Results 131 to 140 of about 1,473,129 (216)
Cross Wavelet Transform (XWT) is combined with a pre‐trained AlexNet to extract rich time‐frequency features from non‐stationary EEG signals. Also, the proposed framework simultaneously extracts and integrates spatial (Node2vec), time‐frequency (XWT + AlexNet), and spectral (PSD + TSCN) features from EEG and ERP signals within a parallel architecture ...
Atefeh Abedzadeh Attar +2 more
wiley +1 more source
This study presents a hybrid AI framework that enables autonomous magnetic microrobots to navigate complex, non‐Newtonian tumor microenvironments. By integrating physics‐informed recurrent reinforcement learning with active persistent excitation, the system successfully infers hidden fluid rheology for precise targeted navigation and structural causal ...
Xinyuan Chen +2 more
wiley +1 more source
Sensorless Contact Force Estimation and Adaptive Variable-Damping Compliant Control for Biomimetic Robotic Arm. [PDF]
Xie Y, He J, Zhang Y.
europepmc +1 more source
Model‐Enabled Knowledge Transfer Across Cell Lines, Culture Scales and Conditions
ABSTRACT Mechanistic models are central to quantitative understanding and optimization of Chinese hamster ovary (CHO) cell culture processes, but their utility is often restricted by parameter sets calibrated for specific cell lines, scales, or operating conditions.
Luxi Yu +2 more
wiley +1 more source
Software-Defined UHF RFID Asset Tracking in Metallic Aircraft Cabins via IMU-Assisted Adaptive Kalman Filtering and Distilled Edge Intelligence. [PDF]
Karadag M, Pinarer O.
europepmc +1 more source
There are problems of insufficient accuracy in capturing small motion trajectories and delay in real‐time motion state estimation in the training of track and field athletes. Based on the improved YOLOv8 framework, this paper introduces 3D convolution to construct a spatiotemporal feature pyramid (ST‐FPN) and embeds an optical flow‐guided cross‐frame ...
Yu Ao, Wu Guancheng, Chen Xi
wiley +1 more source
An Adaptive Estimation Method for Heterogeneous Group Targets with Uncertain Multiplicative and Additive Noises. [PDF]
Liu Z, Jing W, Wang P, Gu W, Ma T.
europepmc +1 more source
QG‐Python is an open, reproducible 1.5‐layer quasi‐geostrophic modelling service whose published diagnostics show that the classical von Neumann bound underestimates the true Leapfrog stability limit by a factor of 13.7, and that the Robert–Asselin–Williams filter reduces kinetic energy and enstrophy biases from ~21% and ~45% to under 4%.
Elias D. Nino‐Ruiz
wiley +1 more source
Beat Frequency Estimation in a Square He-Ne Ring Laser Gyroscope: Joint I/Q Channel Calibration and Kalman Filtering. [PDF]
Shi L +7 more
europepmc +1 more source

