AI-Based IoT Gas Leakage and Fire Detection

—Gas leakage, fire incidents, and abnormal envi- ronmental conditions create safety risks in homes, laborato- ries, workshops, and industrial settings. This paper presents RiskSense, an ESP32-based Internet of Things (IoT) prototype designed to monitor gas-sensitive readings, flame status, tempera- ture, and humidity. The prototype combines an MQ-2 gas sensor, a digital flame sensor, and a DHT11 sensor with local indicators, a buzzer, a motor driver, and the Blynk IoT platform. Sensor readings are processed using configurable thresholdbased logic for local alarms, while status values and alerts can be viewed remotely through a Wi-Fi-connected dashboard. An artificial intelligence (AI) layer based on a Random Forest classifier is implemented to classify the monitored conditions into NORMAL, WARNING, and CRITICAL risk categories. Isolation Forest for unusual sensor-pattern detection is proposed as future work. The paper describes the system architecture, hardware and software design, control logic, the Random Forest algorithm used, implementation methodology, validation plan, limitations, and future work. Since measured experimental results and numerical model-evaluation metrics have not been provided, no numerical performance claims are made. Index Terms—Internet of Things, ESP32, MQ-2, flame detec- tion, DHT11, gas leakage, fire detection, environmental monitor- ing, Blynk, Random Forest, machine learning.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24371738
Primary Topic
Fire Detection and Safety Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI-Based IoT Gas Leakage and Fire Detection

Shuyang Zhang
Zenodo (CERN European Organization for Nuclear Research)
Fire Detection and Safety Systems
article

AI-Based IoT Gas Leakage and Fire Detection

Shuyang Zhang
article en

Abstract

—Gas leakage, fire incidents, and abnormal envi- ronmental conditions create safety risks in homes, laborato- ries, workshops, and industrial settings. This paper presents RiskSense, an ESP32-based Internet of Things (IoT) prototype designed to monitor gas-sensitive readings, flame status, tempera- ture, and humidity. The prototype combines an MQ-2 gas sensor, a digital flame sensor, and a DHT11 sensor with local indicators, a buzzer, a motor driver, and the Blynk IoT platform. Sensor readings are processed using configurable thresholdbased logic for local alarms, while status values and alerts can be viewed remotely through a Wi-Fi-connected dashboard. An artificial intelligence (AI) layer based on a Random Forest classifier is implemented to classify the monitored conditions into NORMAL, WARNING, and CRITICAL risk categories. Isolation Forest for unusual sensor-pattern detection is proposed as future work. The paper describes the system architecture, hardware and software design, control logic, the Random Forest algorithm used, implementation methodology, validation plan, limitations, and future work. Since measured experimental results and numerical model-evaluation metrics have not been provided, no numerical performance claims are made. Index Terms—Internet of Things, ESP32, MQ-2, flame detec- tion, DHT11, gas leakage, fire detection, environmental monitor- ing, Blynk, Random Forest, machine learning.

Zenodo (CERN European Organization for Nuclear Research)
Ajeenkya DY Patil University (IN)
Fire Detection and Safety Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon