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

Elnaggar, Omar; Coenen, Frans; Hopkinson, Andrew; Mason, Lyndon; Paoletti, Paolo

doi:10.1016/j.inffus.2023.02.003

Cited by 2 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The KIDS framework in its current form utilised a bespoke wearable sensor module 11 to measure the segment-to-segment orientation about a single body joint. In this work, this quantity was considered an indicative measure of the whole-body physical activity level during sleep.…”

Section: Discussionmentioning

confidence: 99%

“…Once the sensor module was set up and running, the study proceeded with the simulated sleep protocol, in which the participant was guided through a randomised sequence of 12 common sleep postures. To further assist the participant through the posture replication procedure, a leaflet containing pictures of the 12 sleep postures was initially handed to them (definitions of postures can be found in previous work 11 ). Each posture appeared twice in the sequence, but not consecutively.…”

Section: Methodsmentioning

confidence: 99%

“…The participant study employed a custom-made wearable sensor module, specifically designed to measure the left wrist joint kinematics, or alternatively the hand-to-forearm relative orientation. In a previous work 11 , four such modules were affixed to extremity joints (wrists and ankles) to provide a comprehensive sleep posture classification. However, for a start, this study explored the feasibility of whether the kinematics of a single joint would be sufficient to evaluate postural (in)activity during sleep.…”

Section: Methodsmentioning

confidence: 99%

“…In light of the clinical context outlined above, there has been a growing interest within the research community to study human sleep behaviour. Different aspects were investigated including sleep posture classification 10 , 11 , detection of in-bed movements and posture transitions 12 , 13 , sleep staging 14 , sleep physiology and vital sign monitoring 15 , 16 . Various technologies were employed for at-home and in-clinic sleep monitoring.…”

Section: Introductionmentioning

confidence: 99%

“…The choice of exploiting joint kinematics was motivated by the authors’ recent research which indicated the efficacy of similar kinematic cues from extremity joints (wrists and ankles) in identifying 12 sleep postures 11 . However, this previous work required manual segmentation of each posture to showcase the posture classification performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An interpretable framework for sleep posture change detection and postural inactivity segmentation using wrist kinematics

Elnaggar,

Arelhi,

Coenen

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Sleep posture and movements offer insights into neurophysiological health and correlate with overall well-being and quality of life. Clinical practices utilise polysomnography for sleep assessment, which is intrusive, performed in unfamiliar environments, and requires trained personnel. While sensor technologies such as actigraphy are less invasive alternatives, concerns about their reliability and precision in clinical practice persist. Moreover, the field lacks a universally accepted algorithm, with methods ranging from raw signal thresholding to data-intensive classification models that may be unfamiliar to medical staff. This paper proposes a comprehensive framework for objectively detecting sleep posture changes and temporally segmenting postural inactivity using clinically relevant joint kinematics, measured by a custom-made wearable sensor. The framework was evaluated on wrist kinematic data from five healthy participants during simulated sleep. Intuitive three-dimensional visualisations of kinematic time series were achieved through dimension reduction-based preprocessing, providing an out-of-the-box framework explainability that may be useful for clinical monitoring and diagnosis. The proposed framework achieved up to 99.2% F1-score and 0.96 Pearson’s correlation coefficient for posture detection and inactivity segmentation respectively. This work paves the way for reliable home-based sleep movement analysis, serving patient-centred longitudinal care.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations