2

Comparing aggregate and individual-level (N-of-1) analyses of Oura Ring and smartphone survey data from 256 pregnant participants in the BUMP study shows that population-level trends often fail to reflect individual pregnancy trajectories, supporting personalized wearable-based monitoring.

Abdominal ultrasound recordings of the healthy human colon, analyzed with image segmentation and frequency analysis software, reveal three distinct rhythmic motor patterns at 1, 3 and 12 cycles per minute.

We apply model compression techniques such as pruning and quantization to deep learning image compression models and find that pruning affects different components of these models differently.

We propose a 2-D CNN-LSTM deep learning model that uses a MIMO radar to accurately detect, count, and classify passengers in five-seater vehicles, achieving over 95% accuracy in detecting unattended infants/children, 89% accuracy in counting passengers and identifying their seats, and 74% accuracy in classifying passengers, demonstrating its applicability in any five-seater vehicle.