A hidden Markov model and reinforcement learning‐based strategy for fault‐tolerant control
Abstract This study introduces a data‐driven control strategy integrating hidden Markov models (HMM) and reinforcement learning (RL) to achieve resilient, fault‐tolerant operation against persistent disturbances in nonlinear chemical processes. Called hidden Markov model and reinforcement learning (HMMRL), this strategy is evaluated in two case studies
Tamera Leitao +2 more
wiley +1 more source
Velocity-Constraint Kalman Filtering for Enhanced Bubble Tracking in Motion-Compensated Ultrasound Localization Microscopy. [PDF]
Zhu Y +15 more
europepmc +1 more source
Spatio‐Temporal Dual‐Encoder Transformer for Short‐Term Regional Wind Power Forecasting
ST‐DualFormer separates temporal and spatial encoding to model complex dependencies in regional wind power forecasting. The fused dual‐stream representation enables accurate short‐term regional forecasts from multi‐farm meteorological and historical power data. The method achieved 5.25% nMAE and 7.53% nRMSE for three‐day‐ahead forecasting on real‐world
Jianfeng Che +4 more
wiley +1 more source
A Data Reconstruction Method for Inspection Mode in GBSAR Monitoring Using Sage-Husa Adaptive Kalman Filtering and RTS Smoothing. [PDF]
Qi Y +6 more
europepmc +1 more source
DSGE Model Forecasting: Rational Expectations Versus Adaptive Learning
ABSTRACT This paper compares within‐sample and out‐of‐sample fit of a DSGE model with rational expectations to a model with adaptive learning. The Galí, Smets, and Wouters model is the chosen laboratory using quarterly real‐time euro area data vintages, covering 2001Q1–2019Q4.
Anders Warne
wiley +1 more source
Microgrid anti islanding protection scheme based on deep neural network algorithm and unscented Kalman filtering. [PDF]
Chauhdary ST +5 more
europepmc +1 more source
Time‐Varying Skewness–Kurtosis Dynamics in Bitcoin Markets
ABSTRACT This paper examines the relationship between skewness and kurtosis in Bitcoin spot and futures markets using high‐frequency data. We document a strong convex skewness–kurtosis relationship consistent with theoretical moment restrictions. Trading activity is positively associated with realized kurtosis, particularly in futures markets, though ...
Ariston Karagiorgis, Antonis Ballis
wiley +1 more source
Handling method for GPS outages based on PSO-LSTM and fading adaptive Kalman filtering. [PDF]
Li X, Wang X, Pei C.
europepmc +1 more source
Dynamic Mode Decomposition (DMD) for Low‐Latency Real‐Time Cardiac MRI
ABSTRACT Purpose To demonstrate dynamic mode decomposition (DMD) for high spatiotemporal low‐latency online reconstruction in 2D real‐time cardiac MRI. Methods DMD was applied to 2D spiral balanced steady state free precession (bSSFP) real‐time adult and fetal cardiac MRI at 0.55 T, with data from 10 healthy adult volunteers (3F/7M; age: 21–49; BMI: 20–
Ecrin Yagiz +5 more
wiley +1 more source
Adaptive Kalman Filtering Localization Calibration Method Based on Dynamic Mutation Perception and Collaborative Correction. [PDF]
Huang Z, Xu Q, Sun M, Zhu X, Fan S.
europepmc +1 more source

