Predictive modeling of the ratings of perceived exertion during training and competition in professional soccer players.

OBJECTIVES: Evaluate the ability of predicting the ratings of perceived exertion from the external load variables in professional soccer players through a chronological perspective (i.e., past features values are considered additional features) through machine learning models by considering the playing position. DESIGN: Prospective cohort study. METHODS: Thirty-eight elite soccer players aged 19-27 years were observed during 151 training sessions, 44 matches across a full season. External load variables (58 derived from Global Positioning System and 30 from accelerometers) and the internal load derived from ratings of perceived exertion were collected for each player and each session and match. Machine learning models (linear regression, K-NN, decision trees, random forest, elastic net regression, XGBoost) were compared and interpreted in order to deepen the relationship between external load variables and ratings of perceived exertion according to the player position in a predictive perspective. RESULTS: Application of the machine learning models on the dataset provided enough predictive power to reduce the Root Mean Squared Error of 60 % from dummy predictions. The most accurate models (Root Mean Squared Error ≈ 1.1 for random forest and = 1 for XGBoost) highlighted a memory effect in subsequent ratings of perceived exertion values. Past ratings of perceived exertion values over one month were the strongest predicting factors of ratings of perceived exertion as compared to various external load indicators. CONCLUSIONS: The tree-based machine learning models showed statistically significant predictive ability, indicating valuable information for understanding the training load responses based on ratings of perceived exertion changes.

The Use of Fitness-Fatigue Models for Sport Performance Modelling: Conceptual Issues and Contributions from Machine-Learning.

The emergence of the first Fitness-Fatigue impulse responses models (FFMs) have allowed the sport science community to investigate relationships between the effects of training and performance. In the models, athletic performance is described by first order transfer functions which represent Fitness and Fatigue antagonistic responses to training. On this basis, the mathematical structure allows for a precise determination of optimal sequence of training doses that would enhance the greatest athletic performance, at a given time point. Despite several improvement of FFMs and still being widely used nowadays, their efficiency for describing as well as for predicting a sport performance remains mitigated. The main causes may be attributed to a simplification of physiological processes involved by exercise which the model relies on, as well as a univariate consideration of factors responsible for an athletic performance. In this context, machine-learning perspectives appear to be valuable for sport performance modelling purposes. Weaknesses of FFMs may be surpassed by embedding physiological representation of training effects into non-linear and multivariate learning algorithms. Thus, ensemble learning methods may benefit from a combination of individual responses based on physiological knowledge within supervised machine-learning algorithms for a better prediction of athletic performance.In conclusion, the machine-learning approach is not an alternative to FFMs, but rather a way to take advantage of models based on physiological assumptions within powerful machine-learning models.

Uncertain imputation for time-series forecasting: Application to COVID-19 daily mortality prediction.

The object of this study is to put forward uncertainty modeling associated with missing time series data imputation in a predictive context. We propose three imputation methods associated with uncertainty modeling. These methods are evaluated on a COVID-19 dataset out of which some values have been randomly removed. The dataset contains the numbers of daily COVID-19 confirmed diagnoses ("new cases") and daily deaths ("new deaths") recorded since the start of the pandemic up to July 2021. The considered task is to predict the number of new deaths 7 days in advance. The more values are missing, the higher the imputation impact is on the predictive performances. The Evidential K-Nearest Neighbors (EKNN) algorithm is used for its ability to take into account labels uncertainty. Experiments are provided to measure the benefits of the label uncertainty models. Results show the positive impact of uncertainty models on imputation performances, especially in a noisy context where the number of missing values is high.

EBCR: Empirical Bayes concordance ratio method to improve similarity measurement in memory-based collaborative filtering.

Recommender systems aim to provide users with a selection of items, based on predicting their preferences for items they have not yet rated, thus helping them filter out irrelevant ones from a large product catalogue. Collaborative filtering is a widely used mechanism to predict a particular user's interest in a given item, based on feedback from neighbour users with similar tastes. The way the user's neighbourhood is identified has a significant impact on prediction accuracy. Most methods estimate user proximity from ratings they assigned to co-rated items, regardless of their number. This paper introduces a similarity adjustment taking into account the number of co-ratings. The proposed method is based on a concordance ratio representing the probability that two users share the same taste for a new item. The probabilities are further adjusted by using the Empirical Bayes inference method before being used to weight similarities. The proposed approach improves existing similarity measures without increasing time complexity and the adjustment can be combined with all existing similarity measures. Experiments conducted on benchmark datasets confirmed that the proposed method systematically improved the recommender system's prediction accuracy performance for all considered similarity measures.