YOLO Vision-Sensor Hybrid Approach for Automated Nutrient Actuation in Smart Greenhouse Melons
DOI:
https://doi.org/10.47709/brilliance.v6i4.9639Keywords:
Hydroponic Melon, Nutrition Pump, PH Sensor, TDS Sensor, Yolo ModelAbstract
Cultivating hydroponic melons requires precise nutrient management to avoid crop failure. While farmers traditionally rely on visual inspections, this manual approach is subjective and prone to human error. Conversely, relying solely on single-source automated systems—using either cameras or water sensors alone—often causes incorrect automated actions in dynamic greenhouse environments. To bridge this gap, this study introduces RANUM, a smart agriculture system combining advanced edge AI with reliable hardware actuation. The Raspberry Pi 5 is used as the master controller for processing visual data, while the ESP32 serves as the microcontroller to execute the pump actuation logic, RANUM acts as both the eyes and the brain of the greenhouse. The AI was trained on a real-world dataset of 1,000 images, utilizing the optimal "best.pt" checkpoint to maintain continuous accuracy and prevent overfitting. During field tests, the hardware demonstrated exceptional precision, recording minimal average errors of just 0.021 for pH and 1.11 ppm (0.13%) for Total Dissolved Solids (TDS). What makes RANUM truly unique is its hybrid cross-validation approach. Using a strict AND logic protocol, the system takes action only if the visual AI detects a leaf anomaly and the physical sensors confirm a nutrient imbalance. This dual-check mechanism successfully filters out visual false positives. In integration testing, this architecture achieved 100% decision-making accuracy, completely preventing premature triggers for the AB Mix and pH dosing pumps. Supported by an interactive real-time web dashboard, this multimodal framework eliminates technical noise, offering modern farmers a highly reliable and accurate smart agriculture solution.
References
Abiri, R., Rizan, N., Balasundram, S. K., Shahbazi, A. B., & Abdul-Hamid, H. (2023). Application of digital technologies for ensuring agricultural productivity. Heliyon, 9(12).
Agustina, N. Q., Susetyoko, R., Trisniani, W., & Anggraini, S. (2025). Real-Time Monitoring and TDS Forecasting in Smart Hydroponic Melon Cultivation Using SES and LSTM Methods. 2025 International Electronics Symposium (IES), 515–520. IEEE.
Bell, R. (2023). Diagnosis and prediction of deficiency and toxicity of nutrients. In Marschner’s mineral nutrition of plants (pp. 477–495). Elsevier.
Chandel, N. S., Chakraborty, S. K., Jat, D., & Chouhan, P. (2024). Smart farming management system: Pre and post-production interventions. In Artificial Intelligence Techniques in Smart Agriculture (pp. 67–82). Springer.
Chutichaimaytar, P., Zongqi, Z., Kaewtrakulpong, K., & Ahamed, T. (2025). An improved small object detection CTB-YOLO model for early detection of tip-burn and powdery mildew symptoms in coriander (Coriandrum sativum) for indoor environment using an edge device. Smart Agricultural Technology, 12, 101142.
Dhavale, M. C., Aiwale, H. N., & Sarnobat, D. H. (2025). Modern diagnostic techniques in plant pathology. Plant Health and Disease Management: A Modern Approach, 184.
Ghimirey, V., Chaurasia, J., & Marahatta, S. (2024). Plant nutrition disorders: insights from clinic analyses and their impact on plant health. Agriculture Extension in Developing Countries, 2(1), 9–17.
Hu, H., Qu, Z., Liu, Y., Zhu, L., Mei, Z., & Chen, X.-L. (2026). AI-driven fungicide design: From target identification to field application. Plant Communications, 7(5).
Jaramillo-Alcazar, A., Govea, J., & Villegas-Ch, W. (2023). Anomaly detection in a smart industrial machinery plant using IoT and machine learning. Sensors, 23(19), 8286.
Karimzadeh, S., Li, Z., & Ahamed, M. S. (2025). Machine learning-based fault detection and diagnosis of electrical conductivity and pH sensors in hydroponic systems. Computers and Electronics in Agriculture, 237, 110544.
