Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders
For many sensing applications, collecting a large experimental dataset could be a time-consuming and expensive task that can also hinder the implementation of Machine Learning models for analyzing sensor data. Therefore, this paper proposes the generation of synthetic signals through a Variational A...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/adb009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860605451239424 |
|---|---|
| author | Miguel Monteagudo Honrubia Francisco Javier Herraiz-Martínez Javier Matanza Domingo |
| author_facet | Miguel Monteagudo Honrubia Francisco Javier Herraiz-Martínez Javier Matanza Domingo |
| author_sort | Miguel Monteagudo Honrubia |
| collection | DOAJ |
| description | For many sensing applications, collecting a large experimental dataset could be a time-consuming and expensive task that can also hinder the implementation of Machine Learning models for analyzing sensor data. Therefore, this paper proposes the generation of synthetic signals through a Variational Autoencoder (VAE) to enlarge a spectra dataset acquired with a capacitive sensor based on a Dielectric Resonator. Trained with signals of several water/glycerine concentrations, this generative model learns the dataset characteristics and builds a representative latent space. Consequently, exploring this latent space is a critical task to control the generation of synthetic signals and interpolating concentrations unmeasured by the sensor. For this reason, this paper proposes a search method based on Bayesian Optimization that automatically explores the latent space. The results show excellent signal reconstruction quality, proving that the VAE architecture can successfully generate realistic synthetic signals from capacitive sensors. In addition, the proposed search method obtains a reasonable interpolation capability by finding latent encodings that generate signals related to the target glycerin concentrations. Moreover, this approach could be extended to other sensing technologies. |
| format | Article |
| id | doaj-art-cf212195fc804bb9a7365515fdfa574a |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-cf212195fc804bb9a7365515fdfa574a2025-02-10T11:09:19ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101503110.1088/2632-2153/adb009Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencodersMiguel Monteagudo Honrubia0https://orcid.org/0000-0001-9712-7486Francisco Javier Herraiz-Martínez1https://orcid.org/0000-0001-5774-659XJavier Matanza Domingo2https://orcid.org/0000-0002-0391-1331Universidad Pontifica Comillas , Madrid 28015, SpainUniversidad Pontifica Comillas , Madrid 28015, SpainUniversidad Pontifica Comillas , Madrid 28015, SpainFor many sensing applications, collecting a large experimental dataset could be a time-consuming and expensive task that can also hinder the implementation of Machine Learning models for analyzing sensor data. Therefore, this paper proposes the generation of synthetic signals through a Variational Autoencoder (VAE) to enlarge a spectra dataset acquired with a capacitive sensor based on a Dielectric Resonator. Trained with signals of several water/glycerine concentrations, this generative model learns the dataset characteristics and builds a representative latent space. Consequently, exploring this latent space is a critical task to control the generation of synthetic signals and interpolating concentrations unmeasured by the sensor. For this reason, this paper proposes a search method based on Bayesian Optimization that automatically explores the latent space. The results show excellent signal reconstruction quality, proving that the VAE architecture can successfully generate realistic synthetic signals from capacitive sensors. In addition, the proposed search method obtains a reasonable interpolation capability by finding latent encodings that generate signals related to the target glycerin concentrations. Moreover, this approach could be extended to other sensing technologies.https://doi.org/10.1088/2632-2153/adb009variational autoencoderslatent space searchdata augmentationsynthetic datagenerative modelscapacitive sensors |
| spellingShingle | Miguel Monteagudo Honrubia Francisco Javier Herraiz-Martínez Javier Matanza Domingo Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders Machine Learning: Science and Technology variational autoencoders latent space search data augmentation synthetic data generative models capacitive sensors |
| title | Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders |
| title_full | Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders |
| title_fullStr | Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders |
| title_full_unstemmed | Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders |
| title_short | Into the latent space of capacitive sensors: interpolation and synthetic data generation using variational autoencoders |
| title_sort | into the latent space of capacitive sensors interpolation and synthetic data generation using variational autoencoders |
| topic | variational autoencoders latent space search data augmentation synthetic data generative models capacitive sensors |
| url | https://doi.org/10.1088/2632-2153/adb009 |
| work_keys_str_mv | AT miguelmonteagudohonrubia intothelatentspaceofcapacitivesensorsinterpolationandsyntheticdatagenerationusingvariationalautoencoders AT franciscojavierherraizmartinez intothelatentspaceofcapacitivesensorsinterpolationandsyntheticdatagenerationusingvariationalautoencoders AT javiermatanzadomingo intothelatentspaceofcapacitivesensorsinterpolationandsyntheticdatagenerationusingvariationalautoencoders |