A Hybrid Decision Logic Framework Combining Fuzzy Systems and Machine Learning Classifier for Post-Fermentation ‎Tea Quality Grading

  • Authors

    https://doi.org/10.14419/3s15f186

    Received date: July 31, 2025

    Accepted date: September 5, 2025

    Published date: September 13, 2025

  • Fuzzy Inference System; Tea Quality Grading; Hybrid Decision Logic; LightGBM; XGBoost; Spectrophotometric Sensing

  • Abstract

    This study addresses the need for reliable post-fermentation tea quality grading by proposing a hybrid decision logic framework that com-‎bines narrowband spectrophotometric sensing, computer vision-based fermentation indicators, and intelligent classification techniques. The ‎proposed methodology employs low-cost sensing and digital imaging for feature extraction, followed by a two-stage modeling approach ‎that integrates rule-based fuzzy inference system (FIS) with machine learning (ML) classification. After feature extraction, statistical and ‎ML-based feature selection techniques were applied to identify the most informative features. The initial stage employs a FIS to identify the ‎grade and its confidence score based on recurrent fuzzy patterns corresponding to each tea grade. In the second stage, a light-gradient boost‎ing machine LightGBM classifier is trained to enhance predictive accuracy and generate probabilistic confidence scores. Finally, hybrid ‎decision logic is applied to finalize the grade. The proposed hybrid model achieved an accuracy of 99.00%, precision of 99.53%, recall of ‎‎98.27%, and F1-score of 98.74%, outperforming both traditional ML and state-of-the-art models. It demonstrated robust generalization ‎across varying sample sizes and cross-validation folds. Ablation studies confirmed the efficiency of the FIS, showing strong performance ‎with reduced feature sets. Furthermore, the framework maintained shorter execution times than ensemble-based methods, making it suitable ‎for real-time and resource-constrained environments‎.

  • References

    1. Farag, M. A., Elmetwally, F., Elghanam, R., Kamal, N., Hellal, K., Hamezah, H. S., Zhao, C., & Mediani, A. (2023). Metabolomics in tea products; a compile of applications for enhancing agricultural traits and quality control analysis of Camellia sinensis. Food Chemistry, 404, 134628. https://doi.org/10.1016/j.foodchem.2022.134628.
    2. Erukainure, O. L., Chukwuma, C. I., Nambooze, J., Tripathy, S., Salau, V. F., Olofinsan, K., Ogunlakin, A. D., Ebuehi, O. A. T., & Unuofin, J. O. (2025). Tea Consumption and Diabetes: A Comprehensive Pharmacological Review of Black, White, Green, Oolong, and Pu-erh Teas. Plants. 14, 1-48. https://doi.org/10.3390/plants14131898.
    3. Hilal, Y., & Engelhardt, U. (2007). Characterisation of white tea – Comparison to green and black tea. Journal of Consumer Protection and Food Safety, 2, 414–421. https://doi.org/10.1007/s00003-007-0250-3.
    4. Sarmah, P. P., Deka, H., Sabhapondit, S., Chowdhury, P., Rajkhowa, K., & Karak, T. (2025). Black tea: Manufacturing and composition. In Tea in Health and Disease Prevention (pp. 11-20). Academic Press. https://doi.org/10.1016/B978-0-443-14158-4.00081-6.
    5. Li, M., Pan, T., & Chen, Q. (2021a). Estimation of tea quality grade using statistical identification of key variables. Food Control, 119, 107485. https://doi.org/10.1016/j.foodcont.2020.107485.
    6. An, T., Wang, Z., Li, G., Fan, S., Huang, W., Duan, D., Zhao, C., Tian, X., & Dong, C. (2023). Monitoring the major taste components during black tea fermentation using multielement fusion information in decision level. Food Chemistry: X, 18, 1-11. https://doi.org/10.1016/j.fochx.2023.100718.
    7. Wang, T. S., Liang, A. R. D., Ko, C. C., & Lin, J. H. (2022). The importance of region of origin and geographical labeling for tea consumers: The moderating effect of traditional tea processing method and tea prices. Asia Pacific Journal of Marketing and Logistics, 34(6), 1158-1177. https://doi.org/10.1108/APJML-02-2021-0121.
    8. Moreira, J., Aryal, J., Guidry, L., Adhikari, A., Chen, Y., Sriwattana, S., & Prinyawiwatkul, W. (2024). Tea quality: An overview of the analytical methods and sensory analyses used in the most recent studies. Foods, 13(22), 1-21. https://doi.org/10