Results 111 to 120 of about 20,451 (264)

Constrained Pareto Set Identification with Bandit Feedback

open access: yesCoRR
To appear in Proceedings of ...
Kone, Cyrille   +2 more
openaire   +4 more sources

Talk to Your Data: An Agentic Artificial Intelligence‐Driven Decision‐Support Framework for Prosumer Energy Optimization and Recommendations

open access: yesAdvanced Intelligent Systems, EarlyView.
An agentic AI‐driven decision‐support framework for prosumers is proposed, integrating PV generation, load profiling, and multihorizon optimization within a four‐agent architecture. The approach significantly reduces grid dependence, enhances self‐sufficiency and prevents system oversizing.
Adela BÂRA, Simona‐Vasilica OPREA
wiley   +1 more source

Evolutionary Preference Sampling for Pareto Set Learning

open access: yesProceedings of the Genetic and Evolutionary Computation Conference
Genetic and Evolutionary Computation Conference (GECCO '24)
Rongguang Ye   +3 more
openaire   +2 more sources

Overcoming the Phase Discontinuity Problem in RIS Optimization: A Robust and Scalable Phase‐Aware Deep Regression Framework via Hybrid CNN–LSTM Architecture

open access: yesAdvanced Intelligent Systems, EarlyView.
The phase discontinuity problem—where the cyclic nature of phase angles causes catastrophic errors near the ±π boundary—is a fundamental obstacle in learning‐based reconfigurable intelligent surface (RIS) optimization. A phase‐aware hybrid CNN–LSTM framework resolves this by decomposing phase predictions into sine–cosine components, mapping circular ...
Seda Savaşçı Şen   +3 more
wiley   +1 more source

How cold is too cold? A theoretical analysis of the optimal trigger for index insurance for frost damage to crops

open access: yesAmerican Journal of Agricultural Economics, EarlyView.
Abstract Crop insurance is undoubtedly an extremely valuable element in protecting agricultural businesses, but in many cases standard indemnity‐based products have had very low uptake due to high transaction costs elevating premiums to unaffordable levels.
Amogh Prakasha Kumar   +2 more
wiley   +1 more source

Assessing Progression Independent of Relapse Activity in Multiple Sclerosis Using a Patient‐Reported Disability Measure and Self‐Administered Neuroperformance Outcomes

open access: yesAnnals of Neurology, EarlyView.
Objective The objective of this study was to investigate the ability of patient‐reported/administered outcomes to capture disability worsening and progression independent of relapse activity (PIRA) in multiple sclerosis (MS). Methods We included patients from the longitudinal multicenter MS PATHS cohort with ≥3 assessments and >6 months follow‐up. PIRA
Evy M. Reinders   +40 more
wiley   +1 more source

From Marginal to Central: Marginal Zone‐like B Cells as Critical Targets in Cladribine‐Treated Multiple Sclerosis

open access: yesAnnals of Neurology, EarlyView.
Objective Multiple sclerosis (MS) is a chronic autoimmune disease where B cells play a central pathogenic role. Cladribine, an oral therapy, provides durable benefits by reshaping lymphocyte populations, yet its specific long‐term impact on distinct B‐cell subsets is not fully understood.
Marta Pirronello   +20 more
wiley   +1 more source

Design and Optimization of a Double‐Column Vapor Recompression Heat Pump Distillation Process via NSGA‐II for Separating Ternary Wide‐Boiling Mixtures

open access: yesAsia-Pacific Journal of Chemical Engineering, EarlyView.
ABSTRACT This study proposes a novel double‐column vapor recompression heat pump (DCVRHP) distillation process for separating ternary wide‐boiling‐range mixtures under two different vapor conditions: n‐hexane/n‐heptane/n‐octane using low pressure steam and n‐hexanol/n‐octanol/n‐decanol using high pressure steam.
Zeyang Li   +4 more
wiley   +1 more source

Accelerating Sustainable Epoxy Resin Development Through Bayesian Optimization and Inverse Design

open access: yesJournal of Applied Polymer Science, EarlyView.
Development of a machine learning framework for the optimization of the Tg of partially bio‐based epoxy resin formulations in a 13‐component design space using Bayesian optimization, active learning, random design, and inverse design. The results show that the BO effectively navigates high‐dimensional formulation spaces, and the final ML model could ...
Natalie Wunder   +3 more
wiley   +1 more source

Process Optimization of Solution Blow Spinning for Poly (N‐Isopropylacrylamide) Fibers

open access: yesJournal of Applied Polymer Science, EarlyView.
Solution blow spinning has emerged as a safe and scalable technique for fabricating thermoresponsive PNIPAM fibers. The influence of key parameters on jet stability and fiber uniformity is determined through both rheological analysis and statistical process optimization. A Box–Behnken design reveals an optimized window for producing PNIPAM fibers below
Maryam Parastar   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy