We present PREVIS, a visual analytics tool, enhancing machine learning performance analysis in engineering applications. The presented toolchain allows for a direct comparison of regression models. In addition, we provide a methodology to visualize the impact of regression errors on the underlying field of interest in the original domain, the part geometry, via exploiting standard interpolation methods. Further, we allow a real-time preview of user-driven parameter changes in the displacement field via visual interpolation. This allows for fast and accountable online change management. We demonstrate the effectiveness with an ex-ante optimization of an automotive engine hood.
@article{arxiv.2201.10257,
title = {PREVIS -- A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control},
author = {Patrick Ruediger and Felix Claus and Viktor Leonhardt and Hans Hagen and Jan C. Aurich and Christoph Garth},
journal= {arXiv preprint arXiv:2201.10257},
year = {2022}
}