PENGEMBANGAN SISTEM KENDALI PENGERINGAN PADI OTOMATIS BERBASIS MULTIMODAL DEEP LEARNING MENGGUNAKAN DATA SENSOR DAN CITRA VISUAL
Published 2025-08-28
How to Cite
Abstract
Abstract: Rice drying is a crucial post-harvest stage that affects the quality, shelf life, and economic value of rice. Conventional methods, such as sun drying and timer-based systems, are still predominantly used but are less adaptive to weather changes, often resulting in reduced product quality. This study developed an automated rice drying control system based on multimodal deep learning by integrating visual images and weather sensor data. The YOLOv5 model was used to detect grain conditions with 95% accuracy, while sensor analysis using LSTM and Transformer achieved accuracies of 90% and 93%, respectively. Multimodal integration improved control accuracy to 96% through an automatic roof opening/closing mechanism responsive to weather conditions and grain moisture status. Test results show that this system is more efficient than the baseline method, with an average drying time of 12 hours, moisture content accuracy of ±96%, and 30% lower yield loss. These findings highlight the potential of multimodal deep learning in supporting precision agriculture and modernizing post-harvest processes in Indonesia, while also opening opportunities for developing similar systems for other food commodities to support sustainable food security.
Â
Keywords: Rice Drying, Intelligent Control System, Multimodal Deep Learning, Sensor Data, Visual Imagery
Â
Abstrak: Pengeringan padi merupakan tahap krusial pascapanen yang memengaruhi mutu, daya simpan, dan nilai ekonomis gabah. Metode konvensional, seperti penjemuran matahari dan sistem berbasis timer, masih dominan digunakan namun kurang adaptif terhadap perubahan cuaca, sehingga sering menurunkan kualitas hasil. Penelitian ini mengembangkan sistem kendali pengeringan padi otomatis berbasis multimodal deep learning dengan mengintegrasikan citra visual dan data sensor cuaca. Model YOLOv5 digunakan untuk mendeteksi kondisi gabah dengan akurasi 95%, sedangkan analisis sensor menggunakan LSTM dan Transformer menghasilkan akurasi masing-masing 90% dan 93%. Integrasi multimodal meningkatkan akurasi kendali menjadi 96% melalui mekanisme buka–tutup atap otomatis yang responsif terhadap kondisi cuaca dan status kekeringan gabah. Hasil uji menunjukkan sistem ini lebih efisien dibandingkan metode baseline, dengan waktu pengeringan rata-rata 12 jam, akurasi kadar air ±96%, serta kehilangan hasil 30% lebih rendah. Temuan ini menegaskan potensi penerapan multimodal deep learning dalam mendukung pertanian presisi dan modernisasi proses pascapanen di Indonesia, sekaligus membuka peluang pengembangan sistem serupa pada komoditas pangan lain untuk mendukung ketahanan pangan berkelanjutan.
Â
Kata Kunci: Pengeringan Padi, Sistem Kendali Cerdas, Multimodal Deep Learning, Data Sensor, Citra Visual
Downloads
References
- H. Nurjannah, S. Nurjannah, and R. Kurniawan, "Design and Implementation of Smart Paddy Dryer using Arduino and IoT," IOP Conf. Ser.: Earth Environ. Sci., vol. 762, no. 1, p. 012048, 2021. [Online]. Available: https://doi.org/10.1088/1755-1315/762/1/012048.
- D. Kusnadi et al., "Evaluasi Kerugian Pascapanen Padi di Indonesia," J. Teknol. Pertan., vol. 24, no. 2, pp. 85–93, 2023.
- T. Nugraha et al., "Sistem Pengering Padi Otomatis dengan Mikrokontroler," J. Riset Elektro, vol. 9, no. 2, pp. 99–106, 2021.
- A. Purwanto and S. Widodo, "Efisiensi Proses Pascapanen Padi di Indonesia," J. Teknol. Pertan., vol. 25, no. 1, pp. 14–23, 2022.
- J. Chen et al., "A hybrid sensor-vision model for monitoring crop drying in real-time," Sensors Actuators B Chem., vol. 343, p. 130051, 2021. [Online]. Available: https://doi.org/10.1016/j.snb.2021.130051
- T. H. Nguyen et al., "Multimodal Deep Learning for Smart Agriculture: A Review," IEEE Access, vol. 10, pp. 124567–124590, 2022. [Online]. Available: https://doi.org/10.1109/ACCESS.2022.3147020
- A. Rahmat et al., "Pemanfaatan AI dalam Otomatisasi Proses Pascapanen," J. Agroind. Indones., vol. 10, no. 2, pp. 77–85, 2023.
- Z. Zhang, Y. Li, and Q. Zhao, "Rice Drying Prediction and Monitoring Based on IoT and Machine Learning," IEEE Access, vol. 9, pp. 113217–113229, 2021. [Online]. Available: https://doi.org/10.1109/ACCESS.2021.3105575
- J. Duan et al., "Multimodal Deep Learning for Smart Agriculture: A Review," Comput. Electron. Agric., vol. 203, p. 107456, 2023. [Online]. Available: https://doi.org/10.1016/j.compag.2022.107456
- J. Han et al., "Application of Multimodal Learning in Agricultural Crop Monitoring," Remote Sens., vol. 13, no. 5, p. 873, 2021. [Online]. Available: https://doi.org/10.3390/rs13050873
- A. Ramadhani and M. A. Sembiring, "Sistem Kendali Berbasis Machine Learning Menggunakan Model Naive Bayes pada Pengeringan Padi Otomatis," J. Sci. Soc. Res., vol. 5, no. 3, pp. 690–696, 2022.