FIRE EARLY WARNING SYSTEM VIA CCTV CAMERA USING CONVOLUTIONAL NEURAL NETWORK

Abstract

At the Informatics Engineering Laboratory of Pontianak State Polytechnic, there is a fire detection system using smoke and heat sensors in certain rooms, while CCTV cameras are available throughout the room. Therefore, a fire detection system using CCTV cameras is proposed as an alternative fire detection tool to support sensor-based fire detection. Convolutional Neural Networks (CNNs) are a class of deep learning algorithms specifically designed for processing structured grid data, such as images. They are particularly effective in tasks related to image recognition and classification due to their ability to automatically learn spatial hierarchies of features from input images. This system works by processing video from CCTV cameras and classified using a Convolutional Neural Network (CNN) model that has been previously trained to recognize visual signs related to fire on video from CCTV cameras. Detected fire will be sent a notification via the user's Telegram application. These results show that the system works as expected with an average confidence level of 91.9% accuracy and 20.8% loss. The system was successfully developed into a fire detection application using the Convolutional Neural Network (CNN) model integrated with CCTV cameras and notification features via the Telegram application.