RESUMO
Abstract Introduction Skateboarding is one of the most popular cultures in Brazil, with more than 8.5 million skateboarders. Nowadays, the discipline of street skating has gained recognition among other more classical sports and awaits its debut at the Tokyo 2020 Summer Olympic Games. This study aimed to explore the state-of-the-art for inertial measurement unit (IMU) use in skateboarding trick detection, and to develop new classification methods using supervised machine learning and artificial neural networks (ANN). Methods State-of-the-art knowledge regarding motion detection in skateboarding was used to generate 543 artificial acceleration signals through signal modeling, corresponding to 181 flat ground tricks divided into five classes (NOLLIE, NSHOV, FLIP, SHOV, OLLIE). The classifier consisted of a multilayer feed-forward neural network created with three layers and a supervised learning algorithm (backpropagation). Results The use of ANNs trained specifically for each measured axis of acceleration resulted in error percentages inferior to 0.05%, with a computational efficiency that makes real-time application possible. Conclusion Machine learning can be a useful technique for classifying skateboarding flat ground tricks, assuming that the classifiers are properly constructed and trained, and the acceleration signals are preprocessed correctly.
RESUMO
Este estudo visou analisar parte dos processos de produção das subjetividades skatistas nas suas relações com determinadas normas sociais em jogo na contemporaneidade, especificamente, através de uma vontade de inclusão de indivíduos e grupos sociais posicionados como anormais. A cartografia social foi usada como referencial teórico-metodológico e o material empírico baseou-se em falas de entrevistas ao rádio e à TV, conversas informais, cartazes de eventos, fotos retiradas de redes sociais no modo público e registros de Diário de Rua. Analisamos vetores de normalização sobre os skatistas articulados a determinadas normas sociais, através de ações e falas moralmente reconhecidas como "do bem", com vistas a atribuir traços de legitimidade e normalidade estratégicos no jogo incessante das relações de poder e da condução de si mesmos(AU)
This study aimed to analyze part of the processes of production of skateboarder's subjectivities in their relations with certain social rules that are in place in contemporaneity, specifically through a wish for inclusion by individuals and social groups positioned as abnormal. Social cartography was used as a theoretical-methodological framework and the empirical material included radio and TV interviews, informal conversations, posters of events, pictures taken from social media sites open to the public and street diary notes. We analyzed vectors of normalization related to skateboarders by connecting them with certain social norms through actions and speeches morally recognized as being "for the good", in order to ascribe traits of legitimacy and normalcy that are strategic to the permanent game of power relations and conduction of oneself(AU)
Este estudio tuvo como objetivo analizar parte de los procesos de producción de las subjetividades de los skaters en sus relaciones con determinadas normas sociales establecidas en la época contemporánea, específicamente a través de la voluntad de inclusión de los individuos y grupos sociales tenidos como anormales. La cartografía social fue utilizada como referencial teórico metodológico y el material empírico consistió en entrevistas a la radio y a la televisión, charlas informales, carteles de eventos, fotos retiradas de redes sociales en modo público y registros de Diario de Calle. Analizamos vectores de normalización sobre los skaters que se articulan a determinadas normas sociales, a través de acciones y discursos moralmente reconocidos como "buenos", con vistas a atribuir rasgos de legitimidad y normalidad estratégicos en el juego incesante de las relaciones de poder y de la conducción de sí mismos(AU)