Tools
Tools
Gunthermann, Lukas K, Pellatt, Lloyd and Roggen, Daniel (2022) Slow feature preprocessing in deep neural networks for wearable sensor-based locomotion recognition. 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), Pisa, Italy, 21 Mar 2022 - 25 Mar 2022. Published in: 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022. 58-61. IEEE ISBN 9781665416474
Full text not available from this repository.Abstract
This paper demonstrates how Slow Feature Analysis (SFA) can be used to transform sensor data before it is classified using a deep neural network. Slow features is concept originating from neurosciences which posits that a function can be regressed to fast changing sensory input to obtain a slower output, commensurate to the dynamics of the physical phenomena. Such dimensionality reduction is a common preprocessing technique. We explore this in the recognition of modes of locomotion and transportation from mobile phone motion sensors. Using a well-established deep learning activity recognition algorithm (DeepConvLSTM), we systematically investigate combinations of slow features as an additional layer, or substituting a layer in the deep network. The data used consists of 5s windows captured by a smartphone acceleration sensor carried at the hips. The results show that SFA can be used to improve the classification performance of the DeepConvLSTM network on an acceleration signal by up to 2.2%.
| Item Type: | Conference Proceedings |
|---|---|
| Keywords: | slow feature analysis, human activity recognition |
| Schools and Departments: | School of Engineering and Informatics > Engineering and Design |
| SWORD Depositor: | Mx Elements Account |
| Depositing User: | Mx Elements Account |
| Date Deposited: | 13 Oct 2022 08:29 |
| Last Modified: | 13 Dec 2022 10:28 |
| URI: | http://sro.sussex.ac.uk/id/eprint/108453 |