The usefulness of genomic prediction in crop and livestock breeding programs has prompted efforts to develop new and improved genomic prediction algorithms, such as artificial neural networks and gradient tree boosting. However, the performance of these algorithms has not been compared in a systematic manner using a wide range of datasets and models. Using data of 18 traits across six plant species with different marker densities and training population sizes, we compared the performance of six linear and six non-linear algorithms. First, we found that hyperparameter selection was necessary for all non-linear algorithms and that feature selection prior to model training was critical for artificial neural networks when the markers greatly outnumbered the number of training lines. Across all species and trait combinations, no one algorithm performed best, however predictions based on a combination of results from multiple algorithms (i.e., ensemble predictions) performed consistently well. While linear and non-linear algorithms performed best for a similar number of traits, the performance of non-linear algorithms vary more between traits. Although artificial neural networks did not perform best for any trait, we identified strategies (i.e., feature selection, seeded starting weights) that boosted their performance to near the level of other algorithms. Our results highlight the importance of algorithm selection for the prediction of trait values.

Physical literacy provides a foundation for lifelong engagement in physical activity, resulting in positive health outcomes. Direct pathways between physical literacy and health have not yet been investigated thoroughly. Associations between physical literacy and well‐being in children ( n = 1073, mean age 10.86 ± 1.20 years) were analysed using machine learning. Motor competence (TGMD‐3 and BOT‐2) and health‐related fitness (PACER and plank) were assessed in the physical competence domain. Motivation (adapted‐Behavioural Regulation in Exercise Questionnaire) and confidence (modified‐Physical Activity Self‐Efficacy Scale) were assessed in the affective domain. Well‐being was measured using the KIDSCREEN‐27. Accuracy of predicting well‐being from physical literacy was investigated using five machine learning classifiers (decision tree, random forest, XGBoost, AdaBoost, k ‐nearest neighbour) in the full sample and across subgroups (sex, socioeconomic status [SES], age). XGBoost predicted well‐being from physical literacy with an accuracy of 87% in the full sample. Predictive accuracy was lowest in low SES participants. Contribution of physical literacy features differed substantially across subgroups. Physical literacy predicts well‐being in children but the relative contribution of physical literacy features to well‐being differs substantially between subgroups.

Cullen, BD, Roantree, M, McCarren, A, Kelly, DT, O'Connor, PL, Hughes, SM, Daly, PG, and Moyna1, NM. Physiological profile and activity pattern of minor Gaelic football players. J Strength Cond Res 31(7): 1811–1820, 2017—The purpose of this study was to evaluate the physiological profile and activity pattern in club- and county-level under-18 (U-18) Gaelic football players relative to playing position. Participants (n = 85) were analyzed during 17 official 15-a-side matches using global positioning system technology (SPI Pro X II; GPSports Systems, Canberra, Australia) and heart rate (HR) telemetry. During the second part of this study, 63 participants underwent an incremental treadmill test to assess their maximal oxygen uptake (V̇o₂max) and peak HR (HRmax). Players covered a mean distance of 5,774 ± 737 m during a full 60-minute match. The mean %HRmax and %V̇o ₂ max observed during the match play were 81.6 ± 4.3% and 70.1 ± 7.75%, respectively. The playing level had no effect on the distance covered, player movement patterns, or %HRmax observed during match play. Midfield players covered significantly greater distance than defenders (p = 0.033). Playing position had no effect on %HRmax or the frequency of sprinting or high-intensity running during match play. The frequency of jogging, cruise running, striding (p = 0.000), and walking (p = 0.003) was greater in the midfield position than in the forward position. Time had a significant effect (F _(1,39) = 33.512, p-value = 0.000, and JOURNAL/jscr/04.03/00124278-201707000-00008/inline-formula1/v/2023-08-19T002737Z/r/image-tiff = 0.462) on distance covered and %HRmax, both of which showed a reduction between playing periods. Gaelic football is predominantly characterized by low-to-moderate intensity activity interspersed with periods of high-intensity running. The information provided may be used as a framework for coaches in the design and prescription of training strategies. Positional specific training may be warranted given the comparatively greater demands observed in the midfield playing position. Replicating the demands of match play in training may reduce the decline in distance covered and %HRmax observed during the second half of match play.

Physical literacy (PL) is highlighted as a construct that can positively impact physical activity (PA). Measurement methods and definitions for PL exist, but vary between research groups. This variation affects the ability to compare research findings. The purpose of this study was to assess the construct validity of PL in children. PL was operationalised according to Whitehead’s (2001 ) definition, comprising confidence, motivation, physical competence, and knowledge and understanding. Participants ( n = 1073; mean age 10.86 ± 1.20 years: 53% male) were measured on: (i) confidence (Physical Activity Self-Efficacy Scale; Bartholomew et al., 2006 ), (ii) motivation (Behavioural Regulation in Exercise-Adapted; Sebire et al., 2013 ), (iii) physical competence (health-related fitness: 20 m shuttle run, back-saver sit-and-reach, handgrip strength, plank); balance (Bruininks-Oseretsky Test of Motor Proficiency 2; Bruininks, 2005 ); object-control and locomotor skills (Test of Gross Motor Development-3rd edition (TGMD-3); Ulrich, 2016 ); and (iv) knowledge and understanding (PA and sedentary guidelines). Confirmatory factor analysis (CFA) was conducted to analyse the factor structure of PL. The best-fitting model (χ² = 209.8, df = 99, p < 0.001; comparative fit index = 0.95, normed fit index = 0.91, Tucker–Lewis index = 0.93, root mean square error of approximation = 0.032, 95% confidence interval: 0.026–0.038) was a three-component model containing the domains of motivation, confidence, and physical competence. The knowledge and understanding domain did not fit the model well. Factor loadings were highest for confidence and motivation. Findings support the adoption of a pragmatic approach to PL measurement. CFA results indicated a similar factor structure as has been identified in other studies which have used different tools to measure PL domains.

• This paper presents a new method for generating 50K diverse synthetic time series. • We present a discussion on time series characteristics and metrics with a view to understanding time series diversity. • We developed a robust framework for validating diversity in synthetic time series generation.