YOLOv11-Based AIoT System for Automated Size Detection and Counting of G0 Seed Potatoes Using MQTT Protocol

Alvandi Fredik  Sembiring; Indah Permatasari; Prasetyo Yuliantoro

doi:10.32664/smatika.v16i02.2336

Penulis

Alvandi Fredik Sembiring Telkom University
Indah Permatasari Telkom University
Prasetyo Yuliantoro Telkom University

DOI:

https://doi.org/10.32664/smatika.v16i02.2336

Kata Kunci:

AIoT, G0 Seed Potato, Object Detection, YOLOv11

Abstrak

The increasing demand for G0 seed potatoes in Indonesia, reaching approximately 143,740 tons in 2021 while only 8.6% of the demand could be supplied, highlights the need for more efficient production and monitoring systems at the early stage of the potato seed supply chain. Current manual sorting and counting processes are labor-intensive, time-consuming, and prone to human error, creating a need for an automated and reliable monitoring solution. This study develops and implements an Artificial Intelligence of Things (AIoT) system based on the YOLOv11n object detection algorithm for real-time detection, size classification, and counting of G0 seed potatoes. The proposed system integrates a conveyor belt, a Logitech C922 Pro USB webcam for image acquisition, and a laptop as the edge computing unit running the YOLOv11n model. Detection results are transmitted through the MQTT protocol to a Node-RED dashboard for real-time remote monitoring. Unlike conventional approaches, the system combines a lightweight YOLOv11n model with MQTT communication to support simultaneous multi-category size classification and synchronized dashboard visualization. Detected potatoes are classified into three size categories (small, medium, and large) based on calibrated bounding-box pixel areas validated with potato farmers. The model was trained and evaluated using four epoch configurations (25, 50, 75, and 100 epochs) with Precision, Recall, F1-score, mAP@0.5, and mAP@0.5–0.95 as evaluation metrics. The 100-epoch model achieved the best performance, with precision approaching 1.00, recall of approximately 0.98, mAP@0.5 of 0.986, and mAP@0.5–0.95 of 0.96. Validation confirmed that calibrated geometric measurements matched the physical potato dimensions, while dashboard data were fully consistent with edge-computing outputs. These findings demonstrate that the proposed YOLOv11n-based AIoT system provides accurate, reliable, and real-time monitoring of G0 potato production, offering a practical solution to improve operational efficiency and data accuracy in Indonesia's potato seed supply chain.

Referensi

[1] FAO, World Food and Agriculture - Statistical Yearbook 2022. Rome, 2022. doi: 10.4060/cc2211en.

[2] Kurniawati, A. Nikmatullah, and Kisman, “Respon Pertumbuhan dan Hasil Empat Varietas Kentang Industri (Solanum tuberosum L.) pada Dua Musim Tanam Berbeda di Desa Sajang, Sembalun, Lombok Timur,” J. Ilm. Mhs. Agrokomplek, vol. 4, no. 1, pp. 112–117, 2025, doi: 10.29303/jima.v4i1.6229.

[3] R. Wardana, F. L. Afriansyah, and H. Oktafa, “Revitalization of the Potato Center through the Implementation of Smart Farming and Smart Agrology Systems in the Production Process and Development of Mashed Potato products in Bondowoso,” in 7th National Conference for Community Service (NaCosVi), Politeknik Negeri Jember, 2024, pp. 378–382.

[4] A. Sembiring, R. Murtiningsih, J. P. Sahat, and S. Hartanto, “GO potato aeroponic seed production in Indonesia, producers’ perception toward the benefits and challenges,” in IOP Conference Series: Earth and Environmental Science, IOP Publishing Ltd, 2021. doi: 10.1088/1755-1315/948/1/012086.

[5] S. Deras, “peningkatan efisiensi agribisnis kentang melalui introduksi bibit Granola 4 di Desa Bandar Hinalang Kecamatan Purba Kabupaten Simalungun,” J. Agriust, vol. 1, pp. 15–22, 2020, doi: 10.54367/agriust.v1i1.1023.

[6] B. L. Candradewani, S. Indriyanto, and I. Permatasari, “Sistem Monitoring Kelembapan Media Tanam Aglaonema SP Berbasis Internet of Things (IoT),” J. SINTA Sist. Inf. dan Teknol. Komputasi, vol. 2, no. 3, 2025, doi: 10.61124/sinta.v2i3.60.

[7] M. Geovanie, I. Ruslianto, and U. Ristian, “Sistem Pemantauan dan Kendali Tanaman Kentang Media Aeroponik Berbasis Internet of Things,” CESS (Journal Comput. Eng. Syst. Sci., vol. 8, no. 1, 2023, [Online]. Available: http://www.jurnal.unimed.ac.id

[8] M. S. Sharafat and others, “An IoT-enabled AI system for real-time crop prediction using soil and weather data in precision agriculture,” Smart Agric. Technol., vol. 12, p. 101263, 2025, doi: 10.1016/j.atech.2025.101263.

