<?xml version="1.0" encoding="UTF-8"?>
<doi_batch version="5.3.1" xmlns="http://www.crossref.org/schema/5.3.1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:jats="http://www.ncbi.nlm.nih.gov/JATS1" xmlns:ai="http://www.crossref.org/AccessIndicators.xsd" xsi:schemaLocation="http://www.crossref.org/schema/5.3.1 http://www.crossref.org/schema/deposit/crossref5.3.1.xsd">
 <head>
  <doi_batch_id>aspg-20-4358-1795083151</doi_batch_id>
  <timestamp>20261119101231</timestamp>
  <depositor>
   <depositor_name>American Scientific Publishing Group</depositor_name>
   <email_address>admin@americaspg.com</email_address>
  </depositor>
  <registrant>American Scientific Publishing Group</registrant>
 </head>
 <body>
  <journal>
   <journal_metadata language="en">
    <full_title>International Journal of Wireless and Ad Hoc Communication</full_title>
    <abbrev_title>IJWAC</abbrev_title>
    <issn media_type="electronic">2692-4056</issn>
   </journal_metadata>
   <journal_issue>
    <publication_date media_type="online">
     <year>2026</year>
    </publication_date>
    <journal_volume>
     <volume>10</volume>
    </journal_volume>
    <issue>1</issue>
   </journal_issue>
   <journal_article publication_type="full_text">
    <titles>
     <title>TA-FaultNet: A Temporal Attention Framework with Bidirectional LSTM for Multi-Class Fault Detection and Health Monitoring in Industrial Wireless Sensor Networks</title>
    </titles>
    <contributors>
     <person_name sequence="first" contributor_role="author">
      <given_name>Massila</given_name>
      <surname>Kamalrudin</surname>
      <affiliations>
       <institution>
        <institution_name>Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Malaysia</institution_name>
       </institution>
      </affiliations>
     </person_name>
     <person_name sequence="additional" contributor_role="author">
      <given_name>Mustafa</given_name>
      <surname>Musa</surname>
      <affiliations>
       <institution>
        <institution_name>Center of Research and Innovation Management, Universiti Teknikal Malaysia Melaka, Malaysia</institution_name>
       </institution>
      </affiliations>
     </person_name>
    </contributors>
    <jats:abstract>
     <jats:p>Industrial wireless sensor networks are central to the continuous monitoring of critical plant equipment, yet reliable identification of multiple concurrent fault modes from heterogeneous multivariate sensor streams remains an unsolved operational challenge. Physical failure mechanisms—pump cavitation, valve blockage, gradual sensor drift—and wireless channel disturbances each imprint distinct but overlapping temporal signatures that render classical thresholdand rule-based detectors inadequate for automated maintenance dispatch. This paper presents TA-FaultNet, a neural architecture designed specifically for the multi-class fault identification problem in industrial sensor deployments. The network couples a two-stage stacked bidirectional recurrent encoder with a parallel multi-head self-attention module and a compact temporal convolutional block, enabling simultaneous capture of long-range process dynamics and fine-grained fault-onset localisation from raw sensor windows. TA-FaultNet is evaluated on the publicly available Skoltech Anomaly Benchmark under five operational classes and assessed through a comprehensive battery of experiments including baseline comparisons, systematic component ablation, cross-experiment generalisation, andprogressive noise-injection testing. The proposed architecture decisively outperforms eight competing methods spanning classical anomaly detectors, standalone recurrent and convolutional networks, and the Transformer, while remaining lightweight enough for edge gateway deployment. Attention weight visualisations expose fault-specific temporal activation patterns, providing maintenance engineers with interpretable diagnostic evidence beyond bare classification labels.</jats:p>
    </jats:abstract>
    <publication_date media_type="online">
     <year>2026</year>
    </publication_date>
    <pages>
     <first_page>26</first_page>
     <last_page>34</last_page>
    </pages>
    <publisher_item>
     <item_number item_number_type="article-number">4358</item_number>
    </publisher_item>
    <ai:program name="AccessIndicators">
     <ai:license_ref applies_to="vor">https://creativecommons.org/licenses/by/4.0/</ai:license_ref>
    </ai:program>
    <doi_data>
     <doi>10.54216/IJWAC.100105</doi>
     <resource>http://demo.americaspg.com/journal/20/article/4358</resource>
     <collection property="text-mining">
      <item>
       <resource mime_type="application/pdf">http://demo.americaspg.com/storage/articles/manuscripts/01M78DF7ET5CVCEPZJNR3T420K.pdf</resource>
      </item>
     </collection>
    </doi_data>
   </journal_article>
  </journal>
 </body>
</doi_batch>
