Results 71 to 80 of about 6,930,474 (290)

A New Hybrid Method: CDRL-QNN for Stable IoT Intrusion Detection

Mathematics
The rapid expansion of the Internet of Things (IoT) has increased the risk of large-scale Distributed Denial-of-Service (DDoS) attacks. In high-availability IoT environments, the operational costs of false positives and false negatives are asymmetric ...
Muhammed Yusuf Küçükkara, Furkan Atban, Cüneyt Bayılmış   +2 more
doaj   +1 more source

Lya-DRL-SMC: a Lyapunov-stability-constrained deep reinforcement learning enhanced sliding mode control method for remotely operated vehicles [PDF]

PeerJ Computer Science
Remotely operated vehicles (ROVs) operating in complex marine environments are subject to multimodal disturbances, such as wave forces, ocean currents, and model uncertainties, which pose significant challenges to the robustness and stability of the ...
Shenao Yan, Zini Wang, Hongwen Yu
doaj   +2 more sources

OntOMat: Toward Ontology‐Based Product and Process Design Engineering and Optimization Solutions Fueling Circular Value Chains

Advanced Engineering Materials, EarlyView.
The OntOMat ontology establishes a structured framework for polymer matrix fiber reinforced composite materials, integrating manufacturing processes, characterization methods, and multiscale design through the VDI/VDE 3682 formalized process description standard.
Nicolas Christ, Jörg Hohe, Martin Kördel, Michael Giese, Niklas Toffert, Christian Seidel, Olaf Rehme, Patrik Schneider, Oliver Focke, Elie Abi Aoun, Claas Falldorf, Beñat Gutierrez, Alexandra Kühn, Sven Torstrick-von der Lieth, Christoph Herden, Erik Johannsen, Jan‐Uwe R. Schmidt, Felix Winkelmann, Andreas Schott, Daniel Schott   +19 more
wiley   +1 more source

Optimized scheduling in Cyber–Physical Systems via constrained reinforcement learning

Alexandria Engineering Journal
Online scheduling is a core tool in modern Cyber–Physical Systems (CPS), enabling real-time task assignment under dynamic resource availability and strict operational constraints. While reinforcement learning (RL) offers a principled approach to learning
Fulin An, Huayun Yu
doaj   +1 more source

Learning Multirobot Hose Transportation and Deployment by Distributed Round-Robin Q-Learning. [PDF]

PLoS ONE, 2015
Multi-Agent Reinforcement Learning (MARL) algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning processes carried out by the agents concurrently.
Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano, Manuel Graña   +2 more
doaj   +1 more source

Adaptive Foam 3D Printing of Ultralight and Multifunctional Materials

Advanced Engineering Materials, EarlyView.
Adaptive foam 3D printing, enabled by expandable microspheres, imparts cellular structures to thermoplastic and thermosetting polymers, manufactured through a variety of processes including fused filament fabrication, direct ink writing, digital light processing, and inkjet printing.
Nariman Rajabifar, Amir Ameli
wiley   +1 more source

Dynamic identification and intervention of consumer low-carbon behavior in sustainable textile and apparel consumption driven by deep reinforcement learning

AUTEX Research Journal
Promoting low-carbon consumer behavior is essential for climate mitigation, especially in textile and apparel consumption where purchase, use, reuse, and disposal decisions jointly shape carbon and resource impacts.
Hu Yating
doaj   +1 more source

Leveraging Symbolic Artificial Intelligence and Fuzzy Logic for Materials Science: A Review of Methods, Challenges, and Applications to Scarce and Imperfect Experimental Data

Advanced Engineering Materials, EarlyView.
This article explores the transformative potential of symbolic artificial intelligence (AI) in the field of materials science, particularly in leveraging experimental data. The article presents several symbolic AI models and discusses their applications in materials science.
Ahmed Amrani, Mohamed‐Ali Belloum, Laurence Boudet, Valentin Fouillard, Edwin Friedmann, Guillaume Lacharme, Ali Mahmoud, Jean‐Philippe Poli   +7 more
wiley   +1 more source

Real-World Reinforcement Learning

, 2021
This is our first public release of real-world reinforcement learning, a document with associated code showing how to design and deploy reinforcement learning solutions in customer-facing applications.If you use this software, please cite it as ...
Mason, Douglas
core   +1 more source

Constrained Meta Agnostic Reinforcement Learning

CoRR
Meta-Reinforcement Learning (Meta-RL) aims to acquire meta-knowledge for quick adaptation to diverse tasks. However, applying these policies in real-world environments presents a significant challenge in balancing rapid adaptability with adherence to environmental constraints. Our novel approach, Constraint Model Agnostic Meta Learning (C-MAML), merges
Karam Daaboul, Florian Kuhm, Tim Joseph, J. Marius Zoellner   +3 more
openaire   +3 more sources