An IoT-Based Framework for Wildfire Detection Using Multi-Sensors Integration and CNN Image Classification
Bibliographic record
Abstract
Wildfires are a growing threat to ecosystems, property, and human lives, especially in rural and forest-adjacent areas where monitoring infrastructure is limited. Traditional detection methods, such as satellite imaging and human surveillance, often suffer from delayed response and low precision during early fire stages. This study proposes a novel IoT-based wildfire detection framework that combines multi-sensor data with deep learning for rapid and localized fire identification. The system integrates smoke and flame sensors with a YOLOv4-based convolutional neural network (CNN) for image classification, all deployed on a Raspberry Pi 5 platform. A dual-layer detection mechanism enables immediate threshold-based alerts and visual confirmation via AI-driven analysis. Real-time notifications are delivered through a Telegram bot, while environmental data are logged and visualized using the ThingSpeak dashboard. The system, developed in Python, is optimized for deployment in low-resource environments. Experimental results demonstrate high detection accuracy and reliable performance across diverse conditions. This work demonstrates the practical potential of lightweight, AI-enhanced IoT systems for early wildfire detection and offers a scalable solution for remote monitoring. Future enhancements will explore more efficient CNN architectures and predictive analytics for proactive fire management.
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 | 0.000 | 0.000 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".