Virtual sensing aims to infer hard-to-measure quantities from accessible measurements and is central to perception and control in physical systems. Despite rapid progress from first-principle and hybrid models to modern data-driven methods research remains siloed, leaving no established default approach that transfers across processes, modalities, and sensing configurations. We introduce MuViS, a domain-agnostic benchmarking suite for multimodal virtual sensing that consolidates diverse datasets into a unified interface for standardized preprocessing and evaluation. Using this framework, we benchmark established approaches spanning gradient-boosted decision trees and deep neural network (NN) architectures, and show that none of these provides a universal advantage, underscoring the need for generalizable virtual sensing architectures. MuViS is released as an open-source, extensible platform for reproducible comparison and future integration of new datasets and model classes.
@article{arxiv.2603.24602,
title = {MuViS: Multimodal Virtual Sensing Benchmark},
author = {Jens U. Brandt and Noah C. Puetz and Jobel Jose George and Niharika Vinay Kumar and Elena Raponi and Marc Hilbert and Thomas Bäck and Thomas Bartz-Beielstein},
journal= {arXiv preprint arXiv:2603.24602},
year = {2026}
}
Comments
Accepted at European Signal Processing Conference (EUSIPCO) 2026