EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks

Huichao Zhu, Yu Wu, Ge Yang, Ruijie Song, Jun Yu, Jianwei Zhang iD

Sensors · 18.02.2024 · 24 (4) · 1319

DOI: 10.3390/s24041319 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.02.2024. Verfasst von Huichao Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Control Science and Engineering, Dalian University of Technology, Dalian 116000, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anti-drift is a new and serious challenge in the field related to gas sensors. Gas sensor drift causes the probability distribution of the measured data to be inconsistent with the probability distribution of the calibrated data, which leads to the failure of the original classification algorithm. In order to make the probability distributions of the drifted data and the regular data consistent, we introduce the Conditional Adversarial Domain Adaptation Network (CDAN)+ Sharpness Aware Minimization (SAM) optimizer—a state-of-the-art deep transfer learning method.The core approach involves the construction of feature extractors and domain discriminators designed to extract shared features from both drift and clean data. These extracted features are subsequently input into a classifier, thereby amplifying the overall model’s generalization capabilities. The method boasts three key advantages: (1) Implementation of semi-supervised learning, thereby negating the necessity for labels on drift data. (2) Unlike conventional deep transfer learning methods such as the Domain-adversarial Neural Network (DANN) and Wasserstein Domain-adversarial Neural Network (WDANN), it accommodates inter-class correlations. (3) It exhibits enhanced ease of training and convergence compared to traditional deep transfer learning networks. Through rigorous experimentation on two publicly available datasets, we substantiate the efficiency and effectiveness of our proposed anti-drift methodology when juxtaposed with state-of-the-art techniques.

Schlagwörter

Stichwörter der Autor:innen

anti-driftdeep learningelectronic nosetransfer learning

Autor:innen und Institutionen

  • School of Control Science and Engineering, Dalian University of Technology, Dalian 116000, China.

ORCID-Profile: Jianwei Zhang

Zitieren

APA

Zhu, H., Wu, Y., Yang, G., Song, R., Yu, J., & Zhang, J. (2024). Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks. Sensors, 24(4), 1319. https://doi.org/10.3390/s24041319

Vancouver

Zhu H, Wu Y, Yang G, Song R, Yu J, Zhang J. Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks. Sensors. 2024;24(4):1319. doi:10.3390/s24041319

BibTeX
@article{Zhu2024,
  author = {Zhu, Huichao and Wu, Yu and Yang, Ge and Song, Ruijie and Yu, Jun and Zhang, Jianwei},
  title = {Electronic Nose Drift Suppression Based on Smooth Conditional Domain Adversarial Networks},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {4},
  pages = {1319},
  doi = {10.3390/s24041319}
}
Kostenlos starten →