[HTML][HTML] Outcome prediction based on automatically extracted infarct core image features in patients with acute ischemic stroke

ML Tolhuisen, JW Hoving, MS Koopman, M Kappelhof… - Diagnostics, 2022 - mdpi.com
Infarct volume (FIV) on follow-up diffusion-weighted imaging (FU-DWI) is only moderately
associated with functional outcome in acute ischemic stroke patients. However, FU-DWI may …

Multitask shape optimization using a 3-d point cloud autoencoder as unified representation

T Rios, B van Stein, T Bäck, B Sendhoff… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The choice of design representations, as of search operators, is central to the performance
of evolutionary optimization algorithms, in particular, for multitask problems. The multitask …

[HTML][HTML] Learning hyperparameter predictors for similarity-based multidisciplinary topology optimization

M Bujny, MS Yousaf, N Zurbrugg, D Detwiler… - Scientific Reports, 2023 - nature.com
Topology optimization (TO) plays a significant role in industry by providing engineers with
optimal material distributions based exclusively on the information about the design space …

Exploiting generative models for performance predictions of 3D car designs

S Saha, T Rios, LL Minku, BV Stein… - 2021 IEEE …, 2021 - ieeexplore.ieee.org
In automotive digital development, engineers utilize multiple virtual prototyping tools to
design and assess the performance of 3D shapes. However, accurate performance …

DeepMorpher: deep learning-based design space dimensionality reduction for shape optimisation

A Abbas, A Rafiee, M Haase - Journal of Engineering Design, 2023 - Taylor & Francis
In engineering design optimisations, the dimensionality of the design space plays a critical
role in determining the number of computationally expensive evaluations required to explore …

Quantifying the generative capabilities of variational autoencoders for 3D car point clouds

S Saha, S Menzel, LL Minku, X Yao… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
During each cycle of automotive development, large amounts of geometric data are
generated as results of design studies and simulation tasks. Discovering hidden knowledge …

Point2ffd: Learning shape representations of simulation-ready 3d models for engineering design optimization

T Rios, B Van Stein, T Bäck… - … Conference on 3D …, 2021 - ieeexplore.ieee.org
Methods for learning on 3D point clouds became ubiquitous due to the popularization of 3D
scanning technology and advances of machine learning techniques. Among these methods …

Exploiting local geometric features in vehicle design optimization with 3D point cloud autoencoders

T Rios, B van Stein, P Wollstadt, T Bäck… - 2021 IEEE Congress …, 2021 - ieeexplore.ieee.org
Methods for learning and compressing high-dimensional data allow designers to generate
novel and low-dimensional design representations for shape optimization problems. By …

A 3d object recognition method from lidar point cloud based on usae-bls

Y Tian, W Song, L Chen, S Fong… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Environmental perception provides the necessary information for unmanned ground
vehicles to recognize and interact with surrounding objects. Velodyne light detection and …

[HTML][HTML] Evaluation of geometric similarity metrics for structural clusters generated using topology optimization

N Dommaraju, M Bujny, S Menzel, M Olhofer… - Applied …, 2023 - Springer
In the early stages of engineering design, multitudes of feasible designs can be generated
using structural optimization methods by varying the design requirements or user …