One of the main problems in applying deep learning techniques to recognize activities of daily living (ADLs) based on inertial sensors is the lack of appropriately large labeled datasets to train deep learning-based models. A large amount of data would be available due to the wide spread of mobile devices equipped with inertial sensors that can collect data to recognize human activities. Unfortunately, this data is not labeled. The paper proposes DISC (Deep Inertial Sensory Clustering), a DL-based clustering architecture that automatically labels multi-dimensional inertial signals. In particular, the architecture combines a recurrent AutoEncoder and a clustering criterion to predict unlabelled human activities-related signals. The proposed architecture is evaluated on three publicly available HAR datasets and compared with four well-known end-to-end deep clustering approaches. The experiments demonstrate the effectiveness of DISC on both clustering accuracy and normalized mutual infor-mation metrics.

Amrani, H., Micucci, D., Napoletano, P. (2022). Unsupervised Deep Learning-based clustering for Human Activity Recognition. In IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin (pp.1-6). IEEE Computer Society [10.1109/ICCE-Berlin56473.2022.9937141].

Unsupervised Deep Learning-based clustering for Human Activity Recognition

Amrani H.;Micucci D.;Napoletano P.
2022

Abstract

One of the main problems in applying deep learning techniques to recognize activities of daily living (ADLs) based on inertial sensors is the lack of appropriately large labeled datasets to train deep learning-based models. A large amount of data would be available due to the wide spread of mobile devices equipped with inertial sensors that can collect data to recognize human activities. Unfortunately, this data is not labeled. The paper proposes DISC (Deep Inertial Sensory Clustering), a DL-based clustering architecture that automatically labels multi-dimensional inertial signals. In particular, the architecture combines a recurrent AutoEncoder and a clustering criterion to predict unlabelled human activities-related signals. The proposed architecture is evaluated on three publicly available HAR datasets and compared with four well-known end-to-end deep clustering approaches. The experiments demonstrate the effectiveness of DISC on both clustering accuracy and normalized mutual infor-mation metrics.
paper
AutoEncoder; Deep learning; Human Activity Recognition; Unsupervised learning;
English
12th IEEE International Conference on Consumer Electronics, ICCE-Berlin 2022 - 2 September 2022 through 6 September 2022
2022
IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
9781665456760
2022
2022-September
1
6
none
Amrani, H., Micucci, D., Napoletano, P. (2022). Unsupervised Deep Learning-based clustering for Human Activity Recognition. In IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin (pp.1-6). IEEE Computer Society [10.1109/ICCE-Berlin56473.2022.9937141].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/10281/398573
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact