Quantitative measurement of two-component pH-sensitive colorimetric spectra using multilayer neural networks

Chii Wann Lin, Joseph C. LaManna, Yoshiyasu Takefuji

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The purpose of this research was to develop a noise tolerant and faster processing approach for in vivo and in vitro spectrophotometric applications where distorted spectra are difficult to interpret quantitatively. A PC based multilayer neural network with a sigmoid activation function and a generalized delta learning rule was trained with a two component (protonated and unprotonated form) pH-dependent spectrum generated from microspectrophotometry of the vital dye neutral red (NR). The network makes use of the digitized absorption spectrum between 375 and 675 nm. The number of nodes in the input layer was determined by the required resolution. The number of output nodes determined the step size of the quantization value used to distinguish the input spectra (i.e. defined the number of distinct output steps). Mathematic analysis provided the conditions for which this network is guaranteed to converge. Simulation results showed that features of the input spectrum were successfully identified and stored in the weight matrix of the input and hidden layers. After convergent training with typical spectra, a calibration curve was constructed to interpret the output layer activity and therefore, predict interpolated pH values of unknown spectra. With its built-in redundant presentation, this approach needed no preprocessing procedures (baseline correction or intensive signal averaging) normally used in multicomponent analyses. The identification of unknown spectra with the activities of the output layer is a one step process using the convergent weight matrix. After learning from examples, real time applications can be accomplished without solving multiple linear equations as in the multiple linear regression method. This method can be generalized to pattern oriented sensory information processing and multi-sensor data fusion for quantitative measurement purposes.

Original languageEnglish
Pages (from-to)303-308
Number of pages6
JournalBiological Cybernetics
Volume67
Issue number4
DOIs
Publication statusPublished - 1992 Aug
Externally publishedYes

Fingerprint

Multilayer neural networks
Sensor data fusion
Linear equations
Microspectrophotometry
Linear regression
Learning
Neutral Red
Weights and Measures
Absorption spectra
Dyes
Mathematics
Chemical activation
Calibration
Sigmoid Colon
Automatic Data Processing
Noise
Linear Models
Coloring Agents
Processing
Research

ASJC Scopus subject areas

  • Biophysics

Cite this

Quantitative measurement of two-component pH-sensitive colorimetric spectra using multilayer neural networks. / Lin, Chii Wann; LaManna, Joseph C.; Takefuji, Yoshiyasu.

In: Biological Cybernetics, Vol. 67, No. 4, 08.1992, p. 303-308.

Research output: Contribution to journalArticle

@article{7be3216eee244e2bbfe983d291c736f3,
title = "Quantitative measurement of two-component pH-sensitive colorimetric spectra using multilayer neural networks",
abstract = "The purpose of this research was to develop a noise tolerant and faster processing approach for in vivo and in vitro spectrophotometric applications where distorted spectra are difficult to interpret quantitatively. A PC based multilayer neural network with a sigmoid activation function and a generalized delta learning rule was trained with a two component (protonated and unprotonated form) pH-dependent spectrum generated from microspectrophotometry of the vital dye neutral red (NR). The network makes use of the digitized absorption spectrum between 375 and 675 nm. The number of nodes in the input layer was determined by the required resolution. The number of output nodes determined the step size of the quantization value used to distinguish the input spectra (i.e. defined the number of distinct output steps). Mathematic analysis provided the conditions for which this network is guaranteed to converge. Simulation results showed that features of the input spectrum were successfully identified and stored in the weight matrix of the input and hidden layers. After convergent training with typical spectra, a calibration curve was constructed to interpret the output layer activity and therefore, predict interpolated pH values of unknown spectra. With its built-in redundant presentation, this approach needed no preprocessing procedures (baseline correction or intensive signal averaging) normally used in multicomponent analyses. The identification of unknown spectra with the activities of the output layer is a one step process using the convergent weight matrix. After learning from examples, real time applications can be accomplished without solving multiple linear equations as in the multiple linear regression method. This method can be generalized to pattern oriented sensory information processing and multi-sensor data fusion for quantitative measurement purposes.",
author = "Lin, {Chii Wann} and LaManna, {Joseph C.} and Yoshiyasu Takefuji",
year = "1992",
month = "8",
doi = "10.1007/BF02414886",
language = "English",
volume = "67",
pages = "303--308",
journal = "Biological Cybernetics",
issn = "0340-1200",
publisher = "Springer Verlag",
number = "4",

