Loading...
Research Project
Life Quality Research Centre
Funder
Authors
Publications
Data Mining Paths for Standard Weekly Training Load in Sub-Elite Young Football Players: A Machine Learning Approach
Publication . Teixeira, José Eduardo; Encarnação, Samuel Gonçalves; Branquinho, Luís; Morgans, Ryland; Afonso, Pedro; Rocha, João Pedro da Silva; Graça, Francisco M.; Barbosa, Tiago M.; Monteiro, A.M.; Ferraz, Ricardo; Forte, Pedro
The aim of this study was to test a machine learning (ML) model to predict high-intensity actions and body impacts during youth football training. Sixty under-15, -17, and -19 sub-elite Portuguese football players were monitored over a 6-week period. External training load data were collected from the target variables of accelerations (ACCs), decelerations (DECs), and dynamic stress load (DSL) using an 18 Hz global positioning system (GPS). Additionally, we monitored the perceived exertion and biological characteristics using total quality recovery (TQR), rating of perceived exertion (RPE), session RPE (sRPE), chronological age, maturation offset (MO), and age at peak height velocity (APHV). The ML model was computed by a feature selection process with a linear regression forecast and bootstrap method. The predictive analysis revealed that the players’ MO demonstrated varying degrees of effectiveness in predicting their DEC and ACC across different ranges of IQR. After predictive analysis, the following performance values were observed: DEC (xpredicted = 41, β = 3.24, intercept = 37.0), lower IQR (IQRpredicted = 36.6, β = 3.24, intercept = 37.0), and upper IQR (IQRpredicted = 46 decelerations, β = 3.24, intercept = 37.0). The player’s MO also demonstrated the ability to predict their upper IQR (IQRpredicted = 51, β = 3.8, intercept = 40.62), lower IQR (IQRpredicted = 40, β = 3.8, intercept = 40.62), and ACC (xpredicted = 46 accelerations, β = 3.8, intercept = 40.62). The ML model showed poor performance in predicting the players’ ACC and DEC using MO (MSE = 2.47–4.76; RMSE = 1.57–2.18: R2 = −0.78–0.02). Maturational concerns are prevalent in football performance and should be regularly checked, as the current ML model treated MO as the sole variable for ACC, DEC, and DSL. Applying ML models to assess automated tracking data can be an effective strategy, particularly in the context of forecasting peak ACC, DEC, and bodily
effects in sub-elite youth football training.
Anthropometric measures, muscle resistance, and balance in physically active, aged adults
Publication . Rodrigues, Filipe; Antunes, Raul; Matos, Rui; Jacinto, Miguel; Monteiro, Diogo; Forte, Pedro; Monteiro, A.M.; Barbosa, Tiago M.
This study aimed to examine the relationship between age, body mass index, muscle strength, and balance in physically active, aged adults. Methods: Eighty-five participants were recruited for this study, having an average age of 70.31 years (SD = 9.90), ranging from 50 to 92 years. Twenty-six (30.6%) participants were male and fifty-nine (69.4%) were female. The participants had an average body mass index of 27.30 kg/m2 (SD = 3.62), ranging from 20.32 to 38.58 kg/m2. Participants undertook the Timed-Up and Go to test balance, and the chair-stand test to assess lower body strength. Hierarchical regression analyses were conducted. Three models (Model 1, 2, and 3) were tested to assess their relationships with balance: M1—Lower body muscle strength; M2—Lower body muscle strength and body mass index; M3—Lower body muscle strength, body mass index, and age. Results: All hierarchical models displayed significant variance. The third model explained 50.9% of the variance in dynamic balance, [F(3, 81) = 27.94, p < 0.001, R = 0.71, Ra2 = 0.51]. The difference in Ra2 between the first, second, and third models was statistically significant (p < 0.05). Age, body mass index, and lower body muscle strength had significant (p < 0.05) correlations with balance. In terms of the significant impact of each predictor, age had the strongest association with balance (p < 0.05). Conclusions: The results are useful to understand mechanisms or diagnose people at risk of fall.
Effects of implementating a hybrid teaching model in a basketball didactic unit
Publication . Ferraz, Ricardo; Oliveira, Julio; Alves, Ana Ruivo; Forte, Pedro; Teixeira, José Eduardo; Moriyamag, Shinichiro; Valente, Nelson; Branquinho, Luís
The eminent purpose of physical education (PE) is to promote physical fitness, health, and overall well-being among individuals. It aims to develop motor skills, improve cognitive functions, and instill a lifelong appreciation for an active and healthy lifestyle. Physical education also fosters social skills, teamwork, and discipline, contributing to the holistic development of individuals. The study aimed to assess the impact of a hybrid teaching model, integrating elements from the Sport Education Model (SEM) and Teaching Games for Understanding (TGfU), on the performance and motivation of students during basketball lessons. Eighteen adolescents (9 girls and 8 boys) aged 15-17 years (mean ± SD: 15.67 ± 0.69 years) participated in the study. Participants engaged in basketball physical education classes twice a week, incorporating principles and attributes from both TGfU and SEM. Motivation and performance (GP) were evaluated before and after basketball sessions. The students' motivation was assessed using the Attitude Questionnaire of Students towards PE, and the performance was measured using the Game Performance Assessment Instrument. The results showed significant improvements in students' GP, but no differences in motivation was found at the end of the instructional unit. However, it was discovered that students enjoyed and appreciated physical education (PE), demonstrating a favorable attitude towards the subject. A hybrid teaching model with principles based on TGfU and SEM seems to be an appropriate approach to enhance students' game understanding, decision-making and overall GP (game skills, both technical and tactical). Attributes and principles such as simulating a sports season and student-centered learning situations that consider individual needs, seems to be important to develop students' awareness of attributing meaning to their actions, resulting in improved GP. The findings could be useful to teachers, coaches and researchers contributing to the development of teaching strategies to empower the PE classes.
Tracking the Prevalence of Obesity in Portuguese School-Aged Children: What Future to Expect?
Publication . Valente, Nelson; Forte, Pedro; Teixeira, José Eduardo; Afonso, Pedro; Ferreira, Sérgio; Marinho, D.A.; Mendes, Pedro Duarte; Ferraz, Ricardo; Branquinho, Luís
Childhood obesity presents a significant public health concern globally,
with implications for cardiovascular health and metabolic syndrome. In Portugal, approximately
31.6% of children are affected, highlighting the urgency for intervention strategies. This study
aimed to assess the prevalence of overweight and obesity in Portuguese school-aged children, with
a focus on sex and age differences. Methods: Anthropometric measurements were conducted on
1564 children aged 6–10 years, including weight, height, and skinfold thickness. Body Mass Index
(BMI) and the percentage of body fat were calculated using established methods. Results: The results
revealed significant differences in BMI (≤0.001) and body fat percentage (≤0.001) among different
BMI categories, with a notable prevalence of overweight and obesity, particularly among boys. A
total of 37% of the studied population is overweight or obese, among which 40.1% and 33.9% are
boys and girls, respectively. Conclusions: This study highlights statistically significant differences in
BMI and body fat percentage for both sexes in different BMI categories. A large proportion of the
population is overweight or obese, with a greater prevalence in boys. In short, childhood obesity has a
negative impact on body composition and is associated with significant differences in anthropometric
parameters, emphasizing the importance of preventative and intervention strategies to address this
health problem.
Motivational correlates, satisfaction with life, and physical activity in older adults: a structural equation analysis
Publication . Rodrigues, Filipe; Jacinto, Miguel; Couto, Nuno; Monteiro, Diogo; Monteiro, A.M.; Forte, Pedro; Antunes, Raul
Motivation is a crucial factor in predicting health-related outcomes, and understanding the determinants of motivation can provide valuable insights into how to improve health behaviors and outcomes in older adults. In this study, we aimed to investigate the associations between intrinsic and extrinsic exercise motivation, basic psychological needs, satisfaction with life, and physical activity among the elderly population. Methods: The sample consisted of 268 older adults (59 male, 209 female) aged 65–90 years old (Mage = 68.11, SD = 6.95). All participants reported that they were exercising, on average, 1.65 days (SD = 0.51) per week. Factor analysis was conducted using a two-step approach. First, a confirmatory factor analysis and then a structural equation model considering all variables under analysis was performed. Results: the structural model displayed acceptable fit to the data: χ2/df = 3.093; CFI = 0.913; TLI = 0.908; SRMR = 0.071; RMSEA 0.079 [0.066, 0.092]. Significant direct effects were found as theoretically proposed, namely: (a) intrinsic motivation were positively and significantly associated with basic psychological need satisfaction (p < 0.001); (b) extrinsic motivation were negatively but not significantly associated with basic psychological needs (p < 0.001); and (c) basic psychological need satisfaction were positively and significantly associated with satisfaction with life (p < 0.001) and physical activity (p < 0.001). Conclusions: Intrinsic motivation and basic psychological needs play a crucial role in shaping exercise behavior and overall well-being. By understanding these motivation and needs, exercise and health professionals can work towards fulfilling them and achieving a greater sense of satisfaction in the life of the elderly and promote exercise adherence.
Organizational Units
Description
Keywords
Contributors
Funders
Funding agency
Fundação para a Ciência e a Tecnologia
Funding programme
6817 - DCRRNI ID
Funding Award Number
UIDB/04748/2020