Geographical Indication Classification Based on Stingless Bee Honey Samples Using a Generative Model on Spectral Data for Mobile Device Applications

Hata Maulana; Yohanes Aris Purwanto; Diding Suhandy; Sony Hartono Wijaya; Heru Sukoco

doi:10.15408/jti.v19i1.49280

Authors

Hata Maulana Computer Science, School of Science, Mathematics and Informatics, Institute Pertanian Bogor University
Yohanes Aris Purwanto Mechanical and Biosystems Engineering, Faculty of Agricultural Technology, Institute Pertanian Bogor University
Diding Suhandy Agricultural Engineering, Faculty of Agricultural, The University of Lampung
Sony Hartono Wijaya Computer Science, School of Science, Mathematics and Informatics, Institute Pertanian Bogor University
Heru Sukoco Computer Science, School of Science, Mathematics and Informatics, Institute Pertanian Bogor University

DOI:

https://doi.org/10.15408/jti.v19i1.49280

Keywords:

Stingless Bee, Honey, Spectrum, Fluorescence, Machine Learning

Abstract

Stingless bee honey (SBH) is a food product with a simple and fast production process. Honey production is highly dependent on the condition and ability of the bees. Each region in Indonesia has different botanical and environmental conditions, with different entomological characteristics of bee species based on their geographical origin. This honey classification model is part of the formation of Geographical Indications (GI) based on product characteristics. A generative model is used in the pre-processing stage to produce spectrum data with the best grouping (silhouette score > 0.6). The main process discussed in this article is the application of GI classification model of four types of stingless bee honey based on cultivation location. The results of the study with a 400x745 dataset and 4 classes (Lampung, Bogor, Sukabumi, and Rangkas Bitung) showed that the classification model produced an accuracy above 95% with a precision and recall above 0.99. The SBH GI classification application has been successfully built using the scrum methodology and is cloud-based. The application displays the classification results of origin, type (entomological), feed dominance (botanical) and dominant spectrum values. The application has also been tested for feasibility based on the User Acceptance Test with results above 90%.

References

[1] G. Chen, Y. Huang, and K. Chen, “Recent advances and applications of near infrared spectroscopy for honey quality assessment,” Adv. J. Food Sci. Technol., vol. 6, no. 4, pp. 461–467, 2014, doi: 10.19026/ajfst.6.55.

[2] N. A. S. Suarin, K. S. Chia, and F. N. Kosmani, “Stingless Bee Honey Classification Using near Infrared Light Coupled with Artificial Neural Network,” 2020 Zooming Innov. Consum. Technol. Conf. ZINC 2020, pp. 99–102, 2020, doi: 10.1109/ZINC50678.2020.9161785.

[3] A. Aziz, “FULL PAPER Adulterated stingless bee honey identification using VIS - NIR spectroscopy,” vol. 5, pp. 85–93, 2021.

[4] H. A. Hidalgo, A. R. Nicolas, and R. Cedon, “Development barriers of stingless bee honey industry in Bicol, Philippines,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 10, no. 3, pp. 1245–1251, 2020, doi: 10.18517/ijaseit.10.3.4747.

[5] A. Hassoun, I. Måge, W. F. Schmidt, H. T. Temiz, and L. Li, “Fraud in Animal Origin Food Products: Advances in Emerging Spectroscopic Detection Methods over the Past Five Years,” Foods, vol. 9, pp. 1–41, 2020, doi: doi:10.3390/foods9081069.

[6] M. Yulia and D. Suhandy, “Authentication of organic Lampung robusta ground roasted coffee by UV-visible spectroscopy and PLS-DA method,” J. Phys. Conf. Ser., vol. 1341, no. 2, 2019, doi: 10.1088/1742-6596/1341/2/022006.

[7] D. Hou, S. Liu, J. Zhang, F. Chen, P. Huang, and G. Zhang, “Online monitoring of water-quality anomaly in water distribution systems based on probabilistic principal component analysis by UV-vis absorption spectroscopy,” J. Spectrosc., vol. 2014, 2014, doi: 10.1155/2014/150636.

[8] I. E. Bell and G. V. G. Baranoski, “Reducing the dimensionality of plant spectral databases,” IEEE Trans. Geosci. Remote Sens., vol. 42, no. 3, pp. 570–576, 2004, doi: 10.1109/TGRS.2003.821697.

[9] Y. Zhu, S. Zhao, Y. Zhang, C. Zhang, and J. Wu, “A Review of Statistical-Based Fault Detection and Diagnosis with Probabilistic Models,” Symmetry (Basel)., vol. 16, no. 4, pp. 1–23, 2024, doi: 10.3390/sym16040455.

[10] Y. A. Purwanto, H. Maulana, S. Hartono W, H. Sukoco, and Diding Suhandy, “Cloud-Based Predictive Mobile Application for Assessing Honey Purity From Stingless Bees,” J. Ilm. Kursor, vol. 12, no. 4, pp. 191–200, Dec. 2024, doi: 10.21107/kursor.v12i4.420.

[11] M. J. Aliaño-González, M. Ferreiro-González, E. Espada-Bellido, M. Palma, and G. F. Barbero, “A screening method based on Visible-NIR spectroscopy for the identification and quantification of different adulterants in high-quality honey,” Talanta, vol. 203, pp. 235–241, 2019, doi: 10.1016/j.talanta.2019.05.067.

[12] A. Pribadi and M. D. E. Wiratmoko, “Karakteristik Fisikokimia Madu Heterotrigona itama Asal Provinsi Riau,” Wahana For. J. Kehutan., vol. 18, no. 2, pp. 13–28, 2023, doi: 10.31849/forestra.v18i2.11107.

[13] L. Neelu and D. Kavitha, “Estimation of software quality parameters for hybrid agile process model,” SN Appl. Sci., vol. 3, no. 3, pp. 1–11, 2021, doi: 10.1007/s42452-021-04305-0.

[14] H. Chen, Z. Lou, and G. Shen, “An integrated flexible multifunctional sensing system for simultaneous monitoring of environment signals,” Sci. China Mater., vol. 63, no. 12, pp. 2560–2569, 2020, doi: 10.1007/s40843-020-1376-4.

[15] H. Parastar, G. van Kollenburg, Y. Weesepoel, A. van den Doel, L. Buydens, and J. Jansen, “Integration of handheld NIR and machine learning to ‘Measure & Monitor’ chicken meat authenticity,” Food Control, vol. 112, no. January, p. 107149, Jun. 2020, doi: 10.1016/j.foodcont.2020.107149.

[16] J. R. Beattie and F. W. L. Esmonde-White, “Exploration of Principal Component Analysis: Deriving Principal Component Analysis Visually Using Spectra,” Appl. Spectrosc., vol. 75, no. 4, pp. 361–375, 2021, doi: 10.1177/0003702820987847.

[17] Z. Wang, T. Wang, Y. Yang, X. Mi, and J. Wang, “Differential Confocal Optical Probes with Optimized Detection Efficiency and Pearson Correlation Coefficient Strategy Based on the Peak-Clustering Algorithm,” Micromachines, vol. 14, no. 6, 2023, doi: 10.3390/mi14061163.

[18] V. E. Baciu, J. Stiens, and B. da Silva, “MLino bench: A comprehensive benchmarking tool for evaluating ML models on edge devices,” J. Syst. Archit., vol. 155, no. June, p. 103262, 2024, doi: 10.1016/j.sysarc.2024.103262.

[19] N. Naik, P. Jenkins, and D. Newell, Learning Agile Scrum Methodology Using the Groupware Tool Trello $^{textregistered }$ Through Collaborative Working, vol. 993. Springer International Publishing, 2020. doi: 10.1007/978-3-030-22354-0_31.

[20] Y. Shen, Y. Wei, C. Zhu, J. Cao, and D. M. Han, “Ratiometric fluorescent signals-driven smartphone-based portable sensors for onsite visual detection of food contaminants,” Coord. Chem. Rev., 2022, doi: doi.org/10.1016/j.ccr.2022.214442.