}

TY - JOUR

T1 - Quantitative measurement of two-component pH-sensitive colorimetric spectra using multilayer neural networks

AU - Lin, Chii Wann

AU - LaManna, Joseph C.

AU - Takefuji, Yoshiyasu

PY - 1992/8

Y1 - 1992/8

N2 - The purpose of this research was to develop a noise tolerant and faster processing approach for in vivo and in vitro spectrophotometric applications where distorted spectra are difficult to interpret quantitatively. A PC based multilayer neural network with a sigmoid activation function and a generalized delta learning rule was trained with a two component (protonated and unprotonated form) pH-dependent spectrum generated from microspectrophotometry of the vital dye neutral red (NR). The network makes use of the digitized absorption spectrum between 375 and 675 nm. The number of nodes in the input layer was determined by the required resolution. The number of output nodes determined the step size of the quantization value used to distinguish the input spectra (i.e. defined the number of distinct output steps). Mathematic analysis provided the conditions for which this network is guaranteed to converge. Simulation results showed that features of the input spectrum were successfully identified and stored in the weight matrix of the input and hidden layers. After convergent training with typical spectra, a calibration curve was constructed to interpret the output layer activity and therefore, predict interpolated pH values of unknown spectra. With its built-in redundant presentation, this approach needed no preprocessing procedures (baseline correction or intensive signal averaging) normally used in multicomponent analyses. The identification of unknown spectra with the activities of the output layer is a one step process using the convergent weight matrix. After learning from examples, real time applications can be accomplished without solving multiple linear equations as in the multiple linear regression method. This method can be generalized to pattern oriented sensory information processing and multi-sensor data fusion for quantitative measurement purposes.

AB - The purpose of this research was to develop a noise tolerant and faster processing approach for in vivo and in vitro spectrophotometric applications where distorted spectra are difficult to interpret quantitatively. A PC based multilayer neural network with a sigmoid activation function and a generalized delta learning rule was trained with a two component (protonated and unprotonated form) pH-dependent spectrum generated from microspectrophotometry of the vital dye neutral red (NR). The network makes use of the digitized absorption spectrum between 375 and 675 nm. The number of nodes in the input layer was determined by the required resolution. The number of output nodes determined the step size of the quantization value used to distinguish the input spectra (i.e. defined the number of distinct output steps). Mathematic analysis provided the conditions for which this network is guaranteed to converge. Simulation results showed that features of the input spectrum were successfully identified and stored in the weight matrix of the input and hidden layers. After convergent training with typical spectra, a calibration curve was constructed to interpret the output layer activity and therefore, predict interpolated pH values of unknown spectra. With its built-in redundant presentation, this approach needed no preprocessing procedures (baseline correction or intensive signal averaging) normally used in multicomponent analyses. The identification of unknown spectra with the activities of the output layer is a one step process using the convergent weight matrix. After learning from examples, real time applications can be accomplished without solving multiple linear equations as in the multiple linear regression method. This method can be generalized to pattern oriented sensory information processing and multi-sensor data fusion for quantitative measurement purposes.

UR - http://www.scopus.com/inward/record.url?scp=0026479731&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026479731&partnerID=8YFLogxK

U2 - 10.1007/BF02414886

DO - 10.1007/BF02414886

M3 - Article

VL - 67

SP - 303

EP - 308

JO - Biological Cybernetics

JF - Biological Cybernetics

SN - 0340-1200

IS - 4

ER -