<?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-20-4364-1795086053</doi_batch_id>
  <timestamp>20261119110053</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>2</issue>
   </journal_issue>
   <journal_article publication_type="full_text">
    <titles>
     <title>WS-STACK: A Weighted Stacking Ensemble with Multi-Criteria Feature Selection for Multi-Class Traffic Classification and Anomaly Detection in Heterogeneous Wireless Sensor Networks</title>
    </titles>
    <contributors>
     <person_name sequence="first" contributor_role="author">
      <given_name>Zainab Hussein</given_name>
      <surname>Arif</surname>
      <affiliations>
       <institution>
        <institution_name>College of Nursing, University of Al-Qadisiyah, Al-Qadisiyah Province, 58002, Iraq</institution_name>
       </institution>
      </affiliations>
     </person_name>
     <person_name sequence="additional" contributor_role="author">
      <given_name>Nureize bt</given_name>
      <surname>Arbaiy</surname>
      <affiliations>
       <institution>
        <institution_name>Fakulti Sains Komputer dan Teknologi Maklumat, Universiti Tun Hussein Onn Malaysia (UTHM), 86400 Batu Pahat, Johor, Malaysia</institution_name>
       </institution>
      </affiliations>
     </person_name>
    </contributors>
    <jats:abstract>
     <jats:p>Heterogeneous Internet-of-Things deployments expose wireless sensor networks to a diverse and continuously evolving threat landscape encompassing distributed denial-of-service flooding, network reconnaissance scanning, and brute-force credential attacks. Existing intrusion detection approaches predominantly adopt single-classifier architectures and binary labelling, which are ill-suited to the multi-class, class-imbalanced traffic characteristic of real-world IoT sensor deployments. This paper proposes WS-STACK, a Weighted Stacking ensemble that combines five heterogeneous base learners—Random Forest, XGBoost, Support Vector Machine, K-Nearest Neighbours, and Gradient Boosting—under an ℓ2-regularised Logistic Regression meta-learner trained on cross validationgenerated probability features. A three-stage feature engineering pipeline comprising mutual information filtering, variance inflation factor pruning, and correlation-based elimination reduces the 83 dimensional RT-IoT2022 feature space to 20 informative features, and the Synthetic Minority Over-Sampling Technique corrects the six-fold class imbalance prior to training. Evaluated on 83,000 labelled network flow records from the publicly available RTIoT2022 benchmark spanning four benign traffic patterns and seven attack categories, WS-STACK achieves 99.61% classification accuracy, a weighted F1-score of 0.9960, and an AUC-ROC of 0.9978, outperforming every individual base classifier and five recently published state-of-the-art baselines. The false positive rate is reduced to 0.0006, and ten-fold cross-validation confirms μacc = 0.9959 (σ = 0.0004). Ablation experiments identify SMOTE as the single most critical preprocessing component, and noise robustness tests confirm 98.81% accuracy under 20% Gaussian feature perturbation. The framework is grounded through a formal variance-reduction proof and a channel-energy anomaly model that establishes the physical motivation for packet-rate features as the dominant intrusion detection signal in constrained wireless sensor networks.</jats:p>
    </jats:abstract>
    <publication_date media_type="online">
     <year>2026</year>
    </publication_date>
    <pages>
     <first_page>43</first_page>
     <last_page>50</last_page>
    </pages>
    <publisher_item>
     <item_number item_number_type="article-number">4364</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.100206</doi>
     <resource>http://demo.americaspg.com/journal/20/article/4364</resource>
     <collection property="text-mining">
      <item>
       <resource mime_type="application/pdf">http://demo.americaspg.com/storage/articles/manuscripts/01M78E5ZZZSY0AZBJN4D6MB8QJ.pdf</resource>
      </item>
     </collection>
    </doi_data>
   </journal_article>
  </journal>
 </body>
</doi_batch>
