Prototype of an Intelligent Monitoring System for Real-Time Detection of Suspicious Objects and Activities Using Deep Learning

Authors

  • Lauro Alfonso Erreyes Cuenca Universidad Técnica de Machala, Facultad de Ingeniería Civil, Carrera de Tecnologías de la Información, Machala, El Oro, Ecuador. https://orcid.org/0009-0002-6552-4537
  • Nahin Josue Olmedo Chica Universidad Técnica de Machala, Facultad de Ingeniería Civil, Carrera de Tecnologías de la Información, Machala, El Oro, Ecuador. https://orcid.org/0009-0004-5555-2977
  • Mariuxi Paola Zea Ordóñez Universidad Técnica de Machala, Facultad de Ingeniería Civil, Carrera de Tecnologías de la Información, Machala, El Oro, Ecuador. https://orcid.org/0000-0001-8860-6282
  • Nancy Magaly Loja Mora Universidad Técnica de Machala, Facultad de Ingeniería Civil, Carrera de Tecnologías de la Información, Machala, El Oro, Ecuador. https://orcid.org/0000-0002-5583-4278

DOI:

https://doi.org/10.33936/isrtic.v9i2.7908

Keywords:

artificial intelligence, deep learning, YOLOv8, video surveillance

Abstract

This research addresses the need to optimize video surveillance systems through the use of artificial intelligence to proactively detect threats. The primary goal is to develop an intelligent monitoring prototype capable of detecting people, weapons, and suspicious behavior in real time, focusing on computational efficiency and detection accuracy to ensure its feasibility on readily available hardware. The CRISP-DM methodology was used to achieve this goal, systematically dividing the project into stages that included data preparation, modeling, and evaluation. A YOLOv8 model is the core element of the system, trained on a custom dataset of approximately 8,500 images and expanded using various methods. The model's robustness is confirmed by quantitative results, which show an F1 score of 93.99% and a mean accuracy (mAP) of 96.97% in the specified classes. Finally, the model was incorporated into a functional video surveillance prototype, demonstrating its usefulness and operational effectiveness in urban and commercial security environments.

Downloads

Download data is not yet available.

References

Acuña-Cid, H. A., Ahumada-Tello, E., Ovalle-Osuna, Ó. O., Evans, R., Hernández-Ríos, J. E., & Zambrano-Soto, M. A. (2025). CRISP-NET: Integration of the CRISP-DM Model with Network Analysis. Machine Learning and Knowledge Extraction, 7(3), 101. https://doi.org/10.3390/make7030101

Alvarado, H. P. L., & Villavicencio, O. E. C. (2024). Regulación del Manejo de la Inteligencia Artificial, Consecuencias y Daños a la Sociedad por su Mal Uso. Ciencia Latina Revista Científica Multidisciplinar, 8(1), 1966–1978. https://doi.org/10.37811/cl_rcm.v8i1.9596

Azatbekuly, N., Mukhanbet, A., & Bekele, S. D. (2024). Development of an Intelligent Video Surveillance System Based on YOLO Algorithm. 2024 IEEE 4th International Conference on Smart Information Systems and Technologies (SIST), 498–503. https://doi.org/10.1109/SIST61555.2024.10629617

Castro-Paredes, J. G., Mendoza-Masache, G. R., Loja-Mora, N. M., & Loján-Alvarado, H. P. (2025). Protección de datos por diseño y por defecto. Implicaciones legales en el desarrollo de software. Ingenium et Potentia, 7(12), 77–96. https://doi.org/10.35381/i.p.v7i12.4471

Cheng, G., Chao, P., Yang, J., & Ding, H. (2024). SGST-YOLOv8: An Improved Lightweight YOLOv8 for Real-Time Target Detection for Campus Surveillance. Applied Sciences, 14(12), 5341. https://doi.org/10.3390/app14125341

Delwar, T. S., Mukhopadhyay, S., Kumar, A., Singh, M., Lee, Y., Ryu, J.-Y., & Hosen, A. S. M. S. (2025). Real-Time Farm Surveillance Using IoT and YOLOv8 for Animal Intrusion Detection. Future Internet, 17(2), 70. https://doi.org/10.3390/fi17020070

