This paper presents BabyBelt, a wearable uterine contraction monitoring system designed to improve maternal care access during late pregnancy, when early detection of labor anomalies like preterm labor is critical. Existing solutions including cardiotocography (CTG) and electrohysterography (EHG), are often expensive, immobile, or sensitive to placement and signal artifacts, limiting their utility in low-resource settings. BabyBelt integrates stretchable fabric with Velostat-based piezoresistive sensors and a passive Wheatstone bridge frontend to enable real-time uterine contraction pressure sensing via off-the-shelf microcontrollers. In simultaneous testing on the same pressure setup, the system achieved waveform correlation with clinical CTG of up to 0.9810 during pressure cycles, demonstrating comparable temporal accuracy using materials costing under 70 USD.

Large language models (LLMs) excel at factual recall yet still propagate stale or incorrect knowledge.In-context knowledge editing offers a gradient-free remedy suitable for black-box APIs, but current editors rely on static demonstration sets chosen by surface-level similarity, leading to two persistent obstacles: (i) a quantity-quality trade-off, and (ii) lack of adaptivity to task difficulty.We address these issues by dynamically selecting supporting demonstrations according to their utility for the edit.We propose Dynamic Retriever for In-Context Knowledge Editing (DR-IKE), a lightweight framework that (1) trains a BERT retriever with REINFORCE to rank demonstrations by editing the reward, and (2) employs a learnable threshold to prune low-value examples, shortening the prompt when the edit is easy and expanding it when the task is hard.DR-IKE performs editing without modifying model weights, relying solely on forward passes for compatibility with black-box LLMs.On the COUNTERFACT benchmark, it improves edit success by up to 17.1%, reduces latency by 41.6%, and preserves accuracy on unrelated queries, demonstrating scalable and adaptive knowledge editing.