Smart Inventory Management for Wastage and Losses in a Construction Company
Jose A. PEREZ JR., Joshua Martin A. PERALTA, Arvin F. EUGENIO, Armand Sebastian E. BUENO, Risty M. ACERADO
Abstract. Small and medium-sized construction enterprises often rely on manual inventory counting, which can lead to errors, material wastage, and operational inefficiencies. To address these challenges, this study developed a YOLOv5 object detection model for mobile-based smart inventory management system. A localized dataset of 671 images representing six construction material classes was collected from local hardware stores and construction sites in the Philippines and augmented to 6,000 images. The trained model achieved an average precision of 85.54%, a recall of 76.53%, an F1-score of 80.37%, an mAP@0.5 of 0.88, and an mAP@0.5:0.95 of 0.64. Thus, the system is accurate and efficient in managing the inventory of construction materials, thereby reducing manual errors, improving operational efficiency, and sustainable inventory management in the construction industry.
Keywords
PyTorch, Flutter, Construction Industry, Object Detection, Mobile Application
Published online 5/10/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Jose A. PEREZ JR., Joshua Martin A. PERALTA, Arvin F. EUGENIO, Armand Sebastian E. BUENO, Risty M. ACERADO, Smart Inventory Management for Wastage and Losses in a Construction Company, Materials Research Proceedings, Vol. 66, pp 326-333, 2026
DOI: https://doi.org/10.21741/9781644904152-30
The article was published as article 30 of the book Advanced Materials and Sustainable Energy Technologies
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Department of Trade and Industry (DTI), “DTI Strategic Plan 2023–2028: Transforming the Philippines through Inclusive, Innovative, and Digitally-driven Industries,” DTI, Manila, Philippines, 2023.
[2] Eurostat, “Digital economy and society statistics – enterprises,” Statistics Explained, 2024. [Online]. Available: https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Digital_economy_and_society_statistics_-_enterprises.
[3] Department of Trade and Industry (DTI), “Profile of the Philippine Construction Industry,” DTI, Manila, Philippines, 2023.
[4] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” 2018. [Online]. Available: https://pjreddie.com/media/files/papers/YOLOv3.pdf
[5] Ultralytics, “YOLOv8: State-of-the-art object detection,” Ultralytics, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics
[6] J. Wang, C. Liu, D. Chen, and Y. Zhang, “Real-time object counting with edge-AI for intelligent construction,” Automation in Construction, vol. 134, p. 104020, 2022. https://doi.org/10.1016/j.autcon.2021.104020.
[7] United Nations, “Sustainable Development Goals,” United Nations. [Online]. Available: https://sdgs.un.org/goals
[8] J. Qin, W. Yan, H. Lu, and J. Wang, “Enhancing object detection robustness through environment-diverse training datasets,” Sensors, vol. 24, no. 2, p. 315, 2024. https://doi.org/10.3390/s24020315.
[9] Y. Zhang, H. Wang, and D. Chen, “Real-time object detection on mobile devices using lightweight deep learning models,” IEEE Access, vol. 9, pp. 123456–123467, 2021.
[10] C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 60, 2019. https://doi.org/10.1186/s40537-019-0197-0.
[11] Roboflow, “Roboflow: Dataset annotation and management for computer vision,” Roboflow, 2023. [Online]. Available: https://roboflow.com
[12] G. Jocher et al., “YOLOv5,” Ultralytics, 2021. [Online]. Available: https://github.com/ultralytics/yolov5
[13] R. Padilla, S. L. Netto, and E. A. B. da Silva, “A survey on performance metrics for object detection algorithms,” International Journal of Computer Vision and Applications, vol. 11, no. 3, pp. 45–59, 2021. https://doi.org/10.1007/s41095-021-0231-4.
[14] A. Ajayi, L. Oyedele, O. Akinade, and M. Bilal, “Waste reduction through material management strategies in construction,” Resources, Conservation and Recycling, vol. 120, pp. 15–28, 2017. https://doi.org/10.1016/j.resconrec.2017.01.012.
[15] S. Sharma, K. Gulati, and S. Kumar, “Real-time object identification and tracking using OpenCV,” International Journal of Computer Science and Mobile Computing, vol. 10, no. 5, pp. 1-7, 2021.
[16] S. Matani, “PyTorch Mobile: Bringing machine learning to edge devices,” Towards Data Science, 2022. [Online]. Available: https://towardsdatascience.com/pytorch-mobile-bringing-machine-learning-to-edge-devices