Erreyes, L. (2025). Dataset Detección personas-armas-personas armadas. Zenodo. https://doi.org/10.5281/zenodo.17215185

Espinoza, L. J. M., Rojas, S. J. Z., Bravo, V. J. P., & Valarezo, L. C. C. (2025). Balanceo de Conjuntos de Datos Basado en Redes Generativas Aplicado a Imágenes del Sector Agrícola. Informática y Sistemas, 9(2), 164–176. https://doi.org/10.33936/isrtic.v9i2.7782

Gawande, U., Hajari, K., & Golhar, Y. (2024). Novel person detection and suspicious activity recognition using enhanced YOLOv5 and motion feature map. Artificial Intelligence Review, 57(2), 16. https://doi.org/10.1007/s10462-023-10630-0

Hua, C., Luo, K., Wu, Y., & Shi, R. (2024). YOLO-ABD: A Multi-Scale Detection Model for Pedestrian Anomaly Behavior Detection. Symmetry, 16(8), 1003. https://doi.org/10.3390/sym16081003

Li, Y., Li, Q., Pan, J., Zhou, Y., Zhu, H., Wei, H., & Liu, C. (2024). SOD-YOLO: Small-Object-Detection Algorithm Based on Improved YOLOv8 for UAV Images. Remote Sensing, 16(16), 3057. https://doi.org/10.3390/rs16163057

Nasir, R., Jalil, Z., Nasir, M., Alsubait, T., Ashraf, M., & Saleem, S. (2025). An enhanced framework for real-time dense crowd abnormal behavior detection using YOLOv8. Artificial Intelligence Review, 58(7), 202. https://doi.org/10.1007/s10462-025-11206-w

Ni, Y., Huo, J., Hou, Y., Wang, J., & Guo, P. (2024). Detection of Underground Dangerous Area Based on Improving YOLOV8. Electronics, 13(3), 623. https://doi.org/10.3390/electronics13030623

Schcolnik-Elias, A., Martínez-Díaz, S., Luna-Taylor, J. E., & Castro-Liera, I. (2023). Detección de armas tipo pistola mediante el uso de redes convolucionales con una arquitectura tipo YOLO y estereoscopía. Pädi Boletín Científico de Ciencias Básicas e Ingenierías del ICBI, 11, 196–204. https://doi.org/10.29057/icbi.v11iEspecial2.10727

Stainer, M. J., Raj, P. V, Aitken, B. M., Bandarian-Balooch, S., & Boschen, M. J. (2021). Decision-making in single and multiple-screen CCTV surveillance. Applied Ergonomics, 93, 103383. https://doi.org/10.1016/j.apergo.2021.103383

Sudharson, D., Srinithi, J., Akshara, S., Abhirami, K., Sriharshitha, P., & Priyanka, K. (2023). Proactive Headcount and Suspicious Activity Detection using YOLOv8. Procedia Computer Science, 230, 61–69. https://doi.org/10.1016/j.procs.2023.12.061

Downloads

Published

2025-11-19

How to Cite

[1]
Erreyes Cuenca, L.A., Olmedo Chica, N.J., Zea Ordóñez, M.P. and Loja Mora, N.M. 2025. Prototype of an Intelligent Monitoring System for Real-Time Detection of Suspicious Objects and Activities Using Deep Learning . Informática y Sistemas. 9, 2 (Nov. 2025), 197–213. DOI:https://doi.org/10.33936/isrtic.v9i2.7908.

Issue

Vol. 9 No. 2: July - December (2025)

Section

Regular Papers

License

Copyright (c) 2025 Lauro Alfonso Erreyes Cuenca, Nahin Josue Olmedo Chica, Mariuxi Paola Zea Ordóñez, Nancy Magaly Loja Mora

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles submitted to this journal for publication will be released for open access under a Creative Commons Attribution Non-Commercial No Derivative Works licence (http://creativecommons.org/licenses/by-nc-nd/4.0).

The authors retain copyright, and are therefore free to share, copy, distribute, perform and publicly communicate the work under the following conditions: Acknowledge credit for the work specified by the author and indicate if changes were made (you may do so in any reasonable way, but not in a way that suggests that the author endorses your use of his or her work. Do not use the work for commercial purposes. In case of remixing, transformation or development, the modified material may not be distributed.