Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Coordinated Action of TjSPL7 and TjNF-YB3 Breaks Seed Dormancy by Rebalancing ABA-JA Levels and Modulating Downstream Signalling in Tilia japonica.

Plant, cell & environment·2026
Same author

Systematic investigation of a Fraxinus mandshurica seed-derived iridoid glucoside fraction as a novel functional ingredient with anti-diabetic potential.

Fitoterapia·2026
Same author

Quercetin as a multifaceted neuroprotective agent against cerebral ischaemia-reperfusion injury: mechanisms and therapeutic potential.

Frontiers in pharmacology·2026
Same author

Wheat MYB46-like Transcription Factor Stimulates Cuticular Wax Biosynthesis.

Biomolecules·2026
Same author

Infrared and Visible Image Fusion Network Based on Self-Compensating Lightweight Convolution.

Sensors (Basel, Switzerland)·2026
Same author

Intercellular chemerin-cmklr1 couples epicardial mechanosensing to fibroblasts in pressure overload.

Nature communications·2026

Related Experiment Video

Updated: Jun 21, 2025

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry
08:23

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry

Published on: March 9, 2018

8.9K

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

Minglv Jiang1,2, Na Li3,4, Mingyong Li5

  • 1Key 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.

Sensors (Basel, Switzerland)
|July 13, 2024
PubMed
Summary

This study presents a novel time-frequency attention convolutional neural network (TFA-CNN) for electronic nose systems. The TFA-CNN achieves high accuracy in gas classification and concentration prediction, improving E-nose performance.

Keywords:
convolutional neural networkelectronic nosegas sensortime–frequency attention

More Related Videos

Fruit Volatile Analysis Using an Electronic Nose
11:02

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

21.4K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

Related Experiment Videos

Last Updated: Jun 21, 2025

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry
08:23

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry

Published on: March 9, 2018

8.9K
Fruit Volatile Analysis Using an Electronic Nose
11:02

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

21.4K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

Area of Science:

  • Sensor Technology
  • Artificial Intelligence
  • Chemical Sensing

Background:

  • Electronic nose (E-nose) systems face challenges in gas type recognition and concentration prediction.
  • Accurate analysis of E-nose signals is crucial for reliable gas sensing applications.

Purpose of the Study:

  • To introduce an innovative pattern recognition method, the time-frequency attention convolutional neural network (TFA-CNN), for E-nose systems.
  • To enhance gas classification and concentration prediction performance by integrating temporal and frequency domain information.

Main Methods:

  • Developed a TFA-CNN incorporating a time-frequency attention block to process E-nose signals.
  • Implemented a novel data augmentation strategy to improve model robustness against sensor drift and noise.
  • Utilized metal-oxide-semiconductor gas sensors for qualitative and quantitative analysis of five target gases.

Main Results:

  • Achieved 100% classification accuracy for gas types.
  • Obtained a coefficient of determination (R²) of 0.99 for concentration prediction.
  • Reported a Pearson correlation coefficient (r) of 0.99 and a mean absolute error (MAE) of 1.54 ppm, with experimental MAE at 1.39 ppm.

Conclusions:

  • The TFA-CNN effectively combines time-frequency domain information for superior E-nose performance.
  • The proposed method demonstrates high accuracy and robustness in gas classification and concentration prediction.
  • This study offers a promising approach for advancing E-nose system capabilities.