Results 191 to 200 of about 177,625 (277)

Disentangling Aleatoric and Epistemic Uncertainty in Physics‐Informed Neural Networks: Application to Insulation Material Degradation Prognostics

Advanced Intelligent Systems, EarlyView.
Physics‐Informed Neural Networks (PINNs) provide a framework for integrating physical laws with data. However, their application to Prognostics and Health Management (PHM) remains constrained by the limited uncertainty quantification (UQ) capabilities.
Ibai Ramirez, Jokin Alcibar, Joel Pino, Mikel Sanz, Jose I. Aizpurua   +4 more
wiley   +1 more source

Variable Bayesian-Based Maximum Correntropy Criterion Cubature Kalman Filter with Application to Target Tracking. [PDF]

Entropy (Basel)
Ma Y, Zhang G, Ye S, An D.
europepmc   +1 more source

Driver Behavior Modeling with Subjective Risk‐Driven Inverse Reinforcement Learning

Advanced Intelligent Systems, EarlyView.
A subjective risk‐driven inverse reinforcement learning framework is proposed to model driver decision‐making. It infers drivers' risk perception and risk tolerance from driving data. A learnable risk threshold is used to regulate decisions, enabling interpretable and human‐like driving behavior decisions.
Yang Liang, Zichao Wang, Zhiwei He, Qingquan Wei, Yong Zuo, Linzhen Nie, Zhishuai Yin   +6 more
wiley   +1 more source

Comb Model in Periodic Potential. [PDF]

Entropy (Basel)
Iomin A, Milovanov A, Sandev T.
europepmc   +1 more source

An Adaptive External Torque Estimation Algorithm for Collision Detection in Robotic Arms. [PDF]

Sensors (Basel)
Yan C, Lyu M, Chen Y, Zhang J.
europepmc   +1 more source

Research on Seafloor 3D Reconstruction Method Based on Sparse Measurement Points. [PDF]

Sensors (Basel)
Xiao E, Qin L, Chi Z, Gu H, Hua Y, Yang H, Li R.   +6 more
europepmc   +1 more source

Metasurfaces and Metadevices for Topological Electromagnetic Waves

Advanced Physics Research, EarlyView.
Optical topologies refer to diverse topological localized structures made by diverse parameters of light fields, such as vortices, skyrmions, and hopfions. This article navigates a direction of metasurface‐based integrated devices for generation, manipulation and detection of novel topologies of light, which would be a rapidly growing interdisciplinary
Rensheng Xie, Nilo Mata‐Cervera, Xi Xie, Yijie Shen   +3 more
wiley   +1 more source

Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers. [PDF]

IEEE Open J Signal Process
Crafts ES, Villa U.
europepmc   +1 more source

A Hybrid Semi‐Inverse Variational and Machine Learning Approach for the Schrödinger Equation

Advanced Physics Research, EarlyView.
A hybrid semi‐inverse variational and machine‐learning framework is presented for solving the Schrödinger equation with complex quantum potentials. Physics‐based variational solutions generate high‐quality training data, enabling Random Forest and Neural Network models to deliver near‐perfect energy predictions.
Khalid Reggab, Houssam Eddine Hailouf, Kingsley Onyebuchi Obodo, Mireille Megnidio‐Tchoukouegno, Mohammed Benali Kanoun, Souraya Goumri‐Said   +5 more
wiley   +1 more source

Generalization of finger-joint kinematics for cleaning tasks. [PDF]

Front Robot AI
Pham C, Tauscher JP, Groth C, Steil JJ.
europepmc   +1 more source