Lightweight Neural Network for Gas Identification Based on Semiconductor Sensor
- 14 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-8
Abstract
This article proposes a lightweight network called multiscale convolutional neural network with attention (MCNA), which combines a multiscale deep convolutional network with a self-attention mechanism. MCNA identifies ambient gases through signals of semiconductor gas sensor arrays, despite poor selectivity and drift problems. Notably, MCNA extracts temporal features of each signal and relevance among different signals more effectively than deep convolutional networks. MCNA requires much fewer parameters and computation costs than previous deep learning networks, but it still achieves the same high gas identification accuracy; this is crucial for gas sensing embedded systems. When the operating conditions of the gas sensor array change, it also exhibits better generalization ability and identification accuracy. We also discuss the effects of different MCNA architecture parameters and compare MCNA and other baseline approaches.Keywords
Funding Information
- National Natural Science Foundation of China (51877170)
- Fundamental Research Funds for the Central Universities and the K. C. Wong Education Foundation
This publication has 28 references indexed in Scilit:
- Gas Classification Using Deep Convolutional Neural NetworksSensors, 2018
- Pt-decorated zinc oxide nanorod arrays with graphitic carbon nitride nanosheets for highly efficient dual-functional gas sensingJournal of Hazardous Materials, 2018
- The Morphologies of the Semiconductor Oxides and Their Gas-Sensing PropertiesSensors, 2017
- Classification of Data from Electronic Nose Using Gradient Tree Boosting AlgorithmSensors, 2017
- Deep Residual Learning for Image Recognition2016
- Wavelet-Based Multiscale Sample Entropy and Chaotic Features for Congestive Heart Failure Recognition Using Heart Rate VariabilityJournal of Medical and Biological Engineering, 2015
- On the performance of gas sensor arrays in open sampling systems using Inhibitory Support Vector MachinesSensors and Actuators B: Chemical, 2013
- Signal and Data Processing for Machine Olfaction and Chemical Sensing: A ReviewIEEE Sensors Journal, 2012
- Classification of data from electronic nose using relevance vector machinesSensors and Actuators B: Chemical, 2009
- A Bio-Inspired Pattern Recognition System for Tin-Oxide Gas Sensor ApplicationsIEEE Sensors Journal, 2009