[9] W. Sun, X. Niu, Z. Wu, and Z. Guo, “Lightweight Detection Counting Method for Pill Boxes Based on Improved YOLOv8n,” Electronics, vol. 13, no. 24, p. 4953, 2024, doi: 10.3390/electronics13244953.

[10] J. Peng and others, “Towards toxic and narcotic medication detection with rotated object detectors,” Quant. Imaging Med. Surg., vol. 13, no. 4, pp. 2156–2166, 2023, doi: 10.21037/qims-21-1146.

[11] D. H. Saputra, B. Imran, and J. Juhartini, “object detection untuk mendeteksi citra buah buahan menggunakan metode yolo,” J. Kecerdasan Buatan dan Teknol. Inf., vol. 2, pp. 70–80, 2023, doi: 10.69916/jkbti.v2i2.18.

[12] L. Du, J. Li, W. Yang, W. Liu, X. Sun, and Y. Xia, “A SCG-YOLOv8n potato counting framework with efficient mobile deployment,” Sci. Rep., vol. 15, no. 1, p. 34909, 2025, doi: 10.1038/s41598-025-18754-9.

[13] A. M. Iqbal, J. Jumadi, and E. Nurlatifah, “Implementasi YOLOv8 Sebagai Pendeteksi Nominal Uang Rupiah Kertas Berbasis Android,” SMATIKA J., vol. 15, no. 02, pp. 268–277, 2025, doi: 10.32664/smatika.v15i02.1545.

[14] R. Li and others, “Maize Kernel Batch Counting System Based on YOLOv8-ByteTrack,” Sensors, vol. 25, no. 17, p. 5584, 2025, doi: 10.3390/s25175584.

[15] N. Ma, Y. Su, L. Lee, Z. Li, and H. Yan, “Wheat Seed Detection and Counting Method Based on Improved YOLOv8 Model,” Sensors, vol. 24, no. 5, p. 1654, 2024, doi: 10.3390/s24051654.

[16] S. M. Alhammad, D. S. Khafaga, W. M. El-hady, F. M. Samy, and K. M. Hosny, “Deep learning and explainable AI for classification of potato leaf diseases,” Front. Artif. Intell., vol. 7, pp. 1–9, 2025, doi: 10.3389/frai.2024.1449329.

[17] S. K. Jayasingh, P. Naik, S. Swain, K. J. Patra, and M. R. Kabat, “Integrated Crowd Counting System Utilizing IoT Sensors, OpenCV and YOLO Models for Accurate People Density Estimation in Real-Time Environments,” in 2024 1st International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU), IEEE, 2024, pp. 1–6. doi: 10.1109/IC-CGU58078.2024.10530804.

[18] S. Gunawan, A. E. Setiawan, and D. Feriyanto, “Design of Prototype Gourami Fry Counting System Based on Internet of Things (IoT) Using Infrared Sensor,” Int. J. Softw. Eng. Informatics, vol. 1, no. 1, pp. 40–48, 2023, [Online]. Available: https://journal.aisyahuniversity.ac.id/index.php/IJosei

[19] L. Gao, H. Cao, H. Zou, and H. Wu, “DMN-YOLO: A Robust YOLOv11 Model for Detecting Apple Leaf Diseases in Complex Field Conditions,” Agriculture, vol. 15, no. 11, p. 1138, May 2025, doi: 10.3390/agriculture15111138.

[20] Y. Liao, L. Li, H. Xiao, F. Xu, B. Shan, and H. Yin, “YOLO-MECD: Citrus Detection Algorithm Based on YOLOv11,” Agronomy, vol. 15, no. 3, p. 687, 2025, doi: 10.3390/agronomy15030687.

[21] I. Permatasari, N. A. F. Tanjung, and N. A. Zen, “Perancangan Sistem Monitoring Konduktivitas dan Padatan Terlarut PDAM Banyumas Berbasis IoT,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 10, no. 1, pp. 25–31, 2021, doi: 10.22146/jnteti.v10i1.1023.

[22] Y. Li, “An Enhanced YOLOv11 for Small-Object Detection in UAV Imagery,” in Proceedings of the 2025 8th International Conference on Computer Information Science and Artificial Intelligence, ACM, 2025, pp. 574–579. doi: 10.1145/3773365.3773458.

[23] R. Van Glabbeek, D. Deac, T. Perale, K. Steenhaut, and A. Braeken, “Flexible and Efficient Security Framework for Many-to-Many Communication in a Publish/Subscribe Architecture,” Sensors, vol. 22, no. 19, p. 7391, 2022, doi: 10.3390/s22197391.