File(s) not publicly available
Slow feature preprocessing in deep neural networks for wearable sensor-based locomotion recognition
conference contribution
posted on 2023-06-10, 05:05 authored by Lukas Kornelius GunthermannLukas Kornelius Gunthermann, Lloyd PellattLloyd Pellatt, Daniel RoggenDaniel RoggenThis 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%.
History
Publication status
- Published
Journal
2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022Publisher
IEEEPage range
58-61Event name
2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)Event location
Pisa, ItalyEvent type
conferenceEvent date
21 Mar 2022 - 25 Mar 2022ISBN
9781665416474Department affiliated with
- Engineering and Design Publications
Full text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2022-10-13Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC