Loading...
515 results
Search Results
Now showing 1 - 10 of 515
- Analyzing Key Factors on Training Days within a Standard Microcycle for Young Sub-Elite Football Players: A Principal Component ApproachPublication . Teixeira, José Eduardo; Branquinho, Luís; Ferraz, Ricardo; Morgans, Ryland; Encarnação, Samuel; Ribeiro, Joana; Afonso, Pedro; Ruzmetov, Nemat; Barbosa, Tiago M.; Monteiro, A.M.; Forte, PedroUtilizing techniques for reducing multivariate data is essential for comprehensively understanding the variations and relationships within both biomechanical and physiological datasets in the context of youth football training. Therefore, the objective of this study was to identify the primary factors influencing training sessions within a standard microcycle among young sub-elite football players. A total of 60 male Portuguese youth sub-elite footballers (15.19 1.75 years) were continuous monitored across six weeks during the 2019–2020 in-season, comprising the training days from match day minus (MD-) 3, MD-2, and MD-1. The weekly training load was collected by an 18 Hz global positioning system (GPS), 1 Hz heart rate (HR) monitors, the perceived exertion (RPE) and the total quality recovery (TQR). A principal component approach (PCA) coupled with a Monte Carlo parallel analysis was applied to the training datasets. The training datasets were condensed into three to five principal components, explaining between 37.0% and 83.5% of the explained variance (proportion and cumulative) according to the training day (p < 0.001). Notably, the eigenvalue for this study ranged from 1.20% to 5.21% within the overall training data. The PCA analysis of the standard microcycle in youth sub-elite football identified that, across MD-3, MD-2, and MD-1, the first was dominated by the covered distances and sprinting variables, while the second component focused on HR measures and training impulse (TRIMP). For the weekly microcycle, the first component continued to emphasize distance and intensity variables, with the ACC and DEC being particularly influential, whereas the second and subsequent components included HR measures and perceived exertion. On the three training days analyzed, the first component primarily consisted of variables related to the distance covered, running speed, high metabolic load, sprinting, dynamic stress load, accelerations, and decelerations. The high intensity demands have a high relative weight throughout the standard microcycle, which means that the training load needs to be carefully monitored and managed.
- Data Mining Paths for Standard Weekly Training Load in Sub-Elite Young Football Players: A Machine Learning ApproachPublication . Teixeira, José Eduardo; Encarnação, Samuel; Branquinho, Luís; Morgans, Ryland; Afonso, Pedro; Rocha, João Pedro da Silva; Graça, Francisco M.; Barbosa, Tiago M.; Monteiro, A.M.; Ferraz, Ricardo; Forte, PedroThe 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.
- Influence of multicomponent exercise program or self-selected physical activity on physical, mental, and biochemical health indicators of older womenPublication . Encarnação, Samuel; Fazolo, Sthefany Lemos; Pereira, Felipe Soares Tomaz; Araújo, Daniele Pereira; Miranda, Cíntia Neves de; Pinto, Beatriz Woyames Ferreira; Forte, Pedro; Teixeira, José Eduardo; Barbosa, Tiago M.; Monteiro, A.M.; Moreira, Osvaldo Costa; Carneiro-Júnior, Miguel AraújoThe aim of this study was to compare physical, mental, and biochemical health indicators of 48 older women (67 ± 1 year) who practiced multicomponent exercise program (ME, n = 25) and self-selected physical activity (PA, n = 23) for 6 months. It was an observational study, which aimed to relate a prospective intervention. Displacement speed, lower limb (LL) power, functional capacity, body composition, biochemical profile, physical activity levels (PAL), sedentary behavior (SB), quality of life (QoL), and mental illness risk (MIR) were evaluated. ME presented better values compared to the PA in the gait speed (p = 0.001, large ES), aerobic capacity (p = 0.0001, large ES), agility/dynamic balance (p = 0.0001, large ES), LL flexibility (p = 0.0003, large ES), UL flexibility (p = 0.04, large ES), upper limb (UL) strength (p = 0.07, moderate ES), Total cholesterol (p = 0.009, large ES), triglycerides (p = 0.003, large ES), creatinine (p = 0.007, large ES), glycated hemoglobin (p= 0.007, large ES), and lower mean glucose value (p = 0.008, large ES). ME was more efficient than PA to improve indicators of gait speed, and functional capacity, regulate glycated hemoglobin, blood glucose, and serum creatinine. Thys study also brings practical applications for coaches, which could adapt and use creativity to develop different types of systematized ME, aiming to enhance positive adaptations in the older people at multilevel outcomes.
