Multimodal Indoor Localisation for Measuring Mobility in Parkinson's Disease using Transformers

Ferdian Jovan, Ryan McConville, Catherine Morgan, Emma Tonkin, Alan Whone, Ian Craddock

Research output: Working paperPreprint

Abstract

Parkinson's disease (PD) is a slowly progressive debilitating neurodegenerative disease which is prominently characterised by motor symptoms. Indoor localisation, including number and speed of room to room transitions, provides a proxy outcome which represents mobility and could be used as a digital biomarker to quantify how mobility changes as this disease progresses. We use data collected from 10 people with Parkinson's, and 10 controls, each of whom lived for five days in a smart home with various sensors. In order to more effectively localise them indoors, we propose a transformer-based approach utilizing two data modalities, Received Signal Strength Indicator (RSSI) and accelerometer data from wearable devices, which provide complementary views of movement. Our approach makes asymmetric and dynamic correlations by a) learning temporal correlations at different scales and levels, and b) utilizing various gating mechanisms to select relevant features within modality and suppress unnecessary modalities. On a dataset with real patients, we demonstrate that our proposed method gives an average accuracy of 89.9%, outperforming competitors. We also show that our model is able to better predict in-home mobility for people with Parkinson's with an average offset of 1.13 seconds to ground truth.
Original languageEnglish
PublisherArXiv
Number of pages17
DOIs
Publication statusPublished - 12 May 2022
Externally publishedYes

Bibliographical note

17 pages, 1 figure, 3 tables

Version History

[v1] Thu, 12 May 2022

Keywords

  • Parkinson's disease
  • indoor localisation
  • multimodal data
  • transformer
  • time series

Fingerprint

Dive into the research topics of 'Multimodal Indoor Localisation for Measuring Mobility in Parkinson's Disease using Transformers'. Together they form a unique fingerprint.

Cite this