Results 221 to 230 of about 88,757 (305)
Safety Science and Technology, EarlyView.An interpretable machine learning framework with SHAP analysis achieves accurate time‐to‐failure prediction for horizontal pressurized tanks under pool fires while identifying fire intensity, filling level, and wall thickness as dominant drivers of model explanation and uncertainty explanation, providing transparent and actionable insights for ...
Yubin Mu +5 more
wiley +1 more source
Hierarchical Reconfiguration of Neurocognitive Task Set Representations Mediates Cognitive Flexibility. [PDF]
J NeurosciLeach SC, Chen X, Hwang K.
europepmc +1 more source
Attention‐Based Spatial–Temporal Model for the Entire Indoor Space Temperature Estimation
IEEJ Transactions on Electrical and Electronic Engineering, EarlyView.This study proposes a novel attention‐based spatial–temporal model for indoor temperature estimation, which integrates positional encoding and an attention mechanism with a fully connected neural network. By jointly capturing temporal dynamics and spatial correlations, the model enables high‐resolution estimation of temperature fields across the entire
Goro Terumichi +3 more
wiley +1 more source
Real-Hardware Deployment of a Nussbaum-Function PID Controller on a Current-Controlled Low-Cost Actuator via Hardware-Aware Optuna Tuning. [PDF]
Sensors (Basel)Zafaranchizadeh Moghaddam D +2 more
europepmc +1 more source
A Spatio‐Temporal Dynamics Model for Indoor Environmental Forecasting
IEEJ Transactions on Electrical and Electronic Engineering, EarlyView.Accurate forecasting of indoor environmental conditions is essential for intelligent building operations and comfort‐oriented controls. However, reliable prediction remains challenging due to spatial heterogeneity across sensing locations, complex multi‐modal interactions, and nonstationary temporal dynamics.
Goro Terumichi +3 more
wiley +1 more source
Speed-feature-based engine stop-position control for hybrid electric vehicles. [PDF]
Sci RepYuan Y, Lin Z, Wang R, Lu Y.
europepmc +1 more source
Wildlife Biology, EarlyView.Exploration of new wildlife surveying methodologies that leverage advances in sensor technology and machine learning has led to tentative research into the application of seismology techniques. This, most commonly, involves the deployment of a footfall trap – a seismic sensor and data logger customised for wildlife footfall.
Benjamin J. Blackledge +4 more
wiley +1 more source
Artificial Intelligence for Engineering, EarlyView.We present a three‐stage training framework combining Behaviour Cloning warm‐starting with auxiliary‐regularised Deep Reinforcement Learning PPO fine‐tuning for 2D drone waypoint navigation under stochastic wind. Persistent imitation regularisation prevents catastrophic forgetting, achieving robust generalisation to unseen targets and out‐of ...
Ahmet Bilgehan Serçe, Necati Aksoy
wiley +1 more source
Graph neural network‐based attack prediction for communication‐based train control systems
CAAI Transactions on Intelligence Technology, EarlyView.Abstract The Advanced Persistent Threats (APTs) have emerged as one of the key security challenges to industrial control systems. APTs are complex multi‐step attacks, and they are naturally diverse and complex. Therefore, it is important to comprehend the behaviour of APT attackers and anticipate the upcoming attack actions.
Junyi Zhao +3 more
wiley +1 more source