Neural network sensitivity analysis of the detected signal from an SO2 electrode

Mei-Jywan Syu, Jwo Ying Liu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A novel SO2 electrode was made by doping polyaniline onto Nafion to detect SO2 at ppm level with a linear correlation between the response current and the SO2 concentration in the range of 20 to 250 ppm. By applying artificial neural network, it was possible to predict the SO2 concentration so that a shorter response time (3 min compared with 6 min) was achieved without the need of a noise filter. The operation conditions, cycles for acid/base treatment and immersion time, considered as the affecting factors of the polyaniline membrane treatment were used for the study of sensitivity analysis. Both the results analyzed from the transfer functions of 2/(1 + e-x) and sgn(x)·x2/(1 + x2) are presented. Prediction of the neural network for sensitivity analysis of the SO2 electrode signal was tested first. Then, the two operation variables considered as important factors affecting the properties of the membrane were studied in view of their influence toward the response current.

Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalSensors and Actuators, B: Chemical
Volume50
Issue number1
DOIs
Publication statusPublished - 1998 Jul 15

Fingerprint

sensitivity analysis
Polyaniline
Sensitivity analysis
Neural networks
Membranes
Electrodes
electrodes
membranes
Transfer functions
Doping (additives)
transfer functions
submerging
Acids
filters
cycles
acids
predictions
polyaniline
perfluorosulfonic acid

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Instrumentation
  • Condensed Matter Physics
  • Surfaces, Coatings and Films
  • Metals and Alloys
  • Electrical and Electronic Engineering
  • Materials Chemistry

Cite this

@article{a1bc03319bb140b7a3b21d2dad4bf54d,
title = "Neural network sensitivity analysis of the detected signal from an SO2 electrode",
abstract = "A novel SO2 electrode was made by doping polyaniline onto Nafion to detect SO2 at ppm level with a linear correlation between the response current and the SO2 concentration in the range of 20 to 250 ppm. By applying artificial neural network, it was possible to predict the SO2 concentration so that a shorter response time (3 min compared with 6 min) was achieved without the need of a noise filter. The operation conditions, cycles for acid/base treatment and immersion time, considered as the affecting factors of the polyaniline membrane treatment were used for the study of sensitivity analysis. Both the results analyzed from the transfer functions of 2/(1 + e-x) and sgn(x)·x2/(1 + x2) are presented. Prediction of the neural network for sensitivity analysis of the SO2 electrode signal was tested first. Then, the two operation variables considered as important factors affecting the properties of the membrane were studied in view of their influence toward the response current.",
author = "Mei-Jywan Syu and Liu, {Jwo Ying}",
year = "1998",
month = "7",
day = "15",
doi = "10.1016/S0925-4005(98)00147-6",
language = "English",
volume = "50",
pages = "1--8",
journal = "Sensors and Actuators, B: Chemical",
issn = "0925-4005",
publisher = "Elsevier",
number = "1",

}

Neural network sensitivity analysis of the detected signal from an SO2 electrode. / Syu, Mei-Jywan; Liu, Jwo Ying.

In: Sensors and Actuators, B: Chemical, Vol. 50, No. 1, 15.07.1998, p. 1-8.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network sensitivity analysis of the detected signal from an SO2 electrode

AU - Syu, Mei-Jywan

AU - Liu, Jwo Ying

PY - 1998/7/15

Y1 - 1998/7/15

N2 - A novel SO2 electrode was made by doping polyaniline onto Nafion to detect SO2 at ppm level with a linear correlation between the response current and the SO2 concentration in the range of 20 to 250 ppm. By applying artificial neural network, it was possible to predict the SO2 concentration so that a shorter response time (3 min compared with 6 min) was achieved without the need of a noise filter. The operation conditions, cycles for acid/base treatment and immersion time, considered as the affecting factors of the polyaniline membrane treatment were used for the study of sensitivity analysis. Both the results analyzed from the transfer functions of 2/(1 + e-x) and sgn(x)·x2/(1 + x2) are presented. Prediction of the neural network for sensitivity analysis of the SO2 electrode signal was tested first. Then, the two operation variables considered as important factors affecting the properties of the membrane were studied in view of their influence toward the response current.

AB - A novel SO2 electrode was made by doping polyaniline onto Nafion to detect SO2 at ppm level with a linear correlation between the response current and the SO2 concentration in the range of 20 to 250 ppm. By applying artificial neural network, it was possible to predict the SO2 concentration so that a shorter response time (3 min compared with 6 min) was achieved without the need of a noise filter. The operation conditions, cycles for acid/base treatment and immersion time, considered as the affecting factors of the polyaniline membrane treatment were used for the study of sensitivity analysis. Both the results analyzed from the transfer functions of 2/(1 + e-x) and sgn(x)·x2/(1 + x2) are presented. Prediction of the neural network for sensitivity analysis of the SO2 electrode signal was tested first. Then, the two operation variables considered as important factors affecting the properties of the membrane were studied in view of their influence toward the response current.

UR - http://www.scopus.com/inward/record.url?scp=0032118995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032118995&partnerID=8YFLogxK

U2 - 10.1016/S0925-4005(98)00147-6

DO - 10.1016/S0925-4005(98)00147-6

M3 - Article

VL - 50

SP - 1

EP - 8

JO - Sensors and Actuators, B: Chemical

JF - Sensors and Actuators, B: Chemical

SN - 0925-4005

IS - 1

ER -