Optimasi Model Yolov8n Menggunakan Augmentasi Data Untuk Peningkatan Akurasi Sistem Dress-Code Surveillance
-
Sherla Mutia
*
Universitas Nusantara PGRI Kediri,
Indonesia
- Rina Firliana Universitas Nusantara PGRI Kediri , Indonesia
- Arie Nugroho Universitas Nusantara PGRI Kediri, Indonesia
Abstract
Manual surveillance of student dress-code compliance on campus is often inefficient, subjective, and constrained by the physical fatigue of security personnel. This study aims to automate the surveillance system by optimizing the Nano variant of the YOLOv8 (YOLOv8n) Deep Learning model based on Computer Vision. The main challenge in real-time object detection is limited datasets and visual diversity, which increases the risk of overfitting. The solution applied to address this issue is the implementation of comprehensive dynamic data augmentation strategies, including Hue, Saturation, Value (HSV) manipulation, Horizontal Flipping, and Mosaic Augmentation. Utilizing the CRISP-DM methodology, this technique expanded the dataset from 5,000 initial images to 9,742 training images. The empirical test results show that the optimized YOLOv8n model significantly improved accuracy by 43,5% compared to the baseline model. The best-performing model achieved a Mean Average Precision (mAP@0.5) of 95.3%, with a Precision of 93.1%, Recall of 91.1%, and an F1-score of 0.92. These metrics demonstrate the reliability of the system in reducing false positives while operating in crowded real-world environments. This automated surveillance system is highly feasible for direct integration into campus CCTV infrastructure using edge computing to objectively support institutional discipline.
References
R. Szeliski, Texts in Computer Science: Computer Vision Algorithms and Applications Second Edition, no. January. 2022.
R. Delussu, L. Putzu, and G. Fumera, “Synthetic Data for Video Surveillance Applications of Computer Vision: A Review,” Int. J. Comput. Vis., vol. 132, no. 10, pp. 4473–4509, Oct. 2024, doi: 10.1007/s11263-024-02102-x.
P. R. Kalluri, W. Agnew, M. Cheng, K. Owens, L. Soldaini, and A. Birhane, “Computer-vision research powers surveillance technology,” Nature, vol. 643, no. 8070, pp. 73–79, Jul. 2025, doi: 10.1038/s41586-025-08972-6.
D. Triyanto, M. Zidan, M. Wahyudi, L. Pujiastuti, U. Bina Sarana Informatika, and S. Antar Bangsa, “Pengembangan Sistem Deteksi Objek Botol Real-Time dengan YOLOv8 untuk Aplikasi Vision,” Journal Computer Science, vol. 3, no. 1, 2024.
N. Wakhidah, P. T. Pungkasanti, and A. P. R. Pinem, “Deteksi Objek menggunakan Deep Learning untuk Mengetahui Tingkat Kerumunan Mahasiswa,” Jurnal Edukasi dan Penelitian Informatika (JEPIN), vol. 9, no. 3, 2023, doi: 10.26418/jp.v9i3.70132.
M. R. Karthikeyan, “EFFICIENT MONITORING OF DRESS CODE ADHERENCE USING AI AND LIVE CAMERA FEEDS IN CLOUD COMPUTING ENVIRONMENTS,” 2025.
J. W. Qi Li, “Lightweight Real-time Detection Method for Dress Code of Anti-static Equipment,” Academic Journal of Computing & Information Science, vol. 6, no. 10, pp. 7–17, 2023, doi: 10.25236/ajcis.2023.061002.
Geraldo Tan, Agung Saputra, Richardo Renzo Chandra, Radja Ardjuna Rithaudin Pua, and Muhammad Akbar Maulana, “YOLOV8 DETECTION FOR STUDENT DRESS CODE COMPLIANCE USING COMPUTER VISION,” JURTEKSI (jurnal Teknologi dan Sistem Informasi), vol. 12, no. 1, pp. 199–206, Dec. 2025, doi: 10.33330/jurteksi.v12i1.4350.
A. R. Firdaus, O. B. Kharisma, E. Ismaredah, and Abdillah, “Deteksi Kode Etik Berpakaian pada Area Kampus Menggunakan YoloV8,” Journal of Information System Research, vol. 5, pp. 450–458, Jan. 2024.
T. Taufiqurrahman, A. P. Hadi, and R. E. Siregar, “Evaluasi Performa Yolov8 Dalam Deteksi Objek Di Depan Kendaraan Dengan Variasi Kondisi Lingkungan,” Jurnal Minfo Polgan, vol. 13, no. 2, pp. 1755–1773, Nov. 2024, doi: 10.33395/jmp.v13i2.14228.
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” Apr. 2020, [Online]. Available: http://arxiv.org/abs/2004.10934
Y. Yanto, F. Aziz, and I. Irmawati, “YOLO-V8 PENINGKATAN ALGORITMA UNTUK DETEKSI PEMAKAIAN MASKER WAJAH,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 7, no. 3, 2023, doi: 10.36040/jati.v7i3.7047.
A. Latifah and Y. Fendriani, “KLASIFIKASI PENYAKIT KANKER PAYUDARA PADA CITRA MAMMOGRAM MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) DAN RANDOM FOREST,” JoP, vol. 10, no. 3, pp. 95–103, 2025, [Online]. Available: https://www.kaggle.com/datasets/hayder17
T. Adriyanto, R. A. Ramadhani, R. Helilintar, and A. Ristyawan, “Classification of Dog and Cat Images using the CNN Method,” ILKOM Jurnal Ilmiah, vol. 14, no. 3, 2022, doi: 10.33096/ilkom.v14i3.1116.203-208.
D. Tsalsabila Rhamadiyanti, “Analisa Performa Convolutional Neural Network dalam Klasifikasi Citra Apel dengan Data Augmentasi,” Media Online), vol. 5, no. 1, pp. 154–162, 2024, doi: 10.30865/klik.v5i1.2023.
R. Delussu, L. Putzu, and G. Fumera, “Synthetic Data for Video Surveillance Applications of Computer Vision: A Review,” Int. J. Comput. Vis., vol. 132, no. 10, pp. 4473–4509, Oct. 2024, doi: 10.1007/s11263-024-02102-x.
T. Bayu Sasongko and A. Amrullah, “ANALISIS EFEK AUGMENTASI DATASET DAN FINE TUNE PADA ALGORITMA PRE-TRAINED CONVOLUTIONAL NEURAL NETWORK (CNN),” vol. 10, no. 4, pp. 763–768, 2023, doi: 10.25126/jtiik.2023106583.
L. N. Smith, “A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay,” Apr. 2018, [Online]. Available: http://arxiv.org/abs/1803.09820
E. Daniati, R. Firliana, A. Imron, and M. F. Aditiya Mufid, “ANALISIS DATA PENJUALAN PADA UMKM KONVEKSI MENGGUNAKAN METODE K-MEANS CLUSTERING DENGAN MENERAPKAN CRISP-DM,” Prosiding Seminar Nasional Teknologi dan Sistem Informasi, vol. 5, no. 1, 2025, doi: 10.33005/sitasi.v5i1.2542.
A. N. Fadhila, R. Firliana, and A. Ristyawan, “Monitoring Information System of Supplementary Feeding Program for Stunted Toddlers at Posyandu Matahari,” 2025.
Copyright (c) 2026 Sherla Mutia, Rina Firliana, Arie Nugroho
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
.png)
.png)
