Movement-Based Sleep Estimation Using a Smart Mattress: Adaptation of Cole–Kripke Algorithm and Comparison with a Multimodal Wearable
Year: 2026
Type: article
Abstract: Multimodal consumer wearables such as Garmin smartwatches combine movement with physiological signals to estimate sleep, whereas bed-based sensing largely relies on movement alone. How far movement alone, sensed from the bed, can go in estimating sleep is unclear. We adapted the Cole–Kripke algorithm to the movement signal of a WhizPad, a smart mattress with a 30-zone pressure array, using the original coefficients and one device-specific scale factor. Estimates were compared with those of a Garmin smartwatch, a proprietary comparator rather than a reference standard, across 28 paired nights in four participants. Epoch-level agreement between the two systems was high for sleep (98.08%) but substantially poorer for wake (30.76%; Cohen’s κ = 0.346). Over each system’s own sleep period, pooled wake after sleep onset (WASO) was 7.3 min lower for the WhizPad and pooled total sleep time (TST) 37.2 min higher, largely through a longer sleep period. The mattress registers bed entry, which Garmin does not export, allowing an exploratory, device-derived estimate of sleep latency that was not independently validated. These findings are descriptive and exploratory, and agreement does not establish the accuracy of either system as no polysomnography (PSG) reference was used. Physiological sensing in the bed and, ultimately, PSG validation are directions for future work.
Source: Sensors
DOI: 10.3390/s26227137
Institution: Yuan Ze University
Language: English
Topic: Sleep and related disorders
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $3,137
OpenAlex ID: W7225876937
