Development of a Portable Low-Cost Multispectral Sensor Integrated with IoT and Machine Learning for Classifying Honey Types

Informasi Publikasi

#

Abstrak Resmi (Official Abstract)

#

“Accurate honey type authentication is a significant challenge for small-scale producers, as conventional methods are often costly and impractical. This study aims to design and develop a low-cost honey classification prototype by integrating the AS7265X multispectral sensor with Internet of Things (IoT) technology and machine learning. Spectral data from 18 channels of various Indonesian honey types were acquired using the AS7265X sensor and analyzed exploratively using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). The data were then normalized and used to train Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM) classification models. An ESP32-based IoT system was developed for real-time monitoring and cloud data storage. The results demonstrate that AS7265X spectral data effectively differentiate honey types, with the ANN model achieving 94.05% accuracy, supported by a responsive IoT system (1–2 seconds) for monitoring and centralized storage. This prototype shows potential as a practical, rapid, accurate, and efficient honey authentication solution for various stakeholders.”

Terjemahan Abstrak:

#

Autentikasi jenis madu yang akurat merupakan tantangan signifikan bagi produsen skala kecil, karena metode konvensional seringkali mahal dan tidak praktis. Penelitian ini bertujuan untuk merancang dan mengembangkan prototipe klasifikasi madu berbiaya rendah (low-cost) dengan mengintegrasikan sensor multispektral AS7265X, teknologi Internet of Things (IoT), dan Machine Learning. Data spektral dari 18 kanal berbagai jenis madu Indonesia diakuisisi menggunakan sensor AS7265X dan dianalisis secara eksploratif menggunakan Principal Component Analysis (PCA) dan Linear Discriminant Analysis (LDA). Data kemudian dinormalisasi dan digunakan untuk melatih model klasifikasi Artificial Neural Network (ANN), Random Forest (RF), dan Support Vector Machine (SVM). Sistem IoT berbasis ESP32 dikembangkan untuk pemantauan waktu nyata dan penyimpanan data di cloud. Hasil menunjukkan bahwa data spektral AS7265X secara efektif membedakan jenis madu, dengan model ANN mencapai akurasi 94,05%, didukung oleh sistem IoT yang responsif (1–2 detik) untuk pemantauan dan penyimpanan terpusat. Prototipe ini berpotensi sebagai solusi autentikasi madu yang praktis, cepat, akurat, dan efisien bagi berbagai pemangku kepentingan.

Kata Kunci (Keywords): AS7265X Sensor, Honey classification, Internet of Things, Machine Learning, Spectroscopy.

Spesifikasi & Performa Teknis

#

• Perangkat Keras Sensor: Sensor Optik Multispektral 18-Kanal AS7265X (mencakup pita UV, Visible, dan Near-Infrared / NIR).
• Mikrokontroler & IoT: Mikrokontroler ESP32 dengan telemetri nirkabel waktu nyata (latensi respons 1–2 detik) serta penyimpanan data cloud terpusat.
• Analisis Data Eksploratif: Reduksi dimensi dan analisis pemisahan kelas menggunakan PCA dan LDA.
• Algoritma Klasifikasi: Evaluasi perbandingan model Artificial Neural Network (ANN), Random Forest (RF), dan Support Vector Machine (SVM).
• Akurasi Tertinggi: Model Artificial Neural Network (ANN) mencatatkan akurasi klasifikasi tertinggi sebesar 94,05%.

Kutipan (Citation)

#

@article{Muhammad2025Honey,
  author  = {Muhammad, Riki and Isroni and Wisesa, T. P. and Syahputra, T. S.},
  title   = {Development of a Portable Low-Cost Multispectral Sensor Integrated with IoT and Machine Learning for Classifying Honey Types},
  journal = {Journal of Energy, Material, and Instrumentation Technology},
  volume  = {6},
  number  = {3},
  pages   = {143--153},
  year    = {2025},
  doi     = {10.23960/jemit.343},
  url     = {https://doi.org/10.23960/jemit.343}
}