- Match-to-Match Variation on High-Intensity Demands in a Portuguese Professional Football TeamPublication . Teixeira, José Eduardo; Branquinho, Luís; Leal, Miguel; Morgans, Ryland; Sortwell, Andrew; Barbosa, Tiago M.; Monteiro, A.M.; Afonso, Pedro; Machado, Guilherme; Encarnação, Samuel; Ferraz, Ricardo; Forte, PedroThe aim of this study was to analyze the match-to-match variation in high-intensity demands from one Portuguese professional football team according to playing positions. Twentythree male outfield professional football players were observed during eighteen matches of the Portuguese Second League. Time–motion data were collected using Global Positioning System (GPS) technology. Match running performance was analyzed based on the following three playing positions: defenders (DF), midfielders (MF), and forwards (FW). Repeated measures ANOVA was utilized to compare match running performance within each position role, and seasonal running variation. Practical differences were assessed using the smallest worthwhile change (SWC), coefficient of variation (CV), and twice the coefficient of variation (2CV). Significant differences were found among playing positions in total distance covered (F = 15.45, p < 0.001, η2 = 0.33), average speed (F = 12.79, p < 0.001, η2 = 0.29), high-speed running (F = 16.93, p < 0.001, η2 = 0.36), sprinting (F = 13.49, p < 0.001, η2 = 0.31), accelerations (F = 4.69, p = 0.001, η2 = 0.132), and decelerations (F = 12.21, p < 0.001, η2 = 0.284). The match-to-match running performance encompassed TD (6.59%), AvS (8.67%), HSRr (37.83%), SPR (34.82%), ACC (26.92%), and DEC (27.85%). CV values for total distance covered ranged from 4.87–6.82%, with forwards and midfielders exhibiting the greatest and smallest variation, respectively. Midfielders demonstrated the highest match-to-match variation for all other analyzed variables (8.12–69.17%). All playing positions showed significant variation in high-demanding variables (26.94–37.83%). This study presents the initial analysis of match-tomatch variation in high-intensity demands within a Portuguese professional football team. Thus, the position’s specificity and context can provide a helpful strategy for evaluating match-to-match running performance, and for recommending individualized training exercises based on the peak and high-intensity demands for each player’s role within the game.
- The impact of multicomponent exercise protocols order on the maximum voluntary contraction of older womenPublication . Monteiro, A.M.; Rodrigues, Sandra Beatriz; Matos, Sérgio; Encarnação, Samuel; Teixeira, José Eduardo; Barbosa, Tiago M.; Rodrigues, Filipe; Forte, PedroThe aim of this study was to evaluate the impact of exercise order in multicomponent training (MCT) on the maximum voluntary contraction (MVC) of older women. A total of 91 older women, ranging in age from 60 to 85 years, were randomly assigned to either Group A or Group B. Group A performed a warm up followed by aerobic training and resistance training, whereas Group B followed a warm up followed by resistance training and aerobic training. A control group (CG) did not engage in any exercise interventions. Statistical analysis was conducted using one-way ANOVA for between-group comparisons, and ANOVA was used for repeated measures. The results revealed that Group A demonstrated significant increases in MVC for knee extensors (KEs) between M1 and M3 (p < 0.001) and between M2 and M3 (p < 0.001). Similarly, Group A exhibited significant increases in MVC for knee flexors (KFs) between M1 and M3 (p = 0.001) and between M2 and M3 (p < 0.001). Both Group A and Group B demonstrated significant increases in MVC for elbow flexors (EFs) between M1 and M3 (p < 0.001). Furthermore, Group B showed a significant increase in hand grip strength (HGS) between M1 and M3 (p < 0.001). Overall, the findings suggest that initiating MCT with aerobic training followed by resistance training is the most effective approach for improving muscle strength in older women.
