Results 181 to 190 of about 47,788 (267)

Professionalising the Cybersystemic Practitioner: Five Decades of STiP Education at the Open University (1971–2025)

open access: yesSystems Research and Behavioral Science, EarlyView.
ABSTRACT This paper draws on over five decades of experience in educating and developing systems thinking practitioners at the Open University (OU) UK to explore the opportunities and challenges in the professionalisation of systems thinking in practice (STiP).
Ray Ison
wiley   +1 more source

Explainable Machine Learning for Predicting Time‐to‐Failure of Horizontal Pressurized Storage Tanks in Fire Scenarios

open access: yesSafety 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

Attention‐Based Spatial–Temporal Model for the Entire Indoor Space Temperature Estimation

open access: yesIEEJ 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

Pickin' up good vibrations: a systematic review of footfall detection and analysis in the realm of wildlife surveying

open access: yesWildlife 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

Waypoint Navigation of a 2D Drone in Stochastic Environment via Regularised Proximal Policy Optimisation

open access: yesArtificial 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

Home - About - Disclaimer - Privacy