Título: Seleção De Fatores De Risco De Lesões Em Atletas, Através Da Extração De Conhecimento Dos Pesos De Uma Rede Neural
Autores: Alves, Havana Diogo; Valença, Mêuser Jorge Silva
Resumo: The increased incidence of injuries in Brazilian athletes is of concern to then and their coaches and technical staff. The injuries are a result of various factors, and know the influence of each in favor of lesions can help prevent and treat these injuries. In health, traditional statistical methods are commonly used in the study of several cases, but it is noteworthy that such methods only detect the linear features of the data. As the real world is full of non-linear phenomena, it becomes necessary to use techniques that realize this nonlinearity. For these cases, the Artificial Neural Networks (ANN) have shown satisfactory results. This article aims to test algorithms for variable selection that extract knowledge of the weights of an ANN, to obtain the contribution of each factor in the occurrence of injuries to athletes. It is hoped that finding a new alternative needs to understand the mechanisms that favor injuries, and therefore help in prevention.
Palavras-chave: Redes Neurais; Seleção de Variáveis; Lesões; Fatores de risco; Atletas
Código DOI: 10.21528/CBIC2011-08.4
Artigo em pdf: st_08.4.pdf
Arquivo BibTex: st_08.4.bib