical activity and (b) the effect of gender and day of the week on daily PA levels of university students. This observational cross-sectional study involved 126 (73 women) healthy Portuguese university students aged 18–23 years old. Participants wore the ActiGraph wGT3X-BT accelerometer for seven consecutive days. Number of steps, time spent sedentary and in light, moderate and vigorous physical activity were recorded. The two-way MANOVA revealed that gender (p-value = 0.001; η2 = 0.038; minimum effect) and day of the week (p-value = 0.001; η2 = 0.174; minimum effect) had significant main effects on the physical activity variables. It was shown that during weekdays, male students walked more steps (65.14%), spent less time sedentary (6.77%) and in light activities (3.11%) and spent more time in moderate (136.67%) and vigorous activity (171.29%) in comparison with weekend days (p < 0.05). The descriptive analysis revealed that female students walked more steps (51.18%) and spent more time in moderate (125.70%) and vigorous (124.16%) activities during weekdays than in weekend days (p < 0.05). Women students did not achieve the recommended 10,000 steps/day on average during weekdays and weekend days. Only male students achieved this recommendation during weekdays. In summary, this study showed a high incidence of sedentary time in university students, mainly on weekend days. New strategies must be adopted to promote physical activity in this population, focusing on the change of sedentary behaviour.