Klasifikasi Kelembapan Tanah Berbasis Data Sensor IoT Menggunakan Support Vector Machine (SVM)

KHOTIBUL UMAM; RONY HARIANTO

doi:10.26760/mindjournal.v10i2.250-260

Klasifikasi Kelembapan Tanah Berbasis Data Sensor IoT Menggunakan Support Vector Machine (SVM)

KHOTIBUL UMAM, RONY HARIANTO

Sari

Abstrak
Penerapan teknologi Internet of Things (IoT) dalam pertanian presisi menawarkan peluang signifikan untuk meningkatkan literasi ilmiah sekaligus efisiensi penggunaan sumber daya. Penelitian ini bertujuan mengembangkan sistem klasifikasi kebutuhan penyiraman tanaman berbasis data sensor IoT dengan algoritma Support Vector Machine (SVM). Sistem dirancang menggunakan sensor suhu dan kelembapan (DHT11) serta sensor kelembapan tanah yang dihubungkan dengan mikrokontroler ESP8266. Data dikirim secara berkala ke platform digital dan dianalisis menggunakan metode pembelajaran mesin. Evaluasi kinerja dilakukan melalui metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa SVM dengan kernel Radial Basis Function (RBF) mampu mencapai akurasi hingga 97%. Temuan ini membuktikan bahwa integrasi IoT dapat meningkatkan efisiensi pertanian presisi.

Kata kunci: IoT, klasifikasi, Support Vector Machine, machine learning, pertanian presisi

Abstract
The application of Internet of Things (IoT) technology in precision agriculture offers significant opportunities to improve scientific literacy and resource use efficiency. This study aims to develop a system for classifying plant watering needs based on IoT sensor data using the Support Vector Machine (SVM) algorithm. The system is designed using temperature and humidity sensors (DHT11) and soil moisture sensors connected to an ESP8266 microcontroller. Data is sent periodically to a digital platform and analyzed using machine learning methods. Performance evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results showed that SVM with Radial Basis Function (RBF) kernel was able to achieve an accuracy of up to 97%. These findings prove that IoT integration can improve precision agriculture efficiency.
Keywords: IoT, classification, Support Vector Machines, machine learning, precision agriculture

Teks Lengkap:

PDF

Referensi

Aldila Cinderatama, T., Zulmy Alhamri, R., Yunhasnawa, Y., Sofian Efendi, F., & Ariyanto, R. (2025). JIP (Jurnal Informatika Polinema) Halaman| SISTEM MONITORING IRIGASI DAN PREDIKSI DEBIT AIR BERBASIS IOT DAN SUPPORT VECTOR MACHINE(SVM). JIP (Jurnal Informatika Polinema), 11(2), 171–183.

Angellina, A., Herwindiati, D. E., & Hendryli, J. (2023). Performa Support Vector Machine Pada Klasifikasi Lahan dan Air Tanah. Jurnal Media Informatika Budidarma, 7(1), 231. https://doi.org/10.30865/mib.v7i1.5279

Diva Putra Romadan et al. (2025). Prototype of Soil Moisture Monitoring System for Chili Plants Based on Internet of Things Using Fuzzy Logic Method with NodeMCU ESP8266 , Blynk , and ThingSpeak Prototipe Sistem Monitoring Kelembapan Tanah pada Tanaman Cabai Berbasis Internet of Things de. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(January), 130–140.

Frenica, A., Lindawati, L., Lindawati, L., Soim, S., & Soim, S. (2023). Implementasi Algoritma Support Vector Machine (SVM) untuk Deteksi Banjir. INOVTEK Polbeng - Seri Informatika, 8(2), 291. https://doi.org/10.35314/isi.v8i2.3443

Gultom, A. S., Furqon, M. T., & Sutrisno, S. (2021). Klasifikasi Masa Panen Varietas Unggul Kedelai menggunakan Support Vector Machine (SVM). Jurnal Pengembangan Teknologi Informasi Dan …, 5(12), 5272–5277.

Huang, Y. (2023). Improved SVM-Based Soil-Moisture-Content Prediction Model for Tea Plantation. Plants, 12(12). https://doi.org/10.3390/plants12122309

M, D., S, G., & R, V. (2025). Climate Change, Land Degradation and Sustainability: Insight towards Innovative Solutions from Indian Perspective. Current Research on Geography, Earth Science and Environment Vol. 1, August, 105–120. https://doi.org/10.9734/bpi/crgese/v1/5649

Nurhaliza. (2025). Perancangan Sistem Irigasi Otomatis Berbasis Iot Untuk Optimalisasi Penggunaan Air Pada Lahan Pertanian Kering. Jurnal Teknik Indonesia, 3(April), 129–137.

Saputri, F. R., Linelson, R., Salehuddin, M., Nor, D. M., & Ahmad, M. I. (2025). Erratum: Correction: Design and development of an irrigation monitoring and control system based on blynk internet of things and thingspeak (PloS one (2025) 20 4 DOI: 10.1371/journal.pone.0321250.). PloS One, 20(6), e0326137. https://doi.org/10.1371/journal.pone.0326137

Septiadi, A. D., Sulistya, Y. I., Istighosah, M., Septiara, M., Rakhmadani, D. P., & Rumestri, A. D. S. (2025). Implementasi IoT Untuk Monitoring Pertumbuhan Tanaman Cabai Dengan Sistem Penyiraman Otomatis Di Desa Kembaran Wetan. KREATIF: Jurnal Pengabdian Masyarakat Nusantara, 5(2), 455–468. https://doi.org/10.55606/kreatif.v5i2.6901

Setiawan, I., Fina Antika Cahyani, R., & Sadida, I. (2023). Exploring Complex Decision Trees: Unveiling Data Patterns and Optimal Predictive Power. Journal of Innovation And Future Technology (IFTECH), 5(2), 112–123. https://doi.org/10.47080/iftech.v5i2.2829

Speak, T. (2024). Iot-Based Smart Monitoring Systems for Agricultural Efficiency. 21(2), 855–860. https://doi.org/10.48047/NQ.2023.21.2.NQ23085

Sumarudin, A., Ismantohadi, E., Puspaningrum, A., Maulana, S., & Nadi, M. (2021). Implementation irrigation system using Support Vector Machine for precision agriculture based on IoT. IOP Conference Series: Materials Science and Engineering, 1098(3), 032098. https://doi.org/10.1088/1757-899x/1098/3/032098

Ula, M., Ezwarsyah, E., Saptari, M. A., Bakhtiar, B., & Multazam, T. (2025). System monitoring Soil PH moisture based IoT. Brilliance: Research of Artificial Intelligence, 5(1), 169–174. https://doi.org/10.47709/brilliance.v5i1.5974

Wahyudi, W., Pradana, A. I., & Permatasari, H. (2025). Implementasi Sistem Irigasi Otomatis Berbasis IoT untuk Pertanian Greenhouse. Jurnal Pendidikan Dan Teknologi Indonesia, 5(2), 435–446. https://doi.org/10.52436/1.jpti.656

DOI: https://doi.org/10.26760/mindjournal.v10i2.250-260