Results 101 to 110 of about 10,210,862 (294)
A versatile framework integrates addressable electrothermal actuation and strain‐constraint mechanisms to construct programmable shape‐morphing soft matter systems. By combining an analytical inverse design strategy for high‐fidelity 3D surface reconstruction with deep learning‐based closed‐loop control, this approach enables zero‐energy shape locking,
Kai Liu +5 more
wiley +1 more source
Unsupervised Multi-Kernel Learning for Automated Algorithm Selection
Automated algorithm selection in black-box optimization typically relies on supervised models that map landscape features to algorithm performance labels. Such models are costly to train, benchmark-dependent, and often fail to generalize to unseen problem classes.
Yihang Lu, Tome Eftimov, Carola Doerr
openaire +2 more sources
Conceptual illustration of a Global Ecosystem Methane Observing System (GEM‐OS) integrating satellites, aircraft, atmospheric networks, and ecosystem measurements to quantify methane emissions from anthropogenic and natural sources. The multi‐scale observing framework improves source attribution, reduces uncertainty in regional methane budgets, and ...
P. Ciais +32 more
wiley +1 more source
Making Indefinite Kernel Learning Practical [PDF]
In this paper we embed evolutionary computation into statistical learning theory. First, we outline the connection between large margin optimization and statistical learning and see why this paradigm is successful for many pattern recognition problems ...
Mierswa, Ingo
core
Probing Electrocatalyst Design for Product Selectivity in CO2 Reduction
Selective CO2 electroreduction is controlled by catalyst structure, dynamic surface reconstruction, adsorbate interactions, and reaction microenvironment. This review summarizes Cu‐ and non‐Cu‐based catalysts, single‐atom and molecular systems, degradation pathways, and operando/computational strategies for steering CO2RR toward hydrocarbons ...
Suvodeep Sen +5 more
wiley +1 more source
A Bearing Fault Diagnosis Method Integrating the SWT and MCNN−RIME−KELM Hybrid Model
To address the issues of severe noise interference, limited classification capability of linear classifiers, and difficulty in adaptively optimizing classifier parameters in rolling bearing fault diagnosis, this paper proposes a hybrid diagnostic model ...
Liping Wang +3 more
doaj +1 more source
Exploiting Multimedia Content: A Machine Learning Based Aproach
This thesis explores use of machine learning for multimedia content management involving single/multiple features, modalities and concepts. We introduce shape based feature for binary patterns and apply it for recognition and retrieval application in ...
Ehtesham Hassan
doaj +1 more source
Kernel matrix visualization as correlation plots ordered by hierarchical clustering.
a: Sequence- and structure-based pairwise similarity matrix. b: Task similarity matrix. c: Multi-task learning kernel matrix. d: Phenotypic similarity matrix. e: Multi-task multi-kernel learning matrix. (PDF)
Christian Malte Boßelmann (14725411) +3 more
core +1 more source
EndoTac presents a trocar‐compatible endoscopic vision‐based tactile sensor that uses a convex mirror to enlarge side‐facing tactile coverage during minimally invasive vessel palpation. Distorted tactile images are unwarped and processed by a learning model to estimate vascular deformation, enabling sensitive, spatially distributed tactile perception ...
Yupeng Wang +5 more
wiley +1 more source
To ensure the reliable operation of power converters and prevent catastrophic failures, this paper proposes a novel online fault diagnosis strategy for a four-level converter.
Ning Xie +3 more
doaj +1 more source

