Fuzzy Logic Model for Evaluating Fresh Milk Quality Based on Protein to Fat Ratio
DOI:
https://doi.org/10.62535/9912q034Keywords:
fresh milk, fuzzy logic, quality evaluation.Abstract
The assessment of fresh milk quality plays a crucial role in ensuring food safety and supporting the efficiency of dairy processing. This study aims to develop a fuzzy logic model to evaluate the acceptability of fresh milk based on the protein-to-fat ratio in accordance with the Indonesian National Standard (SNI 3141.1:2011). A qualitative descriptive method was applied using MATLAB software to simulate fuzzy inference with protein and fat contents as input variables and milk quality as the output. Triangular and trapezoidal membership functions were utilized, with the Mamdani inference and centroid defuzzification methods used to obtain precise output values. The results indicate that samples with high and balanced protein and fat contents yield superior milk quality, whereas low levels of both result in poor classification. The fuzzy rule system effectively accommodates natural variations in milk composition, offering a more adaptive and accurate assessment compared to conventional threshold-based evaluations. This model demonstrates strong potential as a decision-support tool for quality control in the dairy industry and contributes to improving the consistency and scientific basis of national milk quality assurance systems.
References
Abdellaoui S, Farah A, Driouich R, Berrada H. 2022.Effect of feed on the milk protein and fat composition. Agricultural Science And Technology.. Animals, 12(11), 1530. doi: /10.15547/ast.2022.02.019
Antanaitis R, Juozaitienė V, Televičius M. 2023.In line registered milk fat to protein ratio for the assesment of metabolic status in dairy cows. Animals. . Animals, 13(18), 3293. doi: /0.3390/ani13203293
Badan Standardisasi Nasional. (2011). Susu Segar Sapi (SNI 3141.1:2011). Jakarta: BSN.
Bhadane K, Deshmukh R, Patil A. 2020. Fuzzy expert system for milk freshness evaluation. Journal of Food Quality and Hazards Control, 7(3), 104–110.
Çelikbilek, Y. (2019). The importance of the place of defuzzification step in fuzzy systems. Sakarya University Journal of Science, 23(2), 139-148. Doi: 10.16984/saufenbilder.421856
Gafar AW, Herlinawati E. 2024. Aplikasi logika fuzzy dalam menentukan jumlah produksi es batu balok berdasarkan data permintaan dan data persediaan. Prosiding Seminar Nasional Sains dan Teknologi “SainTek”. 1(1):48-57.
Gilda KS, Satarkar SL. 2020. Analytical overview of defuzzification methods. International Journal of Advance Research, Ideas and Innovations in Technology, 6(2), 359-365.
Haerani E. 2021. Analisa kendali logika fuzzy dengan metode defuzzifikasi coa (center of area), bisektor, mom (mean of maximum), lom (largest of maximum), dan som (smallest of maximum). SITEKIN: Jurnal Sains, Teknologi dan Industri, 10(2), 245-253. Doi: 10.24014/SITEKIN.V10I2.543
Hari HN, Darmawan I. 2023. Sistem pengontrol suhu pada kandang brooding dengan logika fuzzy menggunakan arduino uno berbasis mobile. Journal of Responsif. 5(1):43-51. doi : /10.51977/jti.v5i1.1049.
Lima JF, Patiño-León A, Orellana M, Zambrano-Martinez JL. 2025. Evaluating the impact of membership functions and defuzzification methods in a fuzzy system: Case of air quality levels. Applied Sciences, 15(4): 1-16. doi: 10.3390/app15041934
Makkar R, Makkar CR. 2018. Application of fuzzy logic: A literature review. Int. J. Stat. Appl. Math, 3(1), 357-359.
Martins, JA, Azevedo AM, Almeida AC, Silva LCR, Fernandes ACG, Valadares NR, Aspiazú I. 2022. Fuzzy logic is a powerful tool for the automation of milk classification, Acta Scientiarum. Technology, 44, e57860. https://doi.org/10.4025/actascitechnol.v44i1.57860
Nisa AK, Abdy M, Zaki A. 2020. Penerapan fuzzy logic untuk menentukan minuman susu kemasan terbaik dalam pengoptimalan gizi. Journal of Mathematics Computations and Statistics, 3(1), 51.
Putri OF, Sudawarti W, Wardah S, Marfuah U, Purnamasari A. 2024. Aplikasi sistem inferensi fuzzy metode mamdani untuk memprediksi jumlah produksi pakaian pada industri kreatif fesyen. Seminar Nasional Sains dan Teknologi 2024. Fakultas Teknik, Universitas Muhammadiyah Jakarta.
Rukmana, M. S., Rakhmatsyah, A., & Wardana, A. A. (2021). Mastitis Detection System in Dairy Cow Milk based on Fuzzy Inference System using Electrical Conductivity and Power of Hydrogen Sensor Value. EMITTER International Journal of Engineering Technology, 9(1), 154‑168.
Saatchi R. 2024. Fuzzy logic concepts, developments and implementation. Information, 15(10): 1-24. doi: 10.3390/info15100656
Schwaab AADS, Nassar SM, Fiho PJDF. 2015. Automatic methods for generation of type-1 and interval type-2 fuzzy membership function. Journal of Computer Sciences. 11(9):976-987. doi: 10.3844/jcssp.2015.976.987.
Simjanović D, Milojković M. 2024. On a Defuzzification Process of Fuzzy Controllers. Facta Universitatis, Series: Automatic Control and Robotics, 22(2): 115-130. Doi: 10.22190/FUACR231202009S
Sonalitha E, Asriningtias SR, Nurdewanto B. 2020. Fuzzy Clustering. Ed ke-1. Graha Ilmu. Yogyakarta
Užga-Rebrovs O, Kuļešova G. 2017. Comparative analysis of fuzzy set defuzzification methods in the context of ecological risk assessment. Information Technology and Management Science, 20(1): 25-29.
Yadav DK, Yadav HB. 2015. Developing membership function and fuzzy rules form numerical data for decision making. National Institute of Technology, Jamshedpur India: IFSA-EUSFLAT 2015.
