OPTIMALISASI KEAMANAN LINGKUNGAN BERBASIS AI MELALUI IMPLEMENTASI DAN EVALUASI APLIKASI MO-TAMU 3.0

Yessy Asri; Dwina Kuswardani; Widya Nita Suliyanti; M. Jafar Ely; Atikah Rifdah Ansyari; Muhammad Iqbal

doi:10.31764/jmm.v10i2.38245

OPTIMALISASI KEAMANAN LINGKUNGAN BERBASIS AI MELALUI IMPLEMENTASI DAN EVALUASI APLIKASI MO-TAMU 3.0

Yessy Asri, Dwina Kuswardani, Widya Nita Suliyanti, M. Jafar Ely, Atikah Rifdah Ansyari, Muhammad Iqbal

Abstract

Abstrak: Keamanan lingkungan perumahan menghadapi tantangan akibat sistem pencatatan tamu manual yang kurang efektif. Kegiatan Pengabdian kepada Masyarakat ini bertujuan memperkuat sistem keamanan pada salah satu kawasan perumahan melalui implementasi Aplikasi Mo-Tamu Versi 3.0 berbasis kecerdasan buatan. Metode yang digunakan meliputi analisis kebutuhan mitra, pengembangan sistem berbasis SDLC, pelatihan partisipatif kepada 5 petugas keamanan, perwakilan warga dan pengurus RT, serta evaluasi melalui pengujian kinerja algoritma dan survei User Acceptance Testing (n=12). Hasil menunjukkan peningkatan akurasi pengenalan wajah hingga 90% dengan precision 0,93 dan recall 0,97. Survei menunjukkan 90% responden menyatakan proses monitoring tamu lebih cepat dan 100% menyatakan fitur Emergency Button meningkatkan rasa aman. Implementasi sistem ini meningkatkan efisiensi pencatatan tamu dan memperkuat kesiapsiagaan masyarakat dalam pengelolaan keamanan lingkungan berbasis digital.

Abstract: Residential security faces challenges due to ineffective manual guest-recording systems. This community service program aimed to strengthen the security system in a residential area through the implementation of Mo-Tamu Application Version 3.0 based on artificial intelligence. The method included partner needs analysis, system development using the SDLC approach, participatory training for five security officers, community representatives and neighborhood administrators, and evaluation through algorithm performance testing and a User Acceptance Testing survey (n=12). The results show an improvement in face recognition accuracy up to 90%, with a precision of 0.93 and recall of 0.97. The survey indicates that 90% of respondents reported faster guest monitoring and 100% stated that the Emergency Button feature enhanced their sense of security. The implementation improved guest data management efficiency and strengthened community preparedness in digital-based environmental security management.

Keywords

Environmental Security; Artificial Intelligence; Face Recognition; Emergency Button; Mo-Tamu Application.

Full Text:

DOWNLOAD [PDF]

References

Asri, I., Rahman, A., & Hadi, M. (2024). Implementasi pengenalan wajah berbasis kecerdasan buatan untuk keamanan komunitas. Jurnal Teknologi Keamanan, 10(3), 145–156.

Hassan, M. M., Hussein, H. I., Eesa, A. S., & Mstafa, R. J. (2021). Face recognition based on Gabor feature extraction followed by FastICA and LDA. Computers, Materials & Continua, 68(2), 1637–1659. https://doi.org/10.32604/cmc.2021.014147

Jiang, X., & Li, W. (2021). Application of face recognition technology in urban security systems. IEEE Access, 9, 3512–3525. https://doi.org/10.1109/ACCESS.2021.3092105

Kurniawan, D., Nugroho, L. E., & Wibowo, A. (2023). Design and implementation of intelligent surveillance system using deep learning for real-time security monitoring. TELKOMNIKA (Telecommunication Computing Electronics and Control), 21(2), 389–398. https://doi.org/10.12928/telkomnika.v21i2.24135

Lee, M., & Lee, K. (2022). Recent advances in face recognition algorithms. Proceedings of the International Conference on Artificial Intelligence, 89–95. https://doi.org/10.1109/ICAIA.2022.00012

Munawir, M., Fitria, L., & Hermansyah, M. (2020). Implementasi face recognition pada absensi kehadiran mahasiswa menggunakan metode Haar Cascade classifier. InfoTekJar: Jurnal Nasional Informatika dan Teknologi Jaringan, 4(2), 314–320. https://doi.org/10.30743/infotekjar.v4i2.2885

Pratama, R., & Santoso, H. B. (2022). Implementation of face recognition system for smart security applications using machine learning approach. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 16(2), 145–156. https://doi.org/10.22146/ijccs.70231

Prayogo, D., Rahmawati, S., & Nugraha, A. (2022). Digital literacy in community-based technology adoption. Jurnal Teknologi Informasi dan Ilmu Komputer, 9(3), 511–520.

Putra, I. N. T. A., & Wirawan, I. M. A. (2021). Face recognition system using local binary pattern histogram and support vector machine. TELKOMNIKA (Telecommunication Computing Electronics and Control), 19(3), 857–865. https://doi.org/10.12928/telkomnika.v19i3.18907

Ramayanti, D., Jumaryadi, Y., Gufron, D. M., & Ramadha, D. D. (2023). Sistem keamanan perumahan menggunakan face recognition berbasis Android. Terapan Informatika Nusantara, 3(12), 486–496. https://doi.org/10.47065/tin.v3i12.2084

Rosid, J., Sakti, D. M., Murti, W. S., & Kurniasari, A. (2022). Face recognition dengan metode Haar Cascade dan FaceNet. Indonesian Journal of Data and Science, 3(1), 30–34. https://doi.org/10.33096/ijodas.v3i1.94

Sakti, D. M., Murti, W. S., & Kurniasari, A. (2022). Implementasi pengenalan wajah untuk sistem keamanan cerdas berbasis citra digital. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 6(2), 295–302. https://doi.org/10.29207/resti.v6i2.3927

Suharno, S., Wibowo, R., & Hartati, T. (2021). Model pemberdayaan masyarakat berbasis teknologi informasi. Jurnal Pemberdayaan Masyarakat, 6(2), 120–131.

Wahyuni, S., Prasetyo, A., & Lestari, D. (2021). Evaluasi penerimaan sistem informasi menggunakan pendekatan User Acceptance Testing. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 5(4), 677–684.

Zhang, X., & Yang, Y. (2020). Deep learning for real-time face recognition applications. International Journal of Artificial Intelligence and Machine Learning, 14(4), 220–230. https://doi.org/10.1109/IJAIML.2020.01124

DOI: https://doi.org/10.31764/jmm.v10i2.38245