- Variações da carga de treino entre titulares e não titulares durante um microciclo padrão em escalões de formação sub-15, sub-17 e sub-19 de uma academia de futebol subelitePublication . Teixeira, José Eduardo; Ribeiro, Joana; Silva-Santos, Sandra; Leal, Miguel; Flores, Pedro Miguel; Encarnação, Samuel; Barbosa, Tiago M.; Monteiro, A.M.; Ferraz, Ricardo; Branquinho, Luís; Forte, PedroO treino complementar tem sido extensamente aplicado para resolver o diferencial da carga de treino semanal entre jogadores titulares e não titulares. Contudo, pouco se sabe da sua aplicação em contextos de futebol de formação subelite. Assim, o objetivo deste estudo foi comparar as variações da carga de treino durante um microciclo padrão em escalões de formação sub-15, sub-17 e sub-19 de uma academia de futebol subelite, tendo em conta o status de titularidade. A carga de treino semanal de sessenta jovens futebolistas foi continuamente monitorizada durante seis semanas, através de sistemas de posicionamento global (GPS), cardiofrequencímetros e escalas de perceção de esforço (RPE) e recuperação (TQR). O status de titularidade considerou os jogadores titulares (iniciam pelo menos 55% dos jogos) e não titulares (suplentes em mais de 55% dos jogos). A distância (D) total percorrida apresentou diferenças significativas entre jogadores titulares e não titulares com um tamanho de efeito moderado (t = -2,38, Δ = -428,03 m, p = 0,018, d = 0,26), tendo-se observado um volume de treino maior nos jogadores não titulares (DTitulares = 5105,53 ± 1684,22 vs. D Não titulares = 5533,56 ± 1549,26 m). De igual modo, verificaram-se efeitos interativos e significativos entre as variáveis de carga de treino acumulada, o status de titularidade, o tempo de jogo e a duração da sessão de treino, considerando-se tanto as comparações intraindividuais (F = 140,46; !2 = 0,85; p <0,001) como as interindividuais (F = 11,63 a 160,70; !2 = 0,05 a 0,76; p <0,001). Deste modo, a titularidade parece influenciar também o volume de treino nos escalões de futebol subelite, sendo recomendável priorizar sessões de treino complementar e/ou individualizado para equalizar a carga de treino semanal e, por conseguinte, proporcionar oportunidades de prática similares a jogadores com menos minutos de competição.
- Player Tracking Data and Psychophysiological Features Associated with Mental Fatigue in U15, U17, and U19 Male Football Players: A Machine Learning ApproachPublication . Teixeira, José Eduardo; Afonso, Pedro; Schneider, André; Branquinho, Luís; Maio, Eduardo; Ferraz, Ricardo; Nascimento, Rafael; Morgans, Ryland; Barbosa, Tiago M.; Monteiro, António M.; Forte, PedroOptimizing recovery is crucial for maintaining performance and reducing fatigue and injury risk in youth football players. This study applied machine learning (ML) models to classify mental fatigue in U15, U17, and U19 male players using wearable signals, tracking data, and psychophysiological features. Over six weeks, training loads were monitored via GPS, psychophysiological scales, and heart rate sensors, analyzing variables such as total distance, high-speed running, recovery state, and perceived exertion. The data preparation process involved managing absent values, applying normalization techniques, and selecting relevant features. A total of five ML models were evaluated: K-Nearest Neighbors (KNN), Gradient Boosting (XGBoost), Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT). XGBoost, RF, and DT achieved high accuracy, while KNN underperformed. Using a correlation matrix, average speed (AvS) was the only variable significantly correlated with the rating of perceived exertion (RPE) (r = 0.142; p = 0.010). After dimensionality reduction, ML models were re-evaluated, with RF and DT performing best, followed by XGBoost and SVM. These findings confirm that tracking and wearable-derived data are effectively useful for predicting RPE, providing valuable insights for workload management and personalized recovery strategies. Future research should integrate psychological and interpersonal factors to enhance predictive modeling in the individual long-term health and performance of young football players.
