Metro Fire Incident Knowledge Graph with 792 Nodes and 83 Case Files

83 metro fire incident case files and Python source code reconstruct a knowledge graph with 792 nodes and 2,061 edges. The dataset supports a paper on constructing a safety risk assessment indicator system using knowledge graphs and fuzzy AHP. It was authored by Biao Ma and last updated on April 30, 2026.

Use Cases

• Replicating the construction of a metro fire risk knowledge graph based on the provided 83 incident files.
• Identifying core evaluation indicators for electrical fire scenarios using Louvain community detection and centrality analysis.
• Benchmarking graph algorithms for safety risk assessment in transportation systems.
• Developing or extending indicator systems for infrastructure safety based on the identified 25 core indicators.

Strengths

• Includes 83 specific incident case files providing a foundation for the knowledge graph.
• The reconstructed graph is explicitly defined with 792 nodes and 2,061 edges.
• Source code is provided for full replication of the methodology.
• Released under a permissive CC-BY-4.0 license.

Limitations

• Row count and column-level documentation are unknown; field semantics must be inferred after download.
• The dataset is small at 197.6 KB, indicating a limited scope focused on methodology demonstration.
• Freshness should be verified as the last update date is in the future (2026).

Provenance

Source

figshare

Collection Method

Likely compiled from incident reports or case studies to support the associated research paper.

Time Range

null

Freshness

Last updated 2026-04-30 08:51:48; freshness should be verified.

Geography

Metro systems (specific location not stated).