Results 41 to 50 of about 9,722 (217)

Hardware Acceleration of Stochastic Neural Networks Enabled by Bit‐Cell Level Co‐Design of Magnetic Tunnel Junctions

Advanced Science, EarlyView.
An MTJ‐based probabilistic processing‐in‐memory architecture unites nonvolatile storage, local entropy generation, and stochastic computation within each memory cell. Stored multi‐bit weights are converted directly into programmable stochastic bitstreams, enabling neural‐network inference, adaptive Ising optimization, and uncertainty‐aware Bayesian ...
Qiuyuan Wang, Dooyong Koh, Brooke McGoldrick, Tudor Mocioi, Yabin Fan, Marc Baldo, Luqiao Liu   +6 more
wiley   +1 more source

From Top to Bottom: Manufacturing Process‐Context Aware Resolution of Energy Device Electrodes Through a 3D Diffusion Generative Model

Advanced Energy Materials, EarlyView.
The application of a generative diffusion model, enhanced with a training data augmentation pipeline retaining the manufacturing process context of electrode microstructures, leads to improved fidelity of the through‐plane tortuosity factor in the AI generated samples.
Victor Ramirez‐Camacho, Siwar Ben Hadj Ali, Maxence Desnoyers, Francisco Fernandez, Nassima Benammar, Alejandro A. Franco   +5 more
wiley   +1 more source

Dual-decoupling of deep reinforcement learning reward function for integrated energy system scheduling: A collaborative mechanism of constraint separation and hierarchical decision-making

International Journal of Electrical Power & Energy Systems
Deep reinforcement learning (DRL) applied to the integrated energy system (IES) scheduling tasks often leads to reward functions composed of multiple coupled components due to the complex structure of IES.
Xiangyan Yang, Shaobing Yang, Liang Hu, Peng Peng, Mingli Wu   +4 more
doaj   +1 more source

Vertical Price Transmission in Food Markets: New Evidence From Meta‐Analysis

Agribusiness, EarlyView.
ABSTRACT A growing body of empirical research has examined price dynamics along the food supply chain, yet findings remain heterogeneous and often conflicting. This study conducts a meta‐analysis of 140 studies, totaling 652 observations, to examine (1) the reported presence of asymmetric price transmission and (2) the reported direction of price ...
Sushan K C, Xiaoli Etienne, Andres Trujillo‐Barrera   +2 more
wiley   +1 more source

Advances in Thermal Modeling and Simulation of Lithium‐Ion Batteries with Machine Learning Approaches

Advanced Intelligent Discovery, EarlyView.
Heat generation in lithium‐ion batteries affects performance, aging, and safety, requiring accurate thermal modeling. Traditional methods face efficiency and adaptability challenges. This article reviews machine learning‐based and hybrid modeling approaches, integrating data and physics to improve parameter estimation and temperature prediction ...
Qi Lin, Kang Fu, Junjie Ding, Kai Sun, Peng Tan   +4 more
wiley   +1 more source

Integrating Reinforcement Learning With Explainable Artificial Intelligence for Real‐Time Clinical Decision Support in Dynamic Healthcare Environments

Advanced Intelligent Systems, EarlyView.
A hybrid Reinforcement Learning–Explainable AI framework integrates SHAP and LIME explanations directly into a Deep Q‐Network inference loop for real‐time ICU decision support. Trained on 18 142 mechanically ventilated stays from the eICU database, the system attains 93.0% decision accuracy, 20% fewer errors than RL alone, and a 91% clinician trust ...
Jannatul Ferdaus Disha, MD Faiaz Zaman Dehan, Kazi Md. Tanvir Anzum   +2 more
wiley   +1 more source

Optimal Security Task Offloading in Cognitive IoT Networks: Provably Optimal Threshold Policies and Model-Free Learning

IoT
The proliferation of Internet of Things (IoT) devices has introduced significant security challenges. Resource-constrained devices face sophisticated threats but lack the computational capacity for advanced security analysis.
Ning Wang, Yali Ren
doaj   +1 more source

Exploiting Edge Semantics in Job Shop Scheduling Problem With Heterogeneous Graph Transformers

Advanced Intelligent Systems, EarlyView.
A heterogeneous graph transformer (HGT) is introduced for reinforcement learning‐based job shop scheduling by explicitly distinguishing precedence and machine‐contention relations through edge‐type‐specific attention. The proposed framework learns richer scheduling representations, improves decision quality over homogeneous graph models, and highlights
Bulent Soykan, Fatih Kasimoglu
wiley   +1 more source

Jumping Threshold-Based Dynamic Event-Triggered Self-Learning Control for IT-2 Fuzzy Semi-Markov Model Under Attack Detection and Mitigation

IEEE Access
This article investigates the optimal control synthesis for a class of semi-Markov jump systems subjected to external disturbances, by integrating advanced event triggered communication and resilient attack mitigation strategies.
P. K. Karan, Karthick Arumugam, Yong-Ki Ma   +2 more
doaj   +1 more source

Stochastic QoE-Aware Optimization in Cloud-Based Content Delivery Networks

IEEE Access, 2018
The problem of cloud resource optimization is examined, while the uncertainty in demand and user feedback is considered. We propose a Markov decision process model for resource assignment in cloud-based content delivery networks.
Ali A. Haghighi, Shahram Shahbazpanahi, Shahram Shah Heydari   +2 more
doaj   +1 more source