Generating Multivariate Synthetic Time Series Data for Absent Sensors from Correlated Sources. Bañuelos, J. J., Sigg, S., He, J., Salim, F., & Costa-Requena, J. In Proceedings of the 2nd International Workshop on Networked AI Systems, of NetAISys '24, pages 19–24, New York, NY, USA, 2024. Association for Computing Machinery. ![Generating Multivariate Synthetic Time Series Data for Absent Sensors from Correlated Sources [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Missing sensor data in human activity recognition is an active field of research that is being targeted with generative models for synthetic data generation. In contrast to most previous approaches, we aim to generate data of a sensor exclusively from data available at sensors in different body locations. Particularly, we evaluate existing approaches proposed in the literature for their suitability in this scenario. In this paper, we focus on the prediction of acceleration data and generate machine learning models based on generative adversarial networks and trained using correlated data from sensors in different body positions to generate synthetic sensor data that can replace the missing data from a sensor in a specific body position. The accuracy of the generated synthetic data is evaluated using a classification model based on a convolutional neural network for human activity recognition.
@inproceedings{10.1145/3662004.3663553,
author = {Ba\~{n}uelos, Juli\'{a}n Jer\'{o}nimo and Sigg, Stephan and He, Jiayuan and Salim, Flora and Costa-Requena, Jose},
title = {Generating Multivariate Synthetic Time Series Data for Absent Sensors from Correlated Sources},
year = {2024},
isbn = {9798400706615},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3662004.3663553},
doi = {10.1145/3662004.3663553},
abstract = {Missing sensor data in human activity recognition is an active field of research that is being targeted with generative models for synthetic data generation. In contrast to most previous approaches, we aim to generate data of a sensor exclusively from data available at sensors in different body locations. Particularly, we evaluate existing approaches proposed in the literature for their suitability in this scenario. In this paper, we focus on the prediction of acceleration data and generate machine learning models based on generative adversarial networks and trained using correlated data from sensors in different body positions to generate synthetic sensor data that can replace the missing data from a sensor in a specific body position. The accuracy of the generated synthetic data is evaluated using a classification model based on a convolutional neural network for human activity recognition.},
booktitle = {Proceedings of the 2nd International Workshop on Networked AI Systems},
pages = {19–24},
numpages = {6},
keywords = {accelerometer, cnn, gan, human activity recognition, iot, multivariate time series data, sensor data, synthetic data generation},
location = {Minato-ku, Tokyo, Japan},
series = {NetAISys '24}
}
Downloads: 0
{"_id":"8jzbpKSwJaTvqWSya","bibbaseid":"bauelos-sigg-he-salim-costarequena-generatingmultivariatesynthetictimeseriesdataforabsentsensorsfromcorrelatedsources-2024","author_short":["Bañuelos, J. J.","Sigg, S.","He, J.","Salim, F.","Costa-Requena, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Bañuelos"],"firstnames":["Julián","Jerónimo"],"suffixes":[]},{"propositions":[],"lastnames":["Sigg"],"firstnames":["Stephan"],"suffixes":[]},{"propositions":[],"lastnames":["He"],"firstnames":["Jiayuan"],"suffixes":[]},{"propositions":[],"lastnames":["Salim"],"firstnames":["Flora"],"suffixes":[]},{"propositions":[],"lastnames":["Costa-Requena"],"firstnames":["Jose"],"suffixes":[]}],"title":"Generating Multivariate Synthetic Time Series Data for Absent Sensors from Correlated Sources","year":"2024","isbn":"9798400706615","publisher":"Association for Computing Machinery","address":"New York, NY, USA","url":"https://doi.org/10.1145/3662004.3663553","doi":"10.1145/3662004.3663553","abstract":"Missing sensor data in human activity recognition is an active field of research that is being targeted with generative models for synthetic data generation. In contrast to most previous approaches, we aim to generate data of a sensor exclusively from data available at sensors in different body locations. Particularly, we evaluate existing approaches proposed in the literature for their suitability in this scenario. In this paper, we focus on the prediction of acceleration data and generate machine learning models based on generative adversarial networks and trained using correlated data from sensors in different body positions to generate synthetic sensor data that can replace the missing data from a sensor in a specific body position. The accuracy of the generated synthetic data is evaluated using a classification model based on a convolutional neural network for human activity recognition.","booktitle":"Proceedings of the 2nd International Workshop on Networked AI Systems","pages":"19–24","numpages":"6","keywords":"accelerometer, cnn, gan, human activity recognition, iot, multivariate time series data, sensor data, synthetic data generation","location":"Minato-ku, Tokyo, Japan","series":"NetAISys '24","bibtex":"@inproceedings{10.1145/3662004.3663553,\n author = {Ba\\~{n}uelos, Juli\\'{a}n Jer\\'{o}nimo and Sigg, Stephan and He, Jiayuan and Salim, Flora and Costa-Requena, Jose},\n title = {Generating Multivariate Synthetic Time Series Data for Absent Sensors from Correlated Sources},\n year = {2024},\n isbn = {9798400706615},\n publisher = {Association for Computing Machinery},\n address = {New York, NY, USA},\n url = {https://doi.org/10.1145/3662004.3663553},\n doi = {10.1145/3662004.3663553},\n abstract = {Missing sensor data in human activity recognition is an active field of research that is being targeted with generative models for synthetic data generation. In contrast to most previous approaches, we aim to generate data of a sensor exclusively from data available at sensors in different body locations. Particularly, we evaluate existing approaches proposed in the literature for their suitability in this scenario. In this paper, we focus on the prediction of acceleration data and generate machine learning models based on generative adversarial networks and trained using correlated data from sensors in different body positions to generate synthetic sensor data that can replace the missing data from a sensor in a specific body position. The accuracy of the generated synthetic data is evaluated using a classification model based on a convolutional neural network for human activity recognition.},\n booktitle = {Proceedings of the 2nd International Workshop on Networked AI Systems},\n pages = {19–24},\n numpages = {6},\n keywords = {accelerometer, cnn, gan, human activity recognition, iot, multivariate time series data, sensor data, synthetic data generation},\n location = {Minato-ku, Tokyo, Japan},\n series = {NetAISys '24}\n }\n\n","author_short":["Bañuelos, J. J.","Sigg, S.","He, J.","Salim, F.","Costa-Requena, J."],"key":"10.1145/3662004.3663553-1","id":"10.1145/3662004.3663553-1","bibbaseid":"bauelos-sigg-he-salim-costarequena-generatingmultivariatesynthetictimeseriesdataforabsentsensorsfromcorrelatedsources-2024","role":"author","urls":{"Paper":"https://doi.org/10.1145/3662004.3663553"},"keyword":["accelerometer","cnn","gan","human activity recognition","iot","multivariate time series data","sensor data","synthetic data generation"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"http://ambientintelligence.aalto.fi/bibtex/LiteraturAll","dataSources":["aPfcTvMp5jE2KuS7H","a6QYyvmdLfrsx7DiL"],"keywords":["accelerometer","cnn","gan","human activity recognition","iot","multivariate time series data","sensor data","synthetic data generation"],"search_terms":["generating","multivariate","synthetic","time","series","data","absent","sensors","correlated","sources","bañuelos","sigg","he","salim","costa-requena"],"title":"Generating Multivariate Synthetic Time Series Data for Absent Sensors from Correlated Sources","year":2024}