Saved in:
Bibliographic Details
Main Authors: Brandt, Jens U., Puetz, Noah C., George, Jobel Jose, Kumar, Niharika Vinay, Raponi, Elena, Hilbert, Marc, Bäck, Thomas, Bartz-Beielstein, Thomas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.24602
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914556345843712
author Brandt, Jens U.
Puetz, Noah C.
George, Jobel Jose
Kumar, Niharika Vinay
Raponi, Elena
Hilbert, Marc
Bäck, Thomas
Bartz-Beielstein, Thomas
author_facet Brandt, Jens U.
Puetz, Noah C.
George, Jobel Jose
Kumar, Niharika Vinay
Raponi, Elena
Hilbert, Marc
Bäck, Thomas
Bartz-Beielstein, Thomas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24602
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MuViS: Multimodal Virtual Sensing Benchmark
Brandt, Jens U.
Puetz, Noah C.
George, Jobel Jose
Kumar, Niharika Vinay
Raponi, Elena
Hilbert, Marc
Bäck, Thomas
Bartz-Beielstein, Thomas
Signal Processing
Artificial Intelligence
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.
title MuViS: Multimodal Virtual Sensing Benchmark
topic Signal Processing
Artificial Intelligence
url https://arxiv.org/abs/2603.24602