Exploring Activity Transitions in the STA-based Activity Recognition STA ile Aktivite Tanimada Aktivite Gecislerinin Arastirilmasi

Eraslan S., Yatbaz H. Y., EVER E., YILMAZ Y.

28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Turkey, 5 - 07 October 2020, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu49456.2020.9302074
  • City: Gaziantep
  • Country: Turkey
  • Keywords: Activity transition Matrix, Aruba Dataset, Elderly Person, Smart home, Unobtrusive activity recognition
  • Middle East Technical University Northern Cyprus Campus Affiliated: Yes

Abstract

The STA (Scanpath Trend Analysis) based activity recognition approach considers both binary sensors and activity transitions to predict activity for a given instance. It is advantageous over other approaches as it provides higher accuracy with less computational complexity. This study explores the effects of activity transitions on the STA-based activity recognition approach. It investigates how the accuracy of the STA-based approach is affected when activity transitions with lower probabilities are considered, and when a different approach is used to compute transition probabilities. The experiments with the dataset previously used for the evaluation of the approach does not reveal considerable differences in the accuracy.