20.500.12556/RUL-148409 Analiza poškodb pri športnih plesalcih z metodami strojnega učenja Analysis of Injuries in Sports Dancers using Machine Learning Methods Področje športnega plesa je izjemno tekmovalno, fizično zahtevno ter psihično naporno področje, zato prihaja do visokega števila poškodb plesalcev. Da bi ugotovili vzroke za poškodbe, so na Fakulteti za šport izvedli meritve za 259 plesalk in plesalcev različnih plesnih zvrsti (hiphop, rokenrol, standardni in latinsko-ameriški plesi ter breakdance). Meritve so vključevale merjenje telesne sestave, nekaterih gibalnih sposobnosti, preko vprašalnikov pa so preverili pojavnost poškodb, stopnjo obremenitve in osnovne demografske podatke o posameznem merjencu. Nekatere meritve so bile izvedene dvakrat (tri mesece po prvih meritvah). Ker so najpogostejše poškodbe plesalcev na področju gležnja, kolena, hrbtenice in ramena, smo z uporabo različnih algoritmov strojnega učenja (angl. "machine learning") zgradili napovedne modele za napoved poškodb omenjenih delov telesa. Na podlagi razlik med prvimi in drugimi meritvami smo zgradili modele za ocenjevanje napredka plesalcev. Za izbor najpomembnejših atributov smo uporabili algoritem ReliefF, modele pa smo tudi ustrezno interpretirali z uporabo knjižnice SHAP. Za modeliranje smo uporabili logistično regresijo, naivnega Bayesa, nevronsko mrežo, metodo podpornih vektorjev (SVM), naključne gozdove, gradient boosting (GB), eXtreme Gradient Boosting (XGB) ter metodo najbližjih sosedov (KNN). Za napoved poškodb kolena smo dosegli klasifikacijsko točnost 69 %, za napoved poškodb hrbtenice 78 %, gležnja 71 % in ramena 88 %. Z modeli za napoved napredka smo dosegli 98 % točnost, kar nam omogoča njihovo uporabo v praksi ter prepoznavanje ključnih vzrokov za napredek. The field of sports dance is highly competitive, physically demanding, and mentally challenging, leading to a high number of injuries among dancers. In order to identify the causes of these injuries, measurements were conducted on 259 dancers of various dance styles (hip-hop, rock and roll, standard and Latin American dances, and breakdance) at the Faculty of Sport. The measurements included body composition, certain motor abilities, and questionnaires to assess the occurrence of injuries, load, and basic demographic data of each participant. Some measurements were repeated twice (three months after the initial measurements). As the most common injuries in dancers are related to the ankle, knee, spine, and shoulder, predictive models for forecasting injuries in these body parts were built using various machine learning algorithms. Based on the differences between the first and second measurements, models were constructed to evaluate dancers' progress. The ReliefF algorithm was used to select the most important attributes, and the models were appropriately interpreted using the SHAP library. Logistic regression, Naive Bayes, neural networks, Support Vector Machines (SVM), Random Forests, Gradient Boosting (GB), eXtreme Gradient Boosting (XGB), and K-Nearest Neighbors (KNN) were used for modeling. For predicting knee injuries, a classification accuracy of 69 % was achieved, for spine injuries 78 %, ankle injuries 71 %, and shoulder injuries 88 %. Models for progress prediction achieved an accuracy of 98 %, enabling their practical application and identification of key factors contributing to progress. strojno učenje klasifikacija poškodbe ples machine learning classification injuries dance true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2023-08-22 08:55:00 2023-08-22 08:55:03 2023-09-11 14:04:16 0000-00-00 00:00:00 2023 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 36489 162353923 Rajher_Rok_-_Analiza_poskodb_pri_sportnih_plesalcih_z_metodami_strojnega_ucenja.pdf Rajher_Rok_-_Analiza_poskodb_pri_sportnih_plesalcih_z_metodami_strojnega_ucenja.pdf 1 4A8DDA67D7AC6D9DA5FAAF222F4F93AA 8a717ce699f8886d79314e28b8e91d1ee9d7818d8370d72f83666cdbaf1f81e8 c63c0a21-40b8-11ee-b9d7-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=172627 Fakulteta za računalništvo in informatiko 0 0 0