Results 61 to 70 of about 8,528 (188)
Advanced Intelligent Discovery, EarlyView.Bayesian optimization enabled the design of PA56 system with just 8 wt% additives, achieving limiting oxygen index 30.5%, tensile strength 80.9 MPa, and UL‐94 V‐0 rating. Without prior knowledge, the algorithm uncovered synergistic effects between aluminum diethyl‐phosphinate and nanoclay.
Burcu Ozdemir +4 more
wiley +1 more source
Hypervolume-based Multi-objective Bayesian Optimization with Student-t Processes [PDF]
, 2016 Student-$t$ processes have recently been proposed as an appealing alternative non-parameteric function prior. They feature enhanced flexibility and predictive variance.
Couckuyt, Ivo +2 more
core +2 more sources
Advanced Intelligent Discovery, EarlyView.Predictive models successfully screen nanoparticles for toxicity and cellular uptake. Yet, complex biological dynamics and sparse, nonstandardized data limit their accuracy. The field urgently needs integrated artificial intelligence/machine learning, systems biology, and open‐access data protocols to bridge the gap between materials science and safe ...
Mariya L. Ivanova +4 more
wiley +1 more source
New approaches for delineating n‐dimensional hypervolumes [PDF]
Methods in Ecology and Evolution, 2017 Abstract Hutchinson's n‐dimensional hypervolume concept underlies many applications in contemporary ecology and evolutionary biology. Estimating hypervolumes from sampled data has been an ongoing challenge due to conceptual and computational issues. We present new algorithms for delineating the boundaries and probability density within n‐dimensional
Blonder, Benjamin +7 more
openaire +3 more sources
Advanced Intelligent Systems, EarlyView.This study presents a multitask strategy for plastic cleanup with autonomous surface vehicles, combining exploration and cleaning phases. A two‐headed Deep Q‐Network shared by all agents is traineded via multiobjective reinforcement learning, producing a Pareto front of trade‐offs.
Dame Seck +4 more
wiley +1 more source
HV-Net: Hypervolume Approximation Based on DeepSets
IEEE Transactions on Evolutionary Computation, 2023 In this letter, we propose HV-Net, a new method for hypervolume approximation in evolutionary multi-objective optimization. The basic idea of HV-Net is to use DeepSets, a deep neural network with permutation invariant property, to approximate the hypervolume of a non-dominated solution set.
Ke Shang +3 more
openaire +3 more sources
A kernel integral method to remove biases in estimating trait turnover
Methods in Ecology and EvolutionTrait diversity, including trait turnover, that differentiates the roles of species and communities according to their functions, is a fundamental component of biodiversity. Accurately capturing trait diversity is crucial to better understand and predict
Guillaume Latombe +3 more
doaj +1 more source
Asia-Pacific Journal of Chemical Engineering, EarlyView.ABSTRACT In order to reflect the actual production situation more comprehensively and optimize the production cost, this paper solves the short‐term scheduling optimization problem for a single pipeline containing high melting point crude oil. Based on the refining plan given by the upper layer, a multi‐objective optimization model with high melting ...
Jing Yao +5 more
wiley +1 more source
Vetor, 2023 Muitos problemas oriundos do mundo real podem ser modelados matematicamente como Problemas de Otimização Multiobjetivo (POMs), já que possuem diversas funções objetivo conflitantes entre si que devem ser minimizadas simultaneamente.
Marcela C. C. Peito +2 more
doaj +1 more source
Energy Science &Engineering, EarlyView.Overview of the under‐study hub energy model showing the energy conversion and distribution among integrated sources and loads. ABSTRACT In this paper, a probabilistic bi‐objective energy management system (EMS) model is proposed for an energy hub (EH) equipped with renewable energy sources such as photovoltaic and wind turbine connected to the main ...
Mohammad Khoshabi +3 more
wiley +1 more source