EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

E-Nose: Time–Frequency Attention Convolutional Neural Network for Gas Classification and Concentration Prediction

Minglv Jiang, Na Li, Mingyong Li, Zhou Wang, Yuan Tian, Kaiyan Peng, Haoran Sheng, Haoyu Li, Qiang Li iD

Sensors · 25.06.2024 · 24 (13) · 4126

DOI: 10.3390/s24134126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.06.2024. Verfasst von Minglv Jiang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Physical Electronics and Devices for Ministry of Education and Shaanxi Provincial Key Laboratory of Photonics & Information Technol…. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the electronic nose (E-nose) systems, gas type recognition and accurate concentration prediction are some of the most challenging issues. This study introduced an innovative pattern recognition method of time–frequency attention convolutional neural network (TFA-CNN). A time–frequency attention block was designed in the network, aiming to excavate and effectively integrate the temporal and frequency domain information in the E-nose signals to enhance the performance of gas classification and concentration prediction tasks. Additionally, a novel data augmentation strategy was developed, manipulating the feature channels and time dimensions to reduce the interference of sensor drift and redundant information, thereby enhancing the model’s robustness and adaptability. Utilizing two types of metal-oxide-semiconductor gas sensors, this research conducted qualitative and quantitative analysis on five target gases. The evaluation results showed that the classification accuracy could reach 100%, and the coefficient of the determination (R2) score of the regression task was up to 0.99. The Pearson correlation coefficient (r) was 0.99, and the mean absolute error (MAE) was 1.54 ppm. The experimental test results were almost consistent with the system predictions, and the MAE was 1.39 ppm. This study provides a method of network learning that combines time–frequency domain information, exhibiting high performance in gas classification and concentration prediction within the E-nose system.

Schlagwörter

Stichwörter der Autor:innen

convolutional neural networkelectronic nosegas sensortime–frequency attention

Autor:innen und Institutionen

  • Key Laboratory of Physical Electronics and Devices for Ministry of Education and Shaanxi Provincial Key Laboratory of Photonics & Information Technology, Xi'an Jiaotong University, Xi'an 710049, China.
  • School of Electronic Science and Engineering, Xi'an Jiaotong University, Xi'an 710049, China.
  • Northwest Survey & Planning Institute of National Forestry and Grassland Administration, Xi'an 710048, China.
  • Key Laboratory of National Forestry and Grassland Administration on Ecological Hydrology and Disaster Prevention in Arid Regions, Xi'an 710048, China.
  • CSSC AlphaPec Instrument (Hubei) Co., Ltd., Yichang 443005, China.
  • China National Engineering Laboratory for Coal Mining Machinery, CCTEG Taiyuan Research Institute Co., Ltd., Taiyuan 030032, China.

ORCID-Profile: Qiang Li

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Jiang, M., Li, N., Li, M., Wang, Z., Tian, Y., Peng, K., Sheng, H., Li, H., & Li, Q. (2024). E-Nose: Time–Frequency Attention Convolutional Neural Network for Gas Classification and Concentration Prediction. Sensors, 24(13), 4126. https://doi.org/10.3390/s24134126

Vancouver

Jiang M, Li N, Li M, Wang Z, Tian Y, Peng K, et al. E-Nose: Time–Frequency Attention Convolutional Neural Network for Gas Classification and Concentration Prediction. Sensors. 2024;24(13):4126. doi:10.3390/s24134126

BibTeX
@article{Jiang2024,
  author = {Jiang, Minglv and Li, Na and Li, Mingyong and Wang, Zhou and Tian, Yuan and Peng, Kaiyan and Sheng, Haoran and Li, Haoyu and Li, Qiang},
  title = {E-Nose: Time–Frequency Attention Convolutional Neural Network for Gas Classification and Concentration Prediction},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4126},
  doi = {10.3390/s24134126}
}
Kostenlos starten →