<?xml version="1.0" encoding="UTF-8"?>
<article article-type="Research Article">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher">journal-of-information-and-optimization-sciences</journal-id>
      <journal-title-group>
        <journal-title>Journal of Information and Optimization Sciences</journal-title>
      </journal-title-group>
      <issn publication-format="electronic">2169-0103</issn>
      <issn publication-format="print">0252-2667</issn>
      <publisher>
        <publisher-name>Taru Publications</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.47974/JIOS-2253</article-id>
      <title-group>
        <article-title>Experimental evaluation of a BiLSTM network for Indian sign language recognition</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author" corresp="yes">
          <name>
            <surname>Chouhan</surname>
            <given-names>Silviya</given-names>
          </name>
          <aff>Department of Electronics &amp; Communication Engineering, Ratanada, MBM University, Jodhpur, Rajasthan, 342011, India</aff>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Bhadada</surname>
            <given-names>Rajesh</given-names>
          </name>
          <aff>Department of Electronics &amp; Communication Engineering, Ratanada, MBM University, Jodhpur, Rajasthan, 342011, India</aff>
        </contrib>
      </contrib-group>
      <volume>47</volume>
      <issue>5-A</issue>
      <fpage>1633</fpage>
      <lpage>1641</lpage>
      <pub-date date-type="pub">
        <day>23</day>
        <month>04</month>
        <year>2026</year>
      </pub-date>
      <abstract>
        <p>For the Hearing-and speech-impaired (HSI) individuals in India, the ISL functions as a standard and helps communication. This paper proposed an efficient Indian Sign Language recognition system that focused on computational efficiency and accuracy, which is achieved by intelligent temporal modelling, key frame selection and lower-dimension feature extraction. The frames are used to extract features with the Mediapipe Holistic model (MPHm) to form a low-dimensional feature vector. A BiLSTM network, which learns temporal dependencies in both forward and backward directions, is used to model the sequential characteristics of signs. The model has been trained and evaluated on 22 frequently-used ISL isolated words from a public-domain pre-recorded video dataset called INCLUDE and achieved an accuracy of 96.91% on these sample strata. In addition to that, the performance of the model is also evaluated on the INCLUDE 50 dataset, and an accuracy of 98.37% has been achieved.</p>
      </abstract>
      <kwd-group>
        <kwd>ASLR</kwd>
        <kwd>Sign language</kwd>
        <kwd>MPHm</kwd>
        <kwd>Hearing-and speech-impaired</kwd>
        <kwd>Indian sign language</kwd>
      </kwd-group>
      <custom-meta-group>
        <custom-meta>
          <meta-name>access</meta-name>
          <meta-value>open</meta-value>
        </custom-meta>
        <custom-meta>
          <meta-name>retracted</meta-name>
          <meta-value>no</meta-value>
        </custom-meta>
      </custom-meta-group>
    </article-meta>
  </front>
</article>
