Continuous Physics‐Informed Learning Expedited Battery Mechanism Decoupling
Advanced Science, Volume 13, Issue 1, 5 January 2026.A battery modeling framework combining dual neural networks with physical prior is presented to track internal mechanisms, decouple overpotential components, and early predict aging trajectories using only DC data, eliminating the need for additional measurements.
Shanling Ji +7 more
wiley +1 more source
3D Indoor Position Estimation Based on a UDU Factorization Extended Kalman Filter Structure Using Beacon Distance and Inertial Measurement Unit Data. [PDF]
Sensors (Basel)Bodrumlu T, Caliskan F.
europepmc +1 more source
Advanced Intelligent Systems, Volume 8, Issue 1, January 2026.This review outlines how recurrent neural networks model multisensory integration by capturing temporal and probabilistic features of sensory input. Key developments, challenges, and future directions are summarized, providing insights into biologically inspired AI. Multisensory integration (MSI) is a core brain function underlying perception, learning,
Ehsan Bolhasani +2 more
wiley +1 more source
Real-time video surveillance on highways using combination of extended Kalman Filter and deep reinforcement learning. [PDF]
HeliyonFu L, Zhang Q, Tian S.
europepmc +1 more source
Advanced Intelligent Systems, Volume 8, Issue 1, January 2026.A memristor‐based associative learning circuit is presented for real‐time, fault‐tolerant sensor fusion in autonomous systems. The circuit mimics biological learning to recognize driving scenarios even with missing or degraded sensor inputs. Its low‐power, analog architecture enables robust decision‐making across diverse conditions, offering a ...
Kapil Bhardwaj +3 more
wiley +1 more source
Skin‐Like Airflow Odometry for Micro Aerial Vehicles Based on Distributed Thermal Anemometers
Advanced Intelligent Systems, Volume 8, Issue 1, January 2026.A novel bioinspired skin‐like airflow odometry system for micro aerial vehicles employs distributed thermal anemometers to enable motion estimation in GNSS‐denied environments. Computational fluid dynamics simulation validates sensor deployment feasibility, while a transformer‐enhanced gated recurrent unit network extracts high‐precision airflow ...
Weicheng Di +7 more
wiley +1 more source
Fault Diagnosis in Wind Turbine Current Sensors: Detecting Single and Multiple Faults with the Extended Kalman Filter Bank Approach. [PDF]
Sensors (Basel)Abbas M, Chafouk H, Ardjoun SAEM.
europepmc +1 more source
Robotic Needle Steering for Percutaneous Interventions: Sensing, Modeling, and Control
Advanced Intelligent Systems, Volume 8, Issue 1, January 2026.This review examines recent advances in robotic needle steering for percutaneous interventions, highlighting closed‐loop sensing, physics‐informed tissue‐needle interaction modeling, and real‐time trajectory planning and control. It synthesizes innovations in deep learning, fiber‐optic feedback, and adaptive control strategies, and outlines emerging ...
Fangjiao Zhao +5 more
wiley +1 more source
Robustness of the Ensemble Score Filter to the Type of Assimilated Observation Networks
Atmospheric Science Letters, Volume 27, Issue 1, January 2026.The development of new geophysical data assimilation methods is accelerating, partly driven by advances in generative AI (GenAI). Using a surface quasi‐geostrophic model, we examine how a recently developed GenAI‐based ensemble method responds to changes in the observation network, compared to a standard ensemble Kalman filter. Our results suggest that
Zixiang Xiong +4 more
wiley +1 more source