This thesis uses predictive models to forecast football injuries.
problem Understanding and predicting football injuries in athletes.
method The study employed machine learning algorithms, feature selection, and exposure records to predict injuries.
result The models accurately predicted injury recovery times, training hours, and fatigue indicators.
Predictive models of training load data failed to accurately predict injuries in Australian football.
problem Predicting injuries in Australian football using training load data.
method Training load data from GPS, accelerometers, and player ratings were analyzed using various predictive models.
result The best model for hamstring injuries had an AUC of 0.76, but overall predictive performance was poor.
Improved fantasy football performance predictor using human feedback.
problem Lack of external factors in traditional statistical models.
method Combining statistical data with human feedback from various sources.
result Model outperformed regular statistical predictors by over 300 points.
Paper uses GPS data and ML to forecast soccer injuries.
problem Injuries in soccer impact team performance and rehabilitation costs.
method Collects GPS training data, constructs injury forecaster using machine learning.
result Injury forecaster is accurate and interpretable, providing practical rules for injury prevention.
We prove that every spherical football (also known as a spherical soccer ball) is a branched cover, branched only in the vertices, of the standard football made up of 12 pentagons and 20 hexagons. We also give examples showing that the corresponding result is not true for footballs of higher genera. Moreover, we classi…
Study tackles workplace injury prediction and prevention.
problem Rare and imbalanced data makes injury risk prediction challenging.
method Ensemble resampling, transfer learning, and variable analysis.
result Improved injury risk prediction and prevention techniques.
Google Research Football: A new 3D physics-based game for reinforcement learning.
problem Training reinforcement learning algorithms in complex, realistic environments.
method Developed a new 3D physics-based football simulator environment.
result Reported baseline results for various reinforcement algorithms.
The study uses unsupervised machine learning to identify top European football teams.
problem Selecting teams for the new European football Super League.
method Used Laplacian eigenmaps clustering on performance data.
result Successfully identified four clusters of teams based on performance metrics.
Unsupervised clustering reveals novel TBI phenotypes.
problem Inadequate categorization of traumatic brain injury (TBI) based on symptoms.
method Applied unsupervised learning with GLRM feature selection.
result Identified four novel TBI phenotypes with distinct feature profiles.
Develops a valuation model for in-play football bets.
problem Valuation and hedging of in-play football bets.
method Model scores using independent Poisson processes, applies Fundamental Theorems of Asset Pricing.
result Derives arbitrage-free valuation formulas for in-play bets.
Optimizes football play calls using reinforcement learning.
problem Maximizing game outcomes with limited data.
method Reinforcement learning to optimize decision-making.
result Optimized play calls lead to better game outcomes.
New framework values football players based on in-game interactions.
problem Valuing football players based on in-game performance.
method Combining financial models and network theory using a passing matrix.
result Dynamic and individualized player valuation framework.
TacticAI helps football coaches improve tactics by analyzing corner kicks.
problem Developing effective responses to rival teams' tactics algorithmically.
method TacticAI combines predictive and generative components to suggest player setups and position adjustments.
result TacticAI's model suggestions are favored over existing tactics 90% of the time by football domain experts.
Paper proposes player roles from match data to help clubs.
problem Difficulty in determining a player's fit for a team's style.
method Identifies 21 player roles from match event data.
result Automatic identification of player roles from match data.
Study describes how compact Ricci solitons degenerate as cone angles approach zero.
problem Understanding degenerations of compact Ricci solitons as cone angles approach zero.
method Completely describes the degenerations of compact Ricci solitons, including the Gromov--Hausdorff limit of cigar solitons from conical teardrop solitons.
result Gromov--Hausdorff limit of cigar solitons from conical teardrop solitons.
AI benchmarks evaluate football team performance using generative models.
problem Evaluating human performance in complex interactive tasks is error-prone and unreliable.
method Trained Conditional VRNN Model on player and ball tracking data to imitate and predict team interactions.
result Trained model as a useful benchmark for evaluating team performance in football.
MRI identifies chronic symptoms in mTBI patients.
problem Chronic symptoms in mTBI patients are hard to characterize.
method Multi-parametric MRI and low-dimensional projection.
result MRI metrics correlate with patient symptoms.
