Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal International Journal of Engineering Continuity
Ghani, Naufal
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Engineering Materials Science & Nanotechnology Mechanical Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : International Journal of Engineering Continuity

 1 
Smart Home Security System Using Object Recognition with the EfficientDet Algorithm: A Real-Time Approach Suyatno, Suyatno; Natali, Yus; Reza Fachrurrozi, Nurwan; Roihan, Muhamad; Dorand, Pietra; Ghani, Naufal
International Journal of Engineering Continuity Vol. 4 No. 1 (2025): ijec
Publisher : Sultan Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58291/ijec.v4i1.400

Abstract

The EfficientDet method, which is implemented on the Raspberry Pi for real-time detection in resource-constrained contexts, is the basis for the smart home security system presented in this study.  The system integrates CCTV cameras, motion sensors, and detectors to identify and classify objects, sending notifications via WhatsApp via the Twilio API.  The EfficientDet-D0 model achieves an accuracy of 94.8%, an average processing time of 45 ms, and a memory usage of about 850 MB.  When compared to moving individuals or non-human things, testing shows that stationary human items have a higher detection accuracy.  Notifications are transmitted roughly every three seconds, with an average latency of 1.4 to 1.8 seconds.  The suggested method provides object recognition, real-time monitoring, and configuration flexibility in contrast to traditional IoT-based systems.  These results highlight the potential of EfficientDet as a reliable and adaptable solution for home security.  Future improvements include improving accuracy in a variety of environmental conditions and implementing adaptive learning.
Co-Authors Nurwan Reza Fachrurrozi Pietra Dorand Roihan, Muhamad Suyatno Suyatno Yus Natali