Prototype smart integrated fire detection based on deep learning YOLO v8 and IoT (internet of things) to improve early fire detection

Abstract

The high incidence of fires in Indonesia in 2018-2023 is 5,336 fire incidents have caused many deaths and enormous material losses. This system is designed to identify early signs of fire through object detection and sensor technology, which is integrated with the Blynk IoT platform for real-time sensor monitoring and Telegram for instant notifications to users. The waterfall prototype method was designed through observation, system design, program code creation, tool testing, and tool implementation. This research uses Deep Learning YOLOv8 technology and IoT using ESP 32 as a microcontroller. Based on the training datasets, it produces precision=0.95872; recall=0.91; mAP50=0.97; mAP50-95 =0.66. The system uses the integration of a multisensor KY-026 flame sensor, DHT 22 temperature and humidity sensor, and MQ-2 sensors can detect CO, LPG, and smoke gas. All these multisensors can be monitored on Blynk IoT and Telegrambot in real time.