Twitter has been proven to be a notable source for predictive modelling on various domains such as the stock market, the dissemination of diseases or sports outcomes. However, such a study has not been conducted in football (soccer) so far. The purpose of this research was to study whether data mined from Twitter can b…
Extract useful information from football players' trajectories.
problem Automatic processing of two-dimensional positional data during matches.
method Newtonian mechanics, Kalman filter, Generative Adversarial Nets, Variational Autoencoders, Discriminator network.
result Deep generative models can learn underlying structure and statistics of trajectories.
Study examines heart and football-shaped metrics, verifying geometric structure.
problem Analyzing reducible spherical conical metrics and their geometric properties.
method Examined 1-parameter heart shape and 3-parameter football shape families, verified structure theorem, used explicit metric and geodesic calculations.
result Naturally arise from Abelian differentials of the third kind, offer new evidence for spherical geometry and complex analytic structure interaction.
Paper finds new realizable data for maps with three branch points.
problem Existence of rational maps with specific branch points.
method New families of branch data identified through football decomposition method.
result Identifies new realizable branch data and exceptional data.
The paper extends a theorem about scalar curvature and volume in higher dimensions.
problem Finding sharp volume bounds for manifolds with specific curvature conditions.
method Axis symmetry or upper bound on Ricci curvature used to extend the theorem.
result The extension of Bray's football theorem to higher dimensions.
Study uncovers tactical line-breaking passes in football using clustering.
problem Detecting and analyzing line-breaking passes in football matches.
method Unsupervised clustering-based framework using event and tracking data.
result Introduced tactical metrics to quantify pass effectiveness.
We show that spheres of positive constant curvature with n (n≥3) conic points converge to a sphere of positive constant curvature with two conic points (or called an (American) football) in Gromov-Hausdorff topology when the corresponding singular divisors converge to a critical divisor in the sense of Troyanov.…
This study uses reinforcement learning to mitigate imminent collisions by controlling car speed and direction.
problem Mitigating imminent collisions on roads.
method Constructed a model using camera images to predict obstacle dynamics. Trained reinforcement learning policies to control braking and steering.
result Both reinforcement learning policies outperform a baseline policy, with the injury model-based policy showing the highest performance.
Study identifies key MRI features for predicting cognitive performance after mTBI.
problem Identify relevant diffusion MRI metrics for cognitive functions in mTBI patients.
method Proposes a novel feature selection method combining best-first search with genetic algorithm crossover.
result Achieves significantly more accurate predictions than other feature selection algorithms.
Natural language processing predicts AKI onset in ICU patients.
problem Early detection of AKI in ICU patients to improve outcomes.
method Clinical notes were processed to generate word and concept embeddings. Five classifiers and a deep learning model were used to predict AKI.
result The best model achieved an AUC of 0.779 for predicting AKI onset.
Bayesian method for estimating functional graphical models from neuroimaging data.
problem Estimating dependence structures from functional data in neuroscience.
method Fully Bayesian regularization scheme, including direct Bayesian analog of functional graphical lasso and graphical horseshoe.
result Insight into brain compensation after traumatic brain injury.
New method learns time-varying home field advantage in football.
problem Discovering causal factors behind home field advantage in sports.
method DYNAMO: a novel causal discovery method for non-stationary processes.
result Time-varying home field advantages influenced by referee bias.
A new method quantifies uncertainty in brain injury simulations.
problem High computational cost and high-dimensional inputs/outputs limit traditional UQ methods for biofidelic head models.
method Two-stage, data-driven manifold learning framework using Gaussian kernel-density estimation, diffusion maps, and Grassmannian diffusion maps.
result Surrogate models reduce computational cost while providing highly accurate approximations of the computational model.
Automated brain CT image retrieval from traumatic brain injury cohorts using deep neural networks.
problem Manual image retrieval of whole brain CT scans from large clinical cohorts is time-consuming and resource-intensive.
method Proposes a deep convolutional neural network (dMIR) for automated classification of 2D montage images.
result Achieved high accuracy (f1=1.0) for validation and testing data sets.
Improved AI model predicts construction safety outcomes from incident reports.
problem Predicting safety outcomes from incident reports using AI.
method Extracted attributes from incident reports using NLP, trained machine learning models (XGBoost, linear SVM), used model stacking, analyzed per-category attribute importance.
result Attributes are highly predictive of safety outcomes, injury severity is well predicted.
