Un método inteligente para estimar el umbral de lactato de atletas recreacionales de manera accesible y no invasiva

  1. Urtats Etxegarai 1
  2. Eva Portillo 1
  3. Jon Irazusta 1
  1. 1 Universidad del País Vasco/Euskal Herriko Unibertsitatea
    info

    Universidad del País Vasco/Euskal Herriko Unibertsitatea

    Lejona, España

    ROR https://ror.org/000xsnr85

Book:
XXXIX Jornadas de Automática: actas. Badajoz, 5-7 de septiembre de 2018
  1. Inés Tejado Balsera (coord.)
  2. Emiliano Pérez Hernández (coord.)
  3. Antonio José Calderón Godoy (coord.)
  4. Isaías González Pérez (coord.)
  5. Pilar Merchán García (coord.)
  6. Jesús Lozano Rogado (coord.)
  7. Santiago Salamanca Miño (coord.)
  8. Blas M. Vinagre Jara (coord.)

Publisher: Universidad de Extremadura

ISBN: 978-84-9749-756-5,  978-84-09-04460-3

Year of publication: 2018

Pages: 880-887

Congress: Jornadas de Automática (39. 2018. Badajoz)

Type: Conference paper

DOI: 10.17979/SPUDC.9788497497565.0880 DIALNET GOOGLE SCHOLAR lock_openRUC editor

Abstract

Lactate threshold is considered an essential physiological variable useful for endurance sports as an aid for training prescription and performance evaluation. However, nowadays there is no reliable way to asses it without specialized equipment or without turning to expensive centres, meaning that it is restricted to few people with access to these resources. Thus, this work proposes a cost-efficient, non-invasive and easily accessible intelligent method to estimate the lactate threshold and so making it accessible to a wider population. A new strategy based on feature standardization combined with Recurrent Neural Network was proposed to model the lactate threshold. In this work, this method is further developed to increase its generalization power and calibrated against a new database. The results show that this system successfully estimates the lactate threshold in 87% of the cases, meaning that our model is a valid accessible tool for lactate threshold assessment.

Data source: Dialnet