Implementasi Machine Learning Dalam Sistem Keamanan Rumah Pintar Berbasis Iot Dengan Deteksi Gerakan dan Pengenalan Wajah

Amirullah, Alfian Nur
Faizin, Arif

Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika)
Vol 10, No 2 (2025): Edisi Agustus

Innovation in digital-based home security systems. This study aims to design and implement a smart home security system capable of detecting motion and recognizing faces using the Convolutional Neural Network (CNN) model. The system utilizes the ESP32-CAM microcontroller and PIR sensor as main components, where captured face images are sent to a local or cloud server for classification. Test results show that the system can detect motion at an optimal distance of 4–6 meters and recognize household members’ faces with an accuracy of up to 92%. The system is also integrated with the Telegram API to send real-time notifications when unknown faces are detected. This approach proves the system to be responsive, efficient, and capable of enhancing home security automatically and adaptively according to environmental conditions.