Litcius/Paper detail

Lightweight Neural Network for Gas Identification Based on Semiconductor Sensor

Jianbin Pan, Aijun Yang, Dawei Wang, Jifeng Chu, Fangfei Lei, Xiaohua Wang, Mingzhe Rong

2021IEEE Transactions on Instrumentation and Measurement35 citationsDOI

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.

Topics & Concepts

Convolutional neural networkComputer scienceDeep learningIdentification (biology)GeneralizationArtificial intelligenceComputationArtificial neural networkSIGNAL (programming language)Machine learningPattern recognition (psychology)AlgorithmMathematicsProgramming languageMathematical analysisBotanyBiologyAdvanced Chemical Sensor TechnologiesGas Sensing Nanomaterials and SensorsAir Quality Monitoring and Forecasting
Lightweight Neural Network for Gas Identification Based on Semiconductor Sensor | Litcius