<p>Summary of Datasets Used for Evaluation.</p>

Ali Alqazzaz provides a summary of datasets used to evaluate the MedDefender-MHAN explainable intrusion detection system for healthcare IoT. The summary, last updated in April 2026, is a 5.5 KB Excel file. It references evaluation results on the CICIDS2017 and TON_IoT benchmark datasets.

Use Cases

• Benchmarking intrusion detection system performance based on reported detection accuracies of 99.47% and 98.92%.
• Evaluating model explainability in cybersecurity based on reported alignment with expert-annotated attack signatures.
• Comparing inference latency and throughput for real-time healthcare IoT security applications.
• Assessing regulatory compliance of AI-driven security solutions for healthcare based on the described framework.

Strengths

• Dataset is openly licensed under CC-BY-4.0.
• Specific performance metrics are provided, including detection accuracies, sub-3ms latency, and 435 samples/second throughput.
• Explainability metrics are quantified with 94.6% alignment and 91.9% temporal accuracy.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The 5.5 KB size suggests the file is a summary or metadata, not the primary evaluation datasets themselves.

Provenance

Source

Ali Alqazzaz via figshare.

Collection Method

Likely compiled as part of academic research on the MedDefender-MHAN system.

Time Range

null

Freshness

Last updated 2026-04-17 17:39:26; freshness should be verified.

Geography

null