DETEKSI API MENGGUNAKAN BACKGROUND SUBSTRACTION DAN ARTIFICIAL NEURAL NETWORK UNTUK REAL TIME MONITORING

Andi Kamaruddin
Vincent Suhartono
Ricardus Anggi Pramunendar

Jurnal Teknologi Informasi Cyberku
Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1

The most important initial step in the detection and localization of the fire is to detect fire quickly and reliably. Video-based surveillance is one of the most promising solutions for automatic fire detection with the ability to monitor a large area and ease of reading an alarm to the operator through the monitorSupervision, unfortunately, the main drawback of video-based fire monitoring system that uses optic is a false alarm caused by an Error detection (Error detection), for it is then in this study using the feature extraction GLCM (Gray level Coocurance Matrix) as input spectral classification of Neural network to detect fire, the approach can reduce the Average Error detection with Error detection rate Average is 7%