Volumen 19 (2020): Heft 2 (December 2020)

In team sport Human Activity Recognition (HAR) using inertial measurement units (IMUs) has been limited to athletes performing a set routine in a controlled environment, or identifying a high intensity event within periods of relatively low work load. The purpose of this study was to automatically classify locomotion in an elite sports match where subjects perform rapid changes in movement type, direction, and intensity. Using netball as a test case, six athletes wore a tri-axial accelerometer and gyroscope. Feature extraction of player acceleration and rotation rates was conducted on the time and frequency domain over a 1s sliding window. Applying several machine learning algorithms Support Vector Machines (SVM) was found to have the highest classification accuracy (92.0%, Cohen’s kappa Ƙ = 0.88). Highest accuracy was achieved using both accelerometer and gyroscope features mapped to the time and frequency domain. Time and frequency domain data sets achieved identical classification accuracy (91%). Model accuracy was greatest when excluding windows with two or more classes, however detecting the athlete transitioning between locomotion classes was successful (69%). The proposed method demonstrated HAR of locomotion is possible in elite sport, and a far more efficient process than traditional video coding methods.

This paper outlines a novel approach to optimising teams for Daily Fantasy Sports (DFS) contests. To this end, we propose a number of new models and algorithms to solve the team formation problems posed by DFS. Specifically, we focus on the National Football League (NFL) and predict the performance of real-world players to form the optimal fantasy team using mixed-integer programming. We test our solutions using real-world data-sets from across four seasons (2014-2017). We highlight the advantage that can be gained from using our machine-based methods and show that our solutions outperform existing benchmarks, turning a profit in up to 81.3% of DFS game-weeks over a season.

In this paper, we critically evaluate the performance of nine machine learning classification techniques when applied to the match outcome prediction problem presented by American Football. Specifically, we implement and test nine techniques using real-world datasets of 1280 games over 5 seasons from the National Football League (NFL). We test the nine different classifier techniques using a total of 42 features for each team and we find that the best performing algorithms are able to improve one previous published works. The algoriothms achieve an accuracy of between 44.64% for a Guassian Process classifier to 67.53% with a Naïve Bayes classifer. We also test each classifier on a year by year basis and compare our results to those of the bookmakers and other leading academic papers.

Artificial Intelligence (AI) invades fields where sophisticated analytics has not been applied before. Modality refers to how something happens or is experienced. Multimodal datasets are beneficial for solving complex research problems with AI methods. Kayaking technique optimization has been challenging, as there seems to be no gold standard for effective paddling techniques since there are outstanding athletes with profoundly different physical capabilities and kayaking styles.

Multimodal analysis can help find the most effective paddling techniques for training and competition based on individuals’ abilities.

We describe the characteristics of the output power of kayak athletes and Electromyogram (EMG) measurements collected from the most critical muscles, and the relationship between these modalities. We propose metrics (weighted arithmetic mean difference and variability of power output and stroke duration) suitable for discerning athletes based on how efficiently and correctly they perform particular training tasks. Additionally, the described methods (asymmetry, coactivation, muscle intensity-output power) help athletes and coaches in assessing their performance and compare it with others based on their EMG activities.

As the next step, we will apply machine-learning approaches on the synchronized dataset we collect with the described methods to reveal desirable EMG and stroke patterns.

The purpose of this study is to analyse the interactions established by Gerard Piqué, one of the world’s top defenders, within the general context of the team. The type of interactions (prospective and retrospective) that the player establishes with his team mates and opponents; the parts of the pitch where his actions are set in motion and later finished; his preferred skill or technical moves and finally his influence on set pieces are taken into account. His output throughout the 2012 UEFA Euro, where he played 100% of the game. The instrument of observation proposed by Maneiro & Amatria (2018) has been used. Polar coordinate analysis, a powerful tecnique capable of reducing the amount of data without compromising its analytical capacity, was used. The results showed significant interactions with players from the same and different lines thanks to technical actions of control, pass and carrying of ball. The analysis of the player’s interactions within the general context of the team will provide other teams with tactical alternatives and allow themto organise special training programmes.