Kumari, S., Pandey, G. K., & Tiwari, S. (2024). Data visualization techniques in smart agriculture implementation. In AI Applications for Business, Medical, and Agricultural Sustainability (pp. 122–159). IGI Global Scientific Publishing.
Lakhiar, I. A., Yan, H., Zhang, C., Wang, G., He, B., Hao, B., … Syed, T. N. (2024). A review of precision irrigation water-saving technology under changing climate for enhancing water use efficiency, crop yield, and environmental footprints. Agriculture, 14(7), 1141.
Loredo-Treviño, A., Gómez-García, R., Guía-García, J. L., Campos, D. A., Dávila-Rangel, I. E., Belmares-Cerda, R. E., & Flores-López, M. L. (2026). Unlocking Potential Perspectives of Cucumis melo L. Fruit: Development of Bio-Functional Food Ingredients for Sustainability and Health Benefits. Processes, Vol. 14, p. 1105. https://doi.org/10.3390/pr14071105
Maqbool, M. S., Nazeer, R., Basit, A., & Zahra, K. (2023). Automated detection and localization of fungal infections on cotton leaves using YOLO-based object detection model. Machines and Algorithms, 2(2), 121–136.
Phankaen, P., & Kumpanuch, W. (2025). Yield and fruit quality of four melon varieties cultivated using the deep flow technique hydroponic system. ASEAN Journal of Scientific and Technological Reports, 28(3), e256961–e256961.
Preanto, S. A., Ahad, M. T., Emon, Y. R., Mustofa, S., & Alamin, M. (2024). A semantic segmentation approach on sweet orange leaf diseases detection utilizing YOLO. ArXiv Preprint ArXiv:2409.06671.
Sadik, M., Abdelhadi, E., Youssef, M., Houda, O., & Samir, E. (2026). Smart Greenhouses in the Era of IoT and AI: A Comprehensive Review of AI Applications, Spectral Sensing, Multimodal Data Fusion, and Intelligent Systems. Agriculture, 16(7), 761.
Shafay, M., Hassan, T., Owais, M., Hussain, I., Khawaja, S. G., Seneviratne, L., & Werghi, N. (2025). Recent advances in plant disease detection: challenges and opportunities. Plant Methods, 21(1), 140.
Sood, T., Kapoor, S., Kaur, J., Hussain, N., & Sood, S. (2025). Fertigation: a paradigm shift in nutrient delivery for sustainable agriculture. In Agricultural nutrient pollution and climate change: Challenges and Opportunities (pp. 135–164). Springer.
Subeesh, A., Chauhan, N., & Kushwaha, N. L. (2025). Integrating IoT With Machine Learning and Deep Learning Models for Precision Soil?Less Agriculture: A Review. Artificial Intelligence for Engineering, 1(2), 137–164.
Sugeru, H., Wibowo, E. P., Musa, P., Harahap, R. K., & Harmanto, S. (2025). Integrating IoT and Machine Learning for Real-Time Soil-Based Crop and Fertilizer Recommendations: The UG-AgroPlan System.
Wirasena, A. F., Fakhrurroja, H., & Pramesti, D. (2025). Back-End Development of an Interactive Dashboard with Real-Time API Integration for Chili Plant Monitoring in Precision Agriculture. JURNAL TEKNIK INFORMATIKA, 18(2), 236–247.
Yang, H., Jin, Y., Jiang, L., Lu, J., & Wen, G. (2025). AI roles in 4R crop pest management—A review. Agronomy, 15(7), 1629.
Yang, T., Peng, B., Zhang, J., Zhang, D., Liang, C., & Fan, X. (2026). Optimizing seed anomaly detection in agricultural automation via lightweight ASD-YOLO and closed-loop control. Computers and Electronics in Agriculture, 243, 111342.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Sutra Wardatul Jannah, Eva Jamiyanti, Amalia Herlina, Febby Ayu Salsabilla
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
