Published August 29, 2026 | Version 1.0

Data Extraction Sheet for Systematic Review: Machine Learning Applications for IoT Intrusion Detection (Manuscript network-4470849)

  • 1. ROR icon Al Baha University
  • 2. EDMO icon University of Technology, Sydney

Description

Structured data-extraction sheet for the 38 method papers synthesised in Table 7 of the systematic review "Machine Learning Applications for IoT Intrusion Detection: Network Dependencies, Dataset Limitations, and Regulatory Compliance—A Systematic Review" (manuscript network-4470849, submitted to Network, MDPI). Extracted per PRISMA 2020 items 9 and 10a/10b: bibliographic identifier, lead author and year, full citation, method family, application focus, gap addressed, dataset(s) used, validation approach, and QA1–QA4 quality-assessment scores.

Extraction was performed by the lead author into a spreadsheet template piloted on five randomly selected full-text candidates before extraction of the full corpus began. A second reviewer independently re-extracted a random 20% sample of included studies; inter-rater agreement on structured fields reached 92%, with remaining disagreements resolved through discussion.

The QA1–QA4 scores reproduced here are drawn from the independently-validated post-hoc reconstruction deposited separately at https://doi.org/10.5281/zenodo.22143353; this dataset combines those scores with the full extraction fields for convenience. The 8 non-method-paper included studies (foundational, methodological, and survey references) are not method-family-classified in the same way and are not included as rows here.

Fields marked "n/r" indicate the detail was not specified in the reviewed evidence.

Files

Files (13.7 kB)

Name Size
md5:34cfff50e87b9ceeda42a1a5c2171d88
13.7 kB Download