Sistem Penyaring Beras Otomatis Berbasis ESP32 Menggunakan Random Forest Regression untuk Prediksi Efisiensi dan Kualitas Hasil Pembersihan Beras

Asniati Asniati, Ery Muchyar Hasiri, Mohamad Arif Suryawan, Jabal Nur

Abstract


Proses pembersihan beras secara manual masih menghadapi kendala dalam menjaga konsistensi kualitas dan efisiensi produksi. Sistem otomatis berbasis sensor yang ada umumnya hanya berfungsi untuk pemantauan tanpa kemampuan prediksi kuantitatif, sehingga diperlukan integrasi multi-sensor dan model prediktif pada perangkat keras berbiaya rendah. Penelitian ini bertujuan merancang dan mengevaluasi Sistem Penyaring Beras Otomatis berbasis ESP32 yang terintegrasi dengan algoritma Random Forest Regression (RFR) untuk memprediksi efisiensi pemisahan kotoran dan skor kualitas pembersihan secara simultan. Sistem memanfaatkan 20 fitur sensor yang berasal dari sensor LDR, sensor berat, DHT22, encoder RPM kipas, dan INA219. Dataset terdiri atas 3.000 rekaman, yaitu 600 data empiris hasil pengujian fisik pada rentang kapasitas 1–200 kg dan 2.400 data sintetik yang dihasilkan melalui augmentasi Gaussian Noise Injection. Data dibagi menjadi data latih dan data uji dengan rasio 80:20, kemudian dievaluasi menggunakan metrik koefisien determinasi (R²) dan Mean Absolute Error (MAE). Model menghasilkan R² = 0,7326 dan MAE = 2,067% untuk prediksi efisiensi, serta R² = 0,6825 dan MAE = 0,97 untuk prediksi kualitas. Pengujian fisik dilakukan pada kapasitas 1–200 kg, sedangkan kapasitas 201–1.000 kg dievaluasi menggunakan data sintetik hasil augmentasi. Keterbaruan penelitian terletak pada kemampuan memprediksi dua target numerik secara simultan dalam satu sistem berbasis ESP32 berbiaya rendah. Sistem berpotensi mendukung pengambilan keputusan otomatis untuk meningkatkan efisiensi dan kualitas pembersihan beras pada industri penggilingan padi skala kecil dan menengah.


Keywords


(ESP32; IoT Pertanian; Penyaring Beras Otomatis; Prediksi Efisiensi Pembersihan Beras; Random Forest Regression).

Full Text:

PDF

References


S. Andriani, A. Rakhman, and S. Suroso, “Design and Build Automatic Rice Winnowing and Weighing Equipment IoT (Internet of Things) Based,” JurnalEcotipe, vol. 9, no. 2, pp. 107–114, Sep. 2022, doi: 10.33019/jurnalecotipe.v9i2.3147.

N. A. Mohidem, N. Hashim, R. Shamsudin, and H. Che Man, “Rice for Food Security: Revisiting Its Production, Diversity, Rice Milling Process and Nutrient Content,” Agriculture, vol. 12, no. 6, p. 741, May 2022, doi: 10.3390/agriculture12060741.

C. A. Zurita, Z. Neuhofer, J. R. Díaz-Valderrama, D. Macedo-Valdivia, C. Woloshuk, and D. Baributsa, “Postharvest Rice Value Chain in Arequipa, Peru: Insights into Farmers’ Storage Decisions,” Agriculture, vol. 14, no. 11, p. 1886, Oct. 2024, doi: 10.3390/agriculture14111886.

W. Liu, S. Zeng, G. Wu, H. Li, and F. Chen, “Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model,” Sensors, vol. 21, no. 13, p. 4384, Jun. 2021, doi: 10.3390/s21134384.

A. Aznan, C. Gonzalez Viejo, A. Pang, and S. Fuentes, “Computer Vision and Machine Learning Analysis of Commercial Rice Grains: A Potential Digital Approach for Consumer Perception Studies,” Sensors, vol. 21, no. 19, p. 6354, Sep. 2021, doi: 10.3390/s21196354.

P. S. Sampaio, A. S. Almeida, and C. M. Brites, “Use of Artificial Neural Network Model for Rice Quality Prediction Based on Grain Physical Parameters,” Foods, vol. 10, no. 12, p. 3016, Dec. 2021, doi: 10.3390/foods10123016.

M. Yusuf, R. Ruimassa, A. I. Tawainella, and D. Maharani, “Klasifikasi Kualitas Beras Menggunakan Convolutional Neural Network Berbasis Android,” Jicon, vol. 12, no. 2, pp. 186–192, Oct. 2024, doi: 10.35508/jicon.v12i2.18004.

C. Kurade et al., “An Automated Image Processing Module for Quality Evaluation of Milled Rice,” Foods, vol. 12, no. 6, p. 1273, Mar. 2023, doi: 10.3390/foods12061273.

K. S. Rani, K. Swetha, K. A. Varshini, and G. Harika, “Rice Grain Quality Analysis Using Image Processing,” Int. J. Adv. Artif. Intell. Mach. Learn., vol. 2, no. 2, pp. 120–127, Jul. 2025, doi: 10.58723/ijaaiml.v2i2.455.

