Plenty of supervised machine learning techniques that use accelerometer and gyroscope signals for automatic Human Activity Recognition (HAR) has been proposed in the last decade. According to recent studies, the combination of accelerometer and gyroscope signals, also called multimodal recognition, increases the accuracy in HAR with respect to the use of each signal alone. This paper presents the results of an analysis we performed in order to compare the effectiveness of machine learning techniques when used separately or jointly on accelerometer and gyroscope signals. We compare SVM and k- NN classifiers (combined with hand-crafted features) with a deep residual network using three publicly available datasets. The results show that the use of deep learning techniques in multimodal mode (i.e., using accelerometer and gyroscope signals jointly) outperforms other strategies of at least 10%.

Ferrari, A., Micucci, D., Mobilio, M., Napoletano, P. (2019). Human activities recognition using accelerometer and gyroscope. In Ambient Intelligence (pp.357-362). Springer [10.1007/978-3-030-34255-5_28].

Human activities recognition using accelerometer and gyroscope

Ferrari A.;Micucci D.;Mobilio M.;Napoletano P.
2019

Abstract

Plenty of supervised machine learning techniques that use accelerometer and gyroscope signals for automatic Human Activity Recognition (HAR) has been proposed in the last decade. According to recent studies, the combination of accelerometer and gyroscope signals, also called multimodal recognition, increases the accuracy in HAR with respect to the use of each signal alone. This paper presents the results of an analysis we performed in order to compare the effectiveness of machine learning techniques when used separately or jointly on accelerometer and gyroscope signals. We compare SVM and k- NN classifiers (combined with hand-crafted features) with a deep residual network using three publicly available datasets. The results show that the use of deep learning techniques in multimodal mode (i.e., using accelerometer and gyroscope signals jointly) outperforms other strategies of at least 10%.
paper
Deep learning; Human Activity Recognition; Inertial sensors; Machine learning
English
European Conference on Ambient Intelligence, AmI 2019
2019
Ambient Intelligence
9783030342548
2019
11912
357
362
none
Ferrari, A., Micucci, D., Mobilio, M., Napoletano, P. (2019). Human activities recognition using accelerometer and gyroscope. In Ambient Intelligence (pp.357-362). Springer [10.1007/978-3-030-34255-5_28].
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/10281/255376
Citazioni
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 11
Social impact