ARTICLE | doi:10.20944/preprints201901.0233.v1
Subject: Social Sciences, Psychology Keywords: dependence; symptomatic; asymptomatic; kickboxing; taekwondo; muaythai
Online: 23 January 2019 (09:55:56 CET)
Debates about the conditions in which the frequency and intensity principles of regular exercise, depending on the fact that sports background can be accepted as extremism, are still a controversial topic. The purpose of this research is to investigate the Exercise Dependence of Athletes doing Kickboxing, Taekwondo and Muaythai. The study included 141 athletes consisting of 87 men and 54 women. Exercise Dependence Scale composed of 21 items developed by Hausenblas and Downs and adapted into Turkish version by Yeltepe and İkizler was applied to athletes. As a result of the research, while athletes showed more sensitivity to exercise dependence scale (= 71.41), this scale was also defined as symptomatic. It was found that 5 athletes (3.5%) were asymptomatic-nondependent, 117 athletes (83.0%) were symptomatic-nondependent and 19 athletes (13.5%) were at-risk for exercise dependence. It was determined that athletes were at-risk for exercise dependence group while 8 athletes were doing kickboxing, 10 athletes were doing taekwondo and 1 athlete was doing muaythai athlete. A significant difference was observed according to regular training and number of daily training. It didn’t significantly differ in other variables. It is possible to say that regular training can be effective to reveal the exercise dependence.
ARTICLE | doi:10.20944/preprints202307.0977.v1
Subject: Social Sciences, Behavior Sciences Keywords: taekwondo; miluh-chagi; motor behavior; motor development; observational methodology
Online: 14 July 2023 (09:15:27 CEST)
Taekwondo masters and coaches believe that they have a kind of “eagle eye” and that is why they feel comfortable to analyze athletes’ skills without using essential tools. The aim of this study was to analyze the athletes’ technical indicators during performance of the Miluh-chagi kick. To analyze the reliability and precision of the cycle of ten kicks (n = 120), performed by 5 women and 7 men senior athletes, we used an expert panel and a previously published observational tool. The coefficient of variation was calculated to verify precision. The intraclass correlation coefficient was calculated to confirm the reliability among the evaluators. Student’s t-test was used for group-to-group analysis. Correlation analyses were accessed using Spearman’s rho. The data quality sample reliability results, for group, intra- and inter-rater were excellent and good re-spectively. Statistically significant differences, with a large effect size, were found in the foot take-off, knee up and start leg flexion observational moments. The values showed a small and negative to moderate correlation between the conducts and aggregates criteria. Perfect correlation values were found between support leg foot and contact leg position. These findings meet the measurement requirements of athletes’ technical indicators to analyze motor behavior, develop-ment and performance of this technique.
ARTICLE | doi:10.20944/preprints202308.1432.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Taekwondo poomsae; action recognition; skeletal data; camera viewpoint; martial arts
Online: 21 August 2023 (07:48:57 CEST)
Issues of fairness and consistency in Taekwondo poomsae evaluation have emerged owing to the lack of an objective evaluation method. This study proposes a three-dimensional (3D) convolutional neural network (CNN)-based action recognition model for the objective evaluation of Taekwondo poomsae. The model exhibits robust recognition performance regardless of variation in perspective by reducing the discrepancies between training and test images. The model uses 3D skeletons of the poomsae unit action collected using a full-body motion-capture suit to generate synthesized two-dimensional (2D) skeletons from the desired perspective. This approach aids in obtaining 2D skeletons from diverse perspectives as part of the training dataset and ensures consistent recognition performance regardless of the viewpoint. The model was trained using 2D skeletons projected from diverse viewpoints, and its performance was evaluated using various test datasets, including projected 2D skeletons and RGB images captured from various viewpoints. Comparison of the performance of the proposed model with that of previously reported action recognition models demonstrated the superiority of the model, underscoring its effectiveness in recognizing and classifying Taekwondo poomsae actions.