Researcher
Tom Dhaene
- Keywords:design optimization, surrogate modeling, data-efficient machine learning
- Disciplines:Machine learning and decision making, Modelling and simulation, Computer-aided design, Electromagnetism and antenna technology, Antennas and propagation, Health informatics
Affiliations
- Department of Information technology (Department)
Member
From1 Jan 1993 → Today
Projects
1 - 10 of 19
- Bayesian Active Learning for EMI Near-Field Emission Characterization of High-Speed ElectronicsFrom1 Jan 2024 → TodayFunding: FWO research project (including WEAVE projects)
- Machine Learning and Radar Sensors for Monitoring Patients and Elderly People in HealthcareFrom1 Feb 2023 → 30 Sep 2023Funding: BOF - doctoral mandates
- Generative design of linear passive electronic systemsFrom1 Jan 2019 → 31 Dec 2022Funding: FWO research project (including WEAVE projects)
- Learning complex patterns with Gaussian processesFrom1 Jan 2019 → 31 Dec 2022Funding: FWO research project (including WEAVE projects)
- Incorporating error control in sparse modellingFrom1 Jan 2016 → 31 Dec 2019Funding: FWO research project (including WEAVE projects)
- Development of machine learning techniques for flow cytometry dataFrom1 Jan 2014 → 31 Dec 2017Funding: IWT personal funding - specialisation scholarships
- Fast and Reliable Assessment of Electromagnetic Field Exposure using Sequential Sampling, Surrogate Modeling and OptimizationFrom1 Jan 2014 → 31 Dec 2019Funding: FWO research project (including WEAVE projects)
- High-dimensional and stochastic macromodeling of parameterized high-speed systemsFrom1 Oct 2013 → 30 Sep 2016Funding: BOF - Other initiatives, FWO fellowships
- Versatile surrogate-based optimization of medium-scale and large-scale problems.From1 Oct 2013 → 30 Sep 2019Funding: FWO fellowships, BOF - Other initiatives
- Accurate parameterized macromodels for efficient designFrom1 Jan 2013 → 31 Dec 2018Funding: FWO research project (including WEAVE projects)
Publications
21 - 30 of 430
- Bayesian active learning for radiation pattern sampling over cylindrical surfaces(2022)
Authors: Federico Garbuglia, Tim Claeys, Ivo Couckuyt, Dirk Deschrijver, Tom Dhaene
Pages: 1391 - 1398 - Quantifying uncertainty in real time with split BiRNN for radar human activity recognition(2022)
Authors: Lorin Werthen-Brabants, Geethika Bhavanasi, Ivo Couckuyt, Tom Dhaene, Dirk Deschrijver
Pages: 173 - 176 - Split BiRNN for real-time activity recognition using radar and deep learning(2022)
Authors: Lorin Werthen-Brabants, Geethika Bhavanasi, Ivo Couckuyt, Tom Dhaene, Dirk Deschrijver
- Adaptive sampling with automatic stopping for feasible region identification in engineering design(2022)
Authors: Jixiang Qing, Nicolas Knudde, Federico Garbuglia, Domenico Spina, Ivo Couckuyt, Tom Dhaene
Pages: 1955 - 1972 - Race against the machine : can deep learning recognize microstructures as well as the trained human eye?(2021)
Authors: Michiel Larmuseau, Michael Sluydts, Koenraad Theuwissen, Lode Duprez, Tom Dhaene, Stefaan Cottenier
Pages: 33 - 37 - Chapter 10 : Mixed epistemic-aleatory uncertainty using a new polynomial chaos formulation combined with machine learning(2021)
Authors: Domenico Spina, Tom Dhaene, Flavia Grassi, Sourajeet Roy
Pages: 243 - 262 - Learning multivariate shapelets with multi-layer neural networks for interpretable time-series classification(2021)
Authors: Roberto Medico, Joeri Ruyssinck, Dirk Deschrijver, Tom Dhaene
Pages: 911 - 936 - Multi-output Gaussian process prediction for computationally expensive problems with multiple levels of fidelity(2021)
Authors: Quan Lin, Jiexiang Hu, Qi Zhou, Yuansheng Cheng, Zhen Hu, Ivo Couckuyt, Tom Dhaene
- Machine learning-based characterization of SNR in digital satellite communication links(2021)
Authors: Brecht Dhuyvetters, Daniel Delaruelle, Hendrik Rogier, Tom Dhaene, Dries Vande Ginste, Domenico Spina
Number of pages: 1 - Bayesian active learning for multi-objective feasible region identification in microwave devices(2021)
Authors: Federico Garbuglia, Jixiang Qing, Nicolas Knudde, Domenico Spina, Ivo Couckuyt, Dirk Deschrijver, Tom Dhaene
Pages: 400 - 403