Deep CNN models simulate cognitive deficits from neurodegenerative diseases and TBI.
problem Limited ability to assess damaged neurons in vivo for accurate diagnosis and prognosis.
method Used convolutional neural networks (CNNs) to damage simulated brain connections based on biophysically relevant data on FAS.
result Damage to simulated brain connections leads to human-like cognitive mistakes and quantifiable accuracy reductions.
EdgeLite detects hazardous supermarket floors, improving safety.
problem Detecting hazardous conditions on supermarket floors to prevent injuries.
method Developed a lightweight deep learning model, EdgeLite, for edge devices.
result EdgeLite outperformed state-of-the-art models in detecting hazards on supermarket floors.
Proposes a framework for personalized treatment recommendations using observational data.
problem Estimating patient-level treatment effects from observational data.
method Integrates existing methods for learning patient-level causal models.
result Improves patient outcomes in heart failure patients with acute kidney injury.
The study predicts pass completion probability in NFL games.
problem Estimating the likelihood of NFL pass completion.
method Machine learning algorithm using distance measures and random forest model.
result Developed a method to predict pass completion probability.
Rational maps structure theorem with geometric decomposition and realizability proof.
problem Realizability of rational maps branch data.
method Geometric decomposition of pullback metric into footballs and application to realizability.
result Realizability of branch data for rational maps when k>l+1. Study uses semi-Markov models to analyze respiratory patterns of preterm infants before extubation.
problem Analyzing respiratory patterns of preterm infants before and after extubation.
method Developed semi-Markov models to compare respiratory patterns of infants who succeeded extubation and those who required reintubation.
result Semi-Markov models reveal unique similarities and differences between infants who succeeded extubation and those who required reintubation.
End-to-end model predicts ATR rehabilitation outcomes from missing data.
problem Predicting rehabilitation outcomes for Achilles Tendon Rupture patients from incomplete data.
method Probabilistic framework for simultaneous imputation and prediction.
result Proposed method outperforms traditional methods in predicting ATR rehabilitation outcomes.
SEED RL accelerates deep RL training on modern accelerators.
problem Training deep RL agents on large datasets at high speeds and low cost.
method Centralized inference, IMPALA/V-trace, R2D2, modern accelerators.
result Significant cost reduction and state-of-the-art performance on various games.
Research uses AI and RNN for detecting falls in wearable devices.
problem Detecting falls for timely assistance to prevent injuries.
method Recurrent Neural Network (RNN) with LSTM blocks for online fall detection.
result The RNN-based classifier outperformed the SisFall authors' results.
New method models construction safety risks using injury reports.
problem Improving construction safety through empirical and quantitative analysis.
method Genetic-inspired framework, data-driven approach, Kernel Density Estimators, Copulas.
result Safety risk distribution similar to natural phenomena.
This paper studies the normalized Ricci flow on surfaces with conical singularities. It's proved that the normalized Ricci flow has a solution for a short time for initial metrics with conical singularities. Moreover, the solution makes good geometric sense. For some simple surfaces of this kind, for example, the tear …
New DP mechanism SWAG-PPM improves privacy in deep learning models.
problem Differential privacy struggles with real-world distributions, especially imbalanced data.
method SWAG-PPM uses a pseudo posterior distribution to downweight high-risk records.
result SWAG-PPM outperforms DP-SGD with similar privacy budget and modest utility degradation.
Auto-detection system identifies safety issues in baby products from reviews.
problem Early detection of safety issues in baby products to reduce injuries and deaths.
method Text cleaning, feature extraction, dimensionality reduction, classifier analysis.
result Logistic regression model with 66% precision in identifying top 50 safety issues.
Paper presents Transfer Portal model for accurate player performance predictions.
problem Predicting future player performance after a transfer.
method Personalized neural network and Bayesian updating framework.
result Model generates accurate predictions for player performance at new clubs.
Deep Rule Forests identifies drug-drug and drug-disease interactions causing AKI.
problem Identifying drug-drug and drug-disease interactions leading to AKI.
method Deep Rule Forests (DRF) algorithm discovering rules from multilayer tree models.
result DRF model outperforms other algorithms in prediction accuracy and interpretability.
Deep learning predicts back-pain risk during manual lifting.
problem Detecting incorrect lifting to prevent back injuries.
method 2D Convolutional Neural Network (CNN) without manual feature extraction.
result Deep CNN achieved 90.6% accuracy in classifying lifting risk.