Feature selection by genetic algorithms for classification of running patterns in high-performance sports

• Grant number: 20/01022-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): May 01, 2020
• Effective date (End): December 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Renato Tinós
• Grantee: Sergio Baldo Junior
• Host Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil

Abstract

The identification of running patterns, especially those associated with fatigue, can assist in designing more efficient workouts and preventing injuries in high-performance sports. However, this task is not trivial due to the complexity of the patterns. An interesting alternative is to use Machine Learning methods, such as Artificial Neural Networks (ANNs), to classify running patterns. In this work, force signals emitted by load cells coupled at the base of a treadmill will be classified by an ANN. It is possible to extract many features (attributes) from these signals, and it is important to identify which ones are most relevant to the classification performed by the ANN. Therefore, this project aims to use Genetic Algorithms to find the best subsets of features extracted from force signals to be used as RNA inputs. (AU)