Tag: Kalman filter

Three tiny neural networks, each under 50,000 parameters, cut prediction error by more than half and reached up to 95 ...

A lightweight deep learning system recognizes eating, standing, and lying in dairy cows and tracks each animal at 52.1 frames ...

A self-calibrating vision system that fuses camera images with inertial measurements tracked landslide creep with sub-millimeter accuracy over a 93-day ...

Researchers report an adaptive hybrid association strategy that dynamically blends motion and appearance cues to reduce identity switches and trajectory ...

LHCb's first-level trigger now runs a full Kalman filter track fit on around 500 GPUs at the experiment's full 30 ...

A new data assimilation study of the Brahmaputra basin finds a land water decline of 70.9 gigatons per decade over ...

Researchers introduced a dual-robust unscented Kalman filter, H∞-GMMC-UKF, which significantly improved UAV state estimation accuracy by addressing simultaneous model mismatch ...

A generative adversarial network combined with an unscented Kalman filter reconstructed missing air-quality data across New York City, cutting prediction ...

A new control framework for solar-integrated EV charging stations combines fuzzy logic, Kalman filtering, and predictive control to achieve high ...

Researchers have developed OrbitGuardNet, a hybrid AI defense that detects BeiDou spoofing attacks on drone swarms with up to 98.1 ...