<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.0 20120330//EN" "JATS-journalpublishing1.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="article">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">csat</journal-id>
      <journal-title-group>
        <journal-title>Computational Science and Techniques</journal-title>
      </journal-title-group>
      <issn pub-type="epub"/>
      <issn pub-type="ppub"/>
      <publisher>
        <publisher-name>KU</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="publisher-id">CE_LITVINASBARONAS_AUTH</article-id>
      <article-id pub-id-type="doi">10.15181/csat.v3i2.1109</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Article</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>The Influence of the Diffusion Module to Determination of two Substrate Concentrations by Artificial Neural Network</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <name>
            <surname>Litvinas</surname>
            <given-names>Linas</given-names>
          </name>
          <email xlink:href="mailto:linas.litvinas@gmail.com">linas.litvinas@gmail.com</email>
          <xref ref-type="corresp" rid="cor1">∗</xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Baronas</surname>
            <given-names>Romas</given-names>
          </name>
          <email xlink:href="mailto:romas.baronas@mif.vu.lt">romas.baronas@mif.vu.lt</email>
        </contrib>
      </contrib-group>
      <author-notes>
        <corresp id="cor1"><label>∗</label>Corresponding author.</corresp>
      </author-notes>
      <volume>3</volume>
      <issue>2</issue>
      <fpage>445</fpage>
      <lpage>453</lpage>
      <pub-date pub-type="epub">
        <day>24</day>
        <month>09</month>
        <year>2015</year>
      </pub-date>
      <history>
        <date date-type="received">
          <day>01</day>
          <month>08</month>
          <year>2015</year>
        </date>
        <date date-type="accepted">
          <day>10</day>
          <month>09</month>
          <year>2015</year>
        </date>
      </history>
      <permissions>
        <copyright-year>2015</copyright-year>
        <license license-type="open-access" xlink:href="http://creativecommons.org/licenses/by/3.0/">
          <license-p>Creative Commons Attribution 3.0 License</license-p>
        </license>
      </permissions>
      <abstract>
        <p>The essential part of amperometric biosensor is an enzyme. It should be selective, i.e., react only with certain substrate. The selectivity of enzyme reduces the set of possible to use enzymes. This paper demonstrates that non selective enzymes (reacting with two substrates) can be used to determine concentrations of two substrates. For this purpose the steady-state current of two double biosensors was measured. The currents were used as input for an artificial neural network to determine concentrations of the substrates. The proposed approach was approved as the relative error of determined concentrations was relatively small. Paper analyses the influence of biosensor parameters to error values. The recommendations to error values minimisation were obtained.</p>
      </abstract>
      <kwd-group>
        <label>Keywords</label>
        <kwd>biosensor</kwd>
        <kwd>artificial neural network</kwd>
        <kwd>enzyme</kwd>
        <kwd>diffusion module</kwd>
      </kwd-group>
    </article-meta>
  </front>
</article>
