Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.

Bento, N., Rebelo, J., Barandas, M., Carreiro, A., Campagner, A., Cabitza, F., et al. (2022). Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition. SENSORS, 22(19) [10.3390/s22197324].

Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition

Campagner A.;Cabitza F.;
2022

Abstract

Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.
Articolo in rivista - Articolo scientifico
accelerometer; deep learning; domain generalization; human activity recognition;
English
27-set-2022
2022
22
19
7324
open
Bento, N., Rebelo, J., Barandas, M., Carreiro, A., Campagner, A., Cabitza, F., et al. (2022). Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition. SENSORS, 22(19) [10.3390/s22197324].
File in questo prodotto:
File Dimensione Formato  
Bento-2022-Sensors-VoR.pdf

accesso aperto

Descrizione: Article
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 1.56 MB
Formato Adobe PDF
1.56 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/401898
Citazioni
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 10
Social impact