Citation

Roy D, Girdzijauskas S, Socolovschi S. Sensors (Basel) 2021; 21(19): e6566.

Copyright

(Copyright © 2021, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s21196566

PMID

34640886

Abstract

Wearable sensors are widely used in activity recognition (AR) tasks with broad applicability in health and well-being, sports, geriatric care, etc. Deep learning (DL) has been at the forefront of progress in activity classification with wearable sensors. However, most state-of-the-art DL models used for AR are trained to discriminate different activity classes at high accuracy, not considering the confidence calibration of predictive output of those models. This results in probabilistic estimates that might not capture the true likelihood and is thus unreliable. In practice, it tends to produce overconfident estimates. In this paper, the problem is addressed by proposing deep time ensembles, a novel ensembling method capable of producing calibrated confidence estimates from neural network architectures. In particular, the method trains an ensemble of network models with temporal sequences extracted by varying the window size over the input time series and averaging the predictive output. The method is evaluated on four different benchmark HAR datasets and three different neural network architectures. Across all the datasets and architectures, our method shows an improvement in calibration by reducing the expected calibration error (ECE)by at least 40%, thereby providing superior likelihood estimates. In addition to providing reliable predictions our method also outperforms the state-of-the-art classification results in the WISDM, UCI HAR, and PAMAP2 datasets and performs as good as the state-of-the-art in the Skoda dataset.

Language: en

Keywords

deep learning; confidence calibration; human activity recognition; model reliability; signal processing; time-series classification; training algorithm; wearable sensors