HyperMoVal: Interactive Visual Validation of Regression Models for Real‐Time Simulation

TLDR

In car‑engine development, machine‑learning regression models are increasingly used for real‑time predictions, yet current validation methods fail to cover all necessary aspects. HyperMoVal is an interactive tool that enables users to compare predictions with known data, identify poorly fitting regions, assess physical plausibility beyond the validation set, and compare multiple models. The system visualizes n‑dimensional scalar functions by projecting them into multiple 2‑D and 3‑D sub‑views around a focal point, linking these views to other perspectives to support the full model‑identification workflow. Evaluation in car‑engine design demonstrates that HyperMoVal speeds up regression‑model identification and boosts engineers’ confidence, as confirmed by expert feedback.

Abstract

Abstract During the development of car engines, regression models that are based on machine learning techniques are increasingly important for tasks which require a prediction of results in real‐time. While the validation of a model is a key part of its identification process, existing computation‐ or visualization‐based techniques do not adequately support all aspects of model validation. The main contribution of this paper is an interactive approach called HyperMoVal that is designed to support multiple tasks related to model validation: 1) comparing known and predicted results, 2) analyzing regions with a bad fit, 3) assessing the physical plausibility of models also outside regions covered by validation data, and 4) comparing multiple models. The key idea is to visually relate one or more n‐dimensional scalar functions to known validation data within a combined visualization. HyperMoVal lays out multiple 2D and 3D sub‐projections of the n‐dimensional function space around a focal point. We describe how linking HyperMoVal to other views further extends the possibilities for model validation. Based on this integration, we discuss steps towards supporting the entire workflow of identifying regression models. An evaluation illustrates a typical workflow in the application context of car‐engine design and reports general feedback of domain experts and users of our approach. These results indicate that our approach significantly accelerates the identification of regression models and increases the confidence in the overall engineering process.