Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo
Data-driven solutions are increasingly transforming the industrial sector, yet collecting large-scale, multimodal datasets remains costly and challenging. This paper presents three synthetic multimodal datasets that replicate real-world industrial conditions across varying levels of complexity, desi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266682702500074X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849433760392544256 |
|---|---|
| author | Diyar Altinses Andreas Schwung |
| author_facet | Diyar Altinses Andreas Schwung |
| author_sort | Diyar Altinses |
| collection | DOAJ |
| description | Data-driven solutions are increasingly transforming the industrial sector, yet collecting large-scale, multimodal datasets remains costly and challenging. This paper presents three synthetic multimodal datasets that replicate real-world industrial conditions across varying levels of complexity, designed to benchmark multimodal machine learning models. We validate their utility through a series of experiments. Cross-modal prediction and domain adaptation demonstrate that the datasets effectively capture strong multimodal correlations. Multimodal reconstruction experiments confirm the internal consistency and richness of the fused representations, indicating that the modalities complement each other in capturing underlying structure. Additionally, multimodal regression significantly outperforms unimodal baselines, underscoring the predictive strength gained through multimodal integration. Together, these results demonstrate the utility of our datasets, establishing a solid baseline for future research and encouraging further advancements in industrial data-driven solutions. |
| format | Article |
| id | doaj-art-315525e07d20408e8a3de1c125f22659 |
| institution | Kabale University |
| issn | 2666-8270 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj-art-315525e07d20408e8a3de1c125f226592025-08-20T03:26:56ZengElsevierMachine Learning with Applications2666-82702025-09-012110069110.1016/j.mlwa.2025.100691Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedoDiyar Altinses0Andreas Schwung1Corresponding author.; Department of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, Soest, 59494, NRW, GermanyDepartment of Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, Soest, 59494, NRW, GermanyData-driven solutions are increasingly transforming the industrial sector, yet collecting large-scale, multimodal datasets remains costly and challenging. This paper presents three synthetic multimodal datasets that replicate real-world industrial conditions across varying levels of complexity, designed to benchmark multimodal machine learning models. We validate their utility through a series of experiments. Cross-modal prediction and domain adaptation demonstrate that the datasets effectively capture strong multimodal correlations. Multimodal reconstruction experiments confirm the internal consistency and richness of the fused representations, indicating that the modalities complement each other in capturing underlying structure. Additionally, multimodal regression significantly outperforms unimodal baselines, underscoring the predictive strength gained through multimodal integration. Together, these results demonstrate the utility of our datasets, establishing a solid baseline for future research and encouraging further advancements in industrial data-driven solutions.http://www.sciencedirect.com/science/article/pii/S266682702500074XBenchmarkingIndustrial applicationsMachine learningMultimodal datasets |
| spellingShingle | Diyar Altinses Andreas Schwung Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo Machine Learning with Applications Benchmarking Industrial applications Machine learning Multimodal datasets |
| title | Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo |
| title_full | Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo |
| title_fullStr | Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo |
| title_full_unstemmed | Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo |
| title_short | Performance benchmarking of multimodal data-driven approaches in industrial settingsZenedoZenedoZenedo |
| title_sort | performance benchmarking of multimodal data driven approaches in industrial settingszenedozenedozenedo |
| topic | Benchmarking Industrial applications Machine learning Multimodal datasets |
| url | http://www.sciencedirect.com/science/article/pii/S266682702500074X |
| work_keys_str_mv | AT diyaraltinses performancebenchmarkingofmultimodaldatadrivenapproachesinindustrialsettingszenedozenedozenedo AT andreasschwung performancebenchmarkingofmultimodaldatadrivenapproachesinindustrialsettingszenedozenedozenedo |