English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Infant sleep is critical to brain and behavioral development. Prior studieson infant sleep/wake classification have been largely limited to reliance onexpensive and burdensome polysomnography (PSG) tests in the laboratory orwearable devices that collect single-modality data. To facilitate datacollection and accuracy of detection, we aimed to advance this field of studyby using a multi-modal wearable device, LittleBeats (LB), to collect audio,electrocardiogram (ECG), and inertial measurement unit (IMU) data among acohort of 28 infants. We employed a 3-branch (audio/ECG/IMU) large scaletransformer-based neural network (NN) to demonstrate the potential of suchmulti-modal data. We pretrained each branch independently with its respectivemodality, then finetuned the model by fusing the pretrained transformer layerswith cross-attention. We show that multi-modal data significantly improvessleep/wake classification (accuracy = 0.880), compared with use of a singlemodality (accuracy = 0.732). Our approach to multi-modal mid-level fusion maybe adaptable to a diverse range of architectures and tasks, expanding futuredirections of infant behavioral research.

Classification of Infant Sleep/Wake States: Cross-Attention among Large Scale Pretrained Transformer Networks using Audio, ECG, and IMU Data