A. Budiarto and A. Izzuddin, "Rancang Bangun Timbangan Beras Digital Menggunakan Arduino Uno," Jurnal Ilmiah Teknologi dan Rekayasa, vol. 25, no. 2, pp. 112–121, 2020, doi: 10.35760/tr.2020.v25i2.2561.

M. Naim and A. Fasaldi, “Perancangan Alat Penimbang Beras Digital dengan Masukan Berat dan Harga Berbasis Mikrokontroler,” jmosfet, vol. 1, no. 2, pp. 14–17, Sep. 2021, doi: 10.31850/jmosfet.v1i2.1155.

S. S. Hidayat, D. Rahmawati, M. C. A. Prabowo, L. Triyono, and F. T. Putri, “Determining the Rice Seeds Quality Using Convolutional Neural Network,” JOIV : Int. J. Inform. Visualisation, vol. 7, no. 2, p. 527, Jun. 2023, doi: 10.30630/joiv.7.2.1175.

K. Anam, “Rancang Bangun Mesin Penjual Beras Berbasis Mikrokontroler Atmega16,” CYCLOTRON, vol. 4, no. 2, Aug. 2021, doi: 10.30651/cl.v4i2.7485.

L. De Oliveira Carneiro et al., “Characterising and Predicting the Quality of Milled Rice Grains Using Machine Learning Models,” AgriEngineering, vol. 5, no. 3, pp. 1196–1215, Jul. 2023, doi: 10.3390/agriengineering5030076.

A. Cartolano, A. Cuzzocrea, and G. Pilato, “Analysing and assessing explainable AI models for smart agriculture environments,” Multimedia Tools and Applications, vol. 83, no. 12, pp. 37225–37246, Apr. 2024, doi: 10.1007/s11042-023-17978-z.

K. Kiratiratanapruk et al., “Development of Paddy Rice Seed Classification Process using Machine Learning Techniques for Automatic Grading Machine,” Journal of Sensors, vol. 2020, pp. 1–14, Jul. 2020, doi: 10.1155/2020/7041310.

V. H. C. Putra, M. Al-Husaini, A. P. Wahyu, and A. R. Raharja, “Perancangan Sistem Monitoring Cerdas Berbasis Internet of Things (IoT) dengan Algoritma Random Forest Regression untuk Deteksi Ketinggian pada Tanaman Tomat Cherry,” MALCOM, vol. 5, no. 1, pp. 10–25, Nov. 2024, doi: 10.57152/malcom.v5i1.1612.

A. Kurniawan, R. T. A. Pohan, and I. Agustian, "Sistem Kendali Suhu Prototipe Mesin Pengering Biji Kopi Dengan Metode PID dan IOT Monitoring," Jurnal Amplifier: Jurnal Ilmiah Bidang Teknik Elektro dan Komputer, vol. 13, no. 1, pp. 10–17, 2023, doi: 10.33369/jamplifier.v13i1.27437.

L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.

A. Géron, Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed. Sebastopol, CA: O'Reilly Media, 2022.

P. Nuangpirom, S. Pitjamit, V. Jaikampan, C. Peerakam, W. Nakkiew, and P. Jewpanya, "Machine Learning on Low-Cost Edge Devices for Real-Time Water Quality Prediction in Tilapia Aquaculture," Sensors, vol. 25, no. 19, p. 6159, Oct. 2025, doi: 10.3390/s25196159.

A. Aznan, C. Gonzalez Viejo, A. Pang, and S. Fuentes, "Rapid Assessment of Rice Quality Traits Using Low-Cost Digital Technologies," Foods, vol. 11, no. 9, p. 1181, Apr. 2022, doi: 10.3390/foods11091181.

S. Suwonsichon, T. Suwonsichon, S. Kusolpalin, and S. Sudajan, "Enhancing Milled Rice Qualitative Classification with Machine Learning Techniques Using Morphological Features of Binary Images," Int. J. Food Prop., vol. 26, no. 1, pp. 2978–2992, Oct. 2023, doi: 10.1080/10942912.2023.2264533.

M. Arslan, M. Güzel, M. Demirci, and S. Özdemir, "SMOTE and Gaussian Noise Based Sensor Data Augmentation," in 2019 4th International Conference on Computer Science and Engineering (UBMK), Samsun, Turkey, Sep. 2019, pp. 458–462, doi: 10.1109/UBMK.2019.8907003.

G. I. Kim and K. Chung, "Extraction of Features for Time Series Classification Using Noise Injection," Sensors, vol. 24, no. 19, p. 6402, Oct. 2024, doi: 10.3390/s24196402.




DOI: https://doi.org/10.55340/jiu.v15i1.2689

Refbacks

  • There are currently no refbacks.


__________________________________________________________________________________________________________________________________________________

SK Accreditation No. 286/DST/C3/HM.01.00/2026 Tanggal 7 April 2026

Editorial Address :

Program Studi Teknik Informatika, Fakultas Teknik, Universitas Dayanu Ikhsanuddin Jl. Dayanu Ikhsanuddin no.124 Baubau, Sulawesi Tenggara 

Jurnal Informatika by Program Studi Teknik Informatika, Fakultas Teknik, Universitas Dayanu Ikhsanuddin Baubau, Indonesia is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Based on work at https://ejournal.unidayan.ac.id/index.php/JIU