EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Evolving Multivariate Time Series Compression Algorithm for IoT Applications

Hagi Costa iD, Marianne Silva iD, Ignacio Sánchez-Gendriz iD, Carlos M D Viegas iD, Ivanovitch Silva iD

Sensors · 14.11.2024 · 24 (22) · 7273

DOI: 10.3390/s24227273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.11.2024. Verfasst von Hagi Costa und 4 weiteren Autor:innen. Beteiligte Einrichtung: UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), National Council for Scientific and Technological Development (CNPq).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Internet of Things (IoT) is transforming how devices interact and share data, especially in areas like vehicle monitoring. However, transmitting large volumes of real-time data can result in high latency and substantial energy consumption. In this context, Tiny Machine Learning (TinyML) emerges as a promising solution, enabling the execution of machine-learning models on resource-constrained embedded devices. This paper aims to develop two online multivariate compression approaches specifically designed for TinyML, utilizing the Typicality and Eccentricity Data Analytics (TEDA) framework. The proposed approaches are based on data eccentricity and do not require predefined mathematical models or assumptions about data distribution, thereby optimizing compression performance. The methodology involves applying the approaches to a case study using the OBD-II Freematics ONE+ dataset, which is focused on vehicle monitoring. Results indicate that both proposed approaches, whether parallel or sequential compression, show significant improvements in execution time and compression errors. These findings highlight the approach’s potential to enhance the performance of embedded IoT systems, thereby improving the efficiency and sustainability of vehicular applications.

Schlagwörter

Stichwörter der Autor:innen

IoTOBD-II edgeTinyMLdata compressionevolving algorithm

Autor:innen und Institutionen

  • UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil.
  • Campus Arapiraca, Federal University of Alagoas, Penedo 57200-000, Brazil.
  • UFRN, Department of Computing Engineering and Automation, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil.

ORCID-Profile: Hagi Costa, Marianne Silva, Ignacio Sánchez-Gendriz, Carlos M D Viegas, Ivanovitch Silva

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
  • National Council for Scientific and Technological Development (CNPq)

Zitieren

APA

Costa, H., Silva, M., Sánchez-Gendriz, I., Viegas, C. M. D., & Silva, I. (2024). An Evolving Multivariate Time Series Compression Algorithm for IoT Applications. Sensors, 24(22), 7273. https://doi.org/10.3390/s24227273

Vancouver

Costa H, Silva M, Sánchez-Gendriz I, Viegas CMD, Silva I. An Evolving Multivariate Time Series Compression Algorithm for IoT Applications. Sensors. 2024;24(22):7273. doi:10.3390/s24227273

BibTeX
@article{Costa2024,
  author = {Costa, Hagi and Silva, Marianne and Sánchez-Gendriz, Ignacio and Viegas, Carlos M D and Silva, Ivanovitch},
  title = {An Evolving Multivariate Time Series Compression Algorithm for IoT Applications},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {22},
  pages = {7273},
  doi = {10.3390/s24227273}
}
Kostenlos starten →