A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition
Abstract The domain of human activity recognition is able to differentiate between human movements based on sensory driven systems, e.g. in the form of an IMU. Though, in order to perform those differentiation tasks, a measurement setup has to be established and subjects have to be recorded. As this...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-01614-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850133457539170304 |
|---|---|
| author | Heiko Oppel Michael Munz |
| author_facet | Heiko Oppel Michael Munz |
| author_sort | Heiko Oppel |
| collection | DOAJ |
| description | Abstract The domain of human activity recognition is able to differentiate between human movements based on sensory driven systems, e.g. in the form of an IMU. Though, in order to perform those differentiation tasks, a measurement setup has to be established and subjects have to be recorded. As this is a time and cost consuming process, research groups are focused to synthetically generate data resembling human movements to improve the underlying recognition task. So far, work groups are able to generate univariate and multivariate synthetic sequences on basis of an accelerometer or six axis IMU. Yet, they lack in generalizing on unseen subjects and are not able to expand further than a single six axis IMU. In this paper, we aim to fill this gap by using the backbone of a denoising diffusion probabilistic model from the vision domain to synthetically generate multiple IMUs which are able to generalize on unseen participants. The model was adapted to fulfill the criteria of generating meaningful human motion sequences. We then evaluated the quality of the data in two ways: (1) by a subjective visual analysis with the help of a clustering approach new to this domain and (2) by the classifier improvement when adding synthetic samples. The results show a significant improvement in the classification task when synthetic samples were added to the pool of training data. One of the key findings is the benefit of improvement, even in a scarce data set of only 2 samples per subject. This is a huge advantage in the domain of HAR as it reduces the time of a subject to perform a task. |
| format | Article |
| id | doaj-art-c3a0c700022a45c8b91f1423976a359d |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c3a0c700022a45c8b91f1423976a359d2025-08-20T02:31:58ZengNature PortfolioScientific Reports2045-23222025-05-0115111510.1038/s41598-025-01614-xA diffusion model for inertial based time series generation on scarce data availability to improve human activity recognitionHeiko Oppel0Michael Munz1AI for Sensor Data Analytics Research Group, Ulm University of Applied SciencesAI for Sensor Data Analytics Research Group, Ulm University of Applied SciencesAbstract The domain of human activity recognition is able to differentiate between human movements based on sensory driven systems, e.g. in the form of an IMU. Though, in order to perform those differentiation tasks, a measurement setup has to be established and subjects have to be recorded. As this is a time and cost consuming process, research groups are focused to synthetically generate data resembling human movements to improve the underlying recognition task. So far, work groups are able to generate univariate and multivariate synthetic sequences on basis of an accelerometer or six axis IMU. Yet, they lack in generalizing on unseen subjects and are not able to expand further than a single six axis IMU. In this paper, we aim to fill this gap by using the backbone of a denoising diffusion probabilistic model from the vision domain to synthetically generate multiple IMUs which are able to generalize on unseen participants. The model was adapted to fulfill the criteria of generating meaningful human motion sequences. We then evaluated the quality of the data in two ways: (1) by a subjective visual analysis with the help of a clustering approach new to this domain and (2) by the classifier improvement when adding synthetic samples. The results show a significant improvement in the classification task when synthetic samples were added to the pool of training data. One of the key findings is the benefit of improvement, even in a scarce data set of only 2 samples per subject. This is a huge advantage in the domain of HAR as it reduces the time of a subject to perform a task.https://doi.org/10.1038/s41598-025-01614-xDiffusion ModelTime seriesSynthetisationHuman activity recognition |
| spellingShingle | Heiko Oppel Michael Munz A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition Scientific Reports Diffusion Model Time series Synthetisation Human activity recognition |
| title | A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition |
| title_full | A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition |
| title_fullStr | A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition |
| title_full_unstemmed | A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition |
| title_short | A diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition |
| title_sort | diffusion model for inertial based time series generation on scarce data availability to improve human activity recognition |
| topic | Diffusion Model Time series Synthetisation Human activity recognition |
| url | https://doi.org/10.1038/s41598-025-01614-x |
| work_keys_str_mv | AT heikooppel adiffusionmodelforinertialbasedtimeseriesgenerationonscarcedataavailabilitytoimprovehumanactivityrecognition AT michaelmunz adiffusionmodelforinertialbasedtimeseriesgenerationonscarcedataavailabilitytoimprovehumanactivityrecognition AT heikooppel diffusionmodelforinertialbasedtimeseriesgenerationonscarcedataavailabilitytoimprovehumanactivityrecognition AT michaelmunz diffusionmodelforinertialbasedtimeseriesgenerationonscarcedataavailabilitytoimprovehumanactivityrecognition |