Improving Fire Safety Systems Based On Internet Of Things And Deep Learning
Bibliographic record
Abstract
Structure fires are one of the main concerns for fire safety systems. The actual fire safety of a building depends on not only how it is designed and constructed, but also on how it is operated. Computational fluid dynamics software is the current solution to reduce the casualties in the fire circumstances. However, it consumes hours to provide the results in some cases that makes it hard to run in real-time. It also does not accept any changes after starting the simulation, which makes it unsuitable for running in the dynamic nature of the fire. On the other hand, the current evacuation signs are fixed, which might guide occupants and firefighter to dangerous zones. In this research, we present a smoke emulator that runs in real-time to reflect what is happening on the ground-truth. This system is achieved using a light-weight smoke emulator engine, deep learning, and internet of things. The IoT sensors are sending the measurements to correct the emulator from any deviation and reflect events such as fire starting, people movement, and the door’s status. This emulator helps the firefighter by providing them with a map that shows the smoke development in the building. They can take a snapshot from the current status of the building and try different virtual evacuation and firefighting plans to pick the best and safest for them to proceed. The system will also control the exit signs to have adaptive exit routes that guide occupants away from fire and smoke to minimize the exposure time to the toxic gases
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".