{"id":280129,"date":"2026-06-24T01:48:00","date_gmt":"2026-06-24T05:48:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/06\/24\/a-hybrid-llm-and-machine-learning-framework-for-early-fire-detection-in-subway-tunnels\/"},"modified":"2026-06-24T01:50:08","modified_gmt":"2026-06-24T05:50:08","slug":"a-hybrid-llm-and-machine-learning-framework-for-early-fire-detection-in-subway-tunnels","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/06\/24\/a-hybrid-llm-and-machine-learning-framework-for-early-fire-detection-in-subway-tunnels\/","title":{"rendered":"A hybrid LLM and machine learning framework for early fire detection in subway tunnels"},"content":{"rendered":"

A hybrid LLM and machine learning framework for early fire detection in subway tunnels<\/a><\/p>\n

https:\/\/www.nature.com\/articles\/s41598-026-56984-7<\/a><\/p>\n

Publish Date: 2026-06-24 01:48:00<\/a><\/p>\n

Source Domain: www.nature.com<\/a><\/p>\n

Appendix<\/h3>\n

Sensitivity analysis of operational parameters<\/h3>\n

Table\u00a08 presents the sensitivity analysis of the LLM-augmented classifiers across different decision thresholds ((tau))<\/span> and temporal persistence windows (k) on the Total dataset. The analysis evaluates how F1 Score, Detection Delay, and Pre-Alarm Rate (PAR) vary as the alarm-formation rule becomes more permissive or more conservative. The default operating setting used in the main experiments is (tau =0.50)<\/span> and (k=1.0text {s})<\/span>.<\/p>\n

Table 8 Sensitivity analysis of LLM-augmented classifiers on the Total dataset across decision thresholds ((tau)<\/span>) and temporal persistence windows. Results are presented as mean (\u00b1 standard deviation) across 5 seeds. Bold values indicate the default operating setting ((tau =0.50)<\/span> and (k=10)<\/span> frames, equivalent to 1.0 s) used in the main experiments; these results are kept consistent with the main tables.<\/p>\n

Overall, the results show a clear trade-off between detection sensitivity and premature-alarm suppression. Lower thresholds generally preserve higher F1 scores but substantially increase PAR, indicating more aggressive alarm behavior. For example, at (tau =0.25)<\/span> and (k=1.0text {s})<\/span>, SVM + LLM and GBM + LLM achieve high F1 scores of 87.45% and 90.85%, respectively, but their PAR values rise to 99.25% and 51.32%. In contrast, higher thresholds suppress premature alarms more strongly but often degrade F1. For instance, increasing the threshold to (tau =0.75)<\/span> at (k=1.0text {s})<\/span> reduces PAR to 8.68% for SVM + LLM, 6.04% for RF + LLM, and 12.08% for GBM + LLM, but lowers their F1 scores to 64.78%, 69.21%, and 69.66%, respectively.<\/p>\n

The temporal persistence window further modulates this trade-off. Increasing the persistence window from 1.0 to 2.0 s or 3.0 s generally reduces PAR, but excessive smoothing can substantially reduce F1, especially for SVM + LLM and RF + LLM. GBM + LLM is comparatively more robust under moderate smoothing: at (tau =0.50)<\/span> and <\/p>\n

Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

A hybrid LLM and machine learning framework for early fire detection in subway tunnels https:\/\/www.nature.com\/articles\/s41598-026-56984-7…<\/p>\n","protected":false},"author":1,"featured_media":280130,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/media.springernature.com\/m685\/springer-static\/image\/art%3A10.1038%2Fs41598-026-56984-7\/MediaObjects\/41598_2026_56984_Fig4_HTML.png","fifu_image_alt":"","footnotes":""},"categories":[14],"tags":[17],"class_list":["post-280129","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-llm"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/280129"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=280129"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/280129\/revisions"}],"predecessor-version":[{"id":280131,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/280129\/revisions\/280131"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/280130"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=280129"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=280129"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=280129"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}