CNN based Gas Mixture Classification

A CNN-based multi-channel time-series analysis method is proposed for accurate classification of gas mixtures using electronic nose sensor data.

2020.03 - 2020.07
Ulsan Industry-University Convergence CampusTime‑Series Representation Learning
E-sensingElectronic NoseGas SensingCNN

Motivation

An electronic nose is a device intended to detect odors or flavors. “Electronic sensing” or “e-sensing” technologies have undergone important developments from a technical and commercial point of view.

Goal

  • To develop an anlysis method for classifying the mixture gas.
  • CNN(Convolution Neural Network) based time-series analysis method is proposed.

Methodology