Learning Optimal Crowd Evacuation from Scratch Through Self‐Play
Advanced Intelligent Systems, Volume 8, Issue 1, January 2026.How would a superintelligent crowd behave in emergencies? This study develops an approach using multiagent deep reinforcement learning combined with self‐play to discover optimal evacuation strategies for pressure‐aware agents. The model learns behaviors such as queuing and zipper‐merging that significantly surpass traditional approaches in fatality ...
Mahdi Nasiri +3 more
wiley +1 more source
A Novel Traffic Scheduling Algorithm for Multi-CQF Using Mixed Integer Programming and Variable Neighborhood Search Genetic Algorithm in Time-Sensitive Networking. [PDF]
Sensors (Basel)Wang C, Lin Z, Zhao Y, Hu F, Huan Z.
europepmc +1 more source
Parallel Algorithm for Approximate State Graph Exploration With Restricted Memory Footprint
Concurrency and Computation: Practice and Experience, Volume 38, Issue 1, January 2026.ABSTRACT We investigate the performance of algorithms that explore large state graphs of finite state machines without input by following paths. To improve on anchor‐based and candidate‐based explorations and to avoid the performance overhead of full anchor lists and the tuning sensitivity of timeout‐based methods, we propose and analyze exploration ...
Jörg Keller, Sebastian Litzinger
wiley +1 more source
IEEE 802.11af-enabled scalable cognitive radio sensor networks with adaptive priority management for early forest fire forewarning. [PDF]
Sci RepAbilasha V, Karthikeyan A.
europepmc +1 more source
Towards Workload‐Tailored Optimization of Job Scheduling Policies in HPC Environments
Concurrency and Computation: Practice and Experience, Volume 38, Issue 1, January 2026.ABSTRACT Supercomputers play a pivotal role in advancing research and development across diverse scientific and engineering domains. However, configuring job scheduling in these systems to ensure maximum productivity and cost‐effectiveness is a challenge. Workload simulation emerges as a crucial tool in this context, offering a mechanism to explore job
João Pedro M. N. dos Santos +2 more
wiley +1 more source
Network traffic control method of NHP based on deep reinforcement learning. [PDF]
Sci RepHuang Q, Tan Z, Wang Q, Jia Z, Chen B.
europepmc +1 more source
FAIR Workflows in Earth System Modelling: A Use Case With Semantic Data Management
Geoscience Data Journal, Volume 13, Issue 1, January 2026.We present a semantic research data management workflow that enables the re‐use of legacy simulation datasets in accordance with FAIR principles. The approach integrates automated semantic annotation, queryable data access, and a connected JupyterHub for FAIR‐compliant output analysis and storage of derived results. ABSTRACT The amount of research data
Sinikka T. Lennartz, Alexander Schlemmer
wiley +1 more source
Real-time traffic signal optimization for urban mobility: a reinforcement learning-enhanced framework with application to Kuwait City. [PDF]
Front Robot AIAlmomany A, Eedi E, Sutcu M.
europepmc +1 more source
Health Science Reports, Volume 9, Issue 1, January 2026.ABSTRACT Background Artificial intelligence (AI) is transforming healthcare by improving care, efficiency, and cost benefit, yet limited research compares its benefits across individual, organizational, and system levels to guide effective integration.
Teferi Gebru Gebremeskel, Frank Romeo
wiley +1 more source