Análisis del número de sensores para la clasificación postural en sedestación

  1. Vermander, Patrick 1
  2. Pérez, Nerea 1
  3. Otamendi, Janire 1
  4. Brull, Asier 1
  5. Mancisidor, Aitziber 1
  6. Cabanes, Itziar 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:
XLIII Jornadas de Automática: libro de actas: 7, 8 y 9 de septiembre de 2022, Logroño (La Rioja)
  1. Carlos Balaguer Bernaldo de Quirós (coord.)
  2. José Manuel Andújar Márquez (coord.)
  3. Ramon Costa Castelló (coord.)
  4. Carlos Ocampo Martínez (coord.)
  5. Jesús Fernández Lozano (coord.)
  6. Matilde Santos Peñas (coord.)
  7. José Enrique Simó Ten (coord.)
  8. Montserrat Gil Martínez (coord.)
  9. Jose Luis Calvo Rolle (coord.)
  10. Raúl Marín Prades (coord.)
  11. Eduardo Rocón de Lima (coord.)
  12. Elisabet Estévez Estévez (coord.)
  13. Pedro Jesús Cabrera Santana (coord.)
  14. David Muñoz de la Peña Sequedo (coord.)
  15. José Luis Guzmán Sánchez (coord.)
  16. José Luis Pitarch Pérez (coord.)
  17. Oscar Reinoso García (coord.)
  18. Oscar Déniz Suárez (coord.)
  19. Emilio Jiménez Macías (coord.)
  20. Vanesa Loureiro Vázquez (coord.)

Publisher: Servizo de Publicacións ; Universidade da Coruña

ISBN: 978-84-9749-841-8

Year of publication: 2022

Pages: 171-178

Congress: Jornadas de Automática (43. 2022. Logroño)

Type: Conference paper

DIALNET GOOGLE SCHOLAR lock_openRUC editor

Abstract

Postural classification is essential for correct monitoring of postural status in the elderly. This monitoring, in addition to providing continuous information to health specialists, can be used to prevent musculoskeletal disorders. In this work, the analysis of the number of sensors of a postural monitoring device composed of 16 FSR sensors is presented. The aim is to reduce the computational cost of classification, simplifying the model and increasing autonomy. To this end, a methodology based on two steps is applied: 1) Calculate the order of relevance of the sensors, using Random Forest and ReliefF. 2) Follow an iterative training process for two classification models based on SVM and KNN. In each iteration the number of sensors introduced as input is increased by one, studying how this number affects the final performance of the models. The results show that a number of 5 sensors is sufficient to achieve hit rates above 90 %.

Data source: Dialnet