- Machine learning classification of consumption habits of creatine supplements in gym goersPublication . Magalhães, Patrícia C.; Encarnação, Samuel; Forte, Pedro; Teixeira, José Eduardo; Monteiro, A. M.; Barbosa, Tiago M.; Pereira, Ana Maria Geraldes Rodrigues; Schneider, AndréThe aim is to identify usage patterns and the main factors that influence creatine supplementation, providing a basis for future educational interventions and recommendations for safe and effective use. The study was applied to gym goers in Bragança, where a QR code for a survey was released. 158 people participated, 65 non-consumers of creatine supplementation (37.34% men; 22.78% women) and 95 consumers (15.19% men; 24.68% women). Five machine learning algorithms were implemented to classify creatine consumption in gym goers: Logistic Regression, Gradient Boosting Classifier, Ada Boost Classifier, Xgboost Classifier. K-folds cross-validation was implemented to validate the machine learning performance. There was an increased proportion of females with considered themselves not sufficiently informed about the creatine effects/side effects (22.2%) in comparison to males (8.47%), p=0.03. The AdaBoost classifier exposed the best overall performance (86%) in classifying overuse of creatine in gym goers based on their Smoke habits (r = 0.33), grams of creatine used per day (r = 0.50) and lack information about the side effects of creatine intake (r = -0.33). The K-folds method validates the results with very good performance (86%). In conclusion, the five machine learning methods employed well characterized the overuse of creatine in gym goers based on smoke habits, grams of creatine per day, and lack information about the side effects of creatine intake.
- Swimsuits used by elite male swimmers in the 13th FINA world Championship: analysis of freestyle eventsPublication . Neiva, Henrique P.; Vilas-Boas, João Paulo; Barbosa, Tiago M.; Silva, A.J.; Marinho, D.A.Several world records have been broken in recent years. Swimming community speculates this fact is partly related due to the changes in swimsuits characteristics. To swim faster one need to increase the thrust and reduce drag, which can be achieved wearing the new polyurethane swimsuits (Marinho et al., 2009). The purpose of this study was to verify the distribution of different swimsuits used by male swimmers during all the freestyle finals, according to the different distances swum, at the last world championships being held at Rome in 2009.
- Is V̇O2peak a valid estimation of V̇O2max in swimmers with physical impairments?Publication . Feitosa, Wellington G.; Barbosa, Tiago M.; Correia, Ricardo de Assis; Castro, Flávio A. de SouzaPeak and maximal oxygen uptake (V_O2peak and V_O2max, respectively) are used in assessing aerobic power. For swimmers with physical impairments, it is unclear whether the physiological variables obtained in 200-m and Nx200-m tests are similar. The objective of this study is to assess the validity of V_O2peak as an estimator of V_O2max and complementary physiological variables, in particular, carbon dioxide production (V_ CO2), respiratory exchange ratio (RER), minute-ventilation (V_ EÞ and absolute (HR) and relative (%HRmax) heart rates—which were obtained in a time trial test (200- m) and an incremental intermittent test (Nx200-m) performed by swimmers with physical impairments. Methods: Eleven well-trained swimmers with physical impairments performed 200-m all-out and Nx200-m from low to all-out (controlled by a visual pacer), both with a respiratory valve system and a portable gas analyzer. Results: A paired Student’s t-test showed no statistical difference (p > .05) for all comparisons. The intraclass correlation coefficient (ICC) was 0.97 and 0.98 for V_O2 in l/min and ml/kg/min, respectively; ICC = 0.75 to 0.9 for V_ CO2 (l/min and ml/kg/min), V_ E (in l/min) and HR (beats/min); ICC = 0.5 and 0.75 for %HRmax; and ICC < 0.5 for RER. Passing-Bablok regression showed that the dispersions were acceptable, considering the proportionality, except for HR and % HRmax. Bland-Altman method showed a high level of agreement for all variables. Conclusions: The _VO2peak and _VO2max, as well as the physiological variables _VCO2 and HR obtained, respectively, by 200-m and Nx200-m tests in swimmers with physical impairment were not different.