Sleep posture one-shot learning framework based on extremity joint kinematics: In-silico and in-vivo case studies

Elnaggar, O ORCID: 0000-0001-7417-6023, Coenen, F ORCID: 0000-0003-1026-6649, Hopkinson, A, Mason, L ORCID: 0000-0002-0371-3183 and Paoletti, P ORCID: 0000-0001-6131-0377 (2023) Sleep posture one-shot learning framework based on extremity joint kinematics: In-silico and in-vivo case studies Information Fusion, 95. pp. 215-236. ISSN 1566-2535, 1872-6305

Access the full-text of this item by clicking on the Open Access link.

Abstract

Sleep posture is linked to several health conditions such as nocturnal cramps and more serious musculoskeletal issues. However, in-clinic sleep assessments are often limited to vital signs (e.g. brain waves). Wearable sensors with embedded inertial measurement units have been used for sleep posture classification; nonetheless, previous works consider only few (commonly four) postures, which are inadequate for advanced clinical assessments. Moreover, posture learning algorithms typically require longitudinal data collection to function reliably, and often operate on raw inertial sensor readings unfamiliar to clinicians. This paper proposes a new framework for sleep posture classification based on a minimal set of joint angle measurements. The proposed framework is validated on a rich set of twelve postures in two experimental pipelines: computer animation to obtain synthetic postural data, and human participant pilot study using custom-made miniature wearable sensors. Through fusing raw geo-inertial sensor measurements to compute a filtered estimate of relative segment orientations across the wrist and ankle joints, the body posture was characterised in a way comprehensible to medical experts. The proposed sleep posture learning framework offers plug-and-play posture classification by capitalising on a novel kinematic data augmentation method that requires only one training example per posture. Additionally, a new metric together with data visualisations were employed to extract meaningful insights from the postures dataset, demonstrate the added value of the data augmentation method, and explain the classification performance. The proposed framework attained promising overall accuracy as high as 100% on synthetic data and 92.7% on real data, on par with state of the art data-hungry algorithms available in the literature.

Item Type:	Article
Uncontrolled Keywords:	Wearable sensors, Sensor fusion, Data augmentation, One-shot learning, Multi-classifier system, Human posture
Divisions:	Faculty of Science & Engineering > School of Engineering
Depositing User:	Symplectic Admin
Date Deposited:	09 Feb 2023 08:36
Last Modified:	22 Jan 2026 14:44
DOI:	10.1016/j.inffus.2023.02.003
Open Access URL:	https://arxiv.org/abs/2205.10778v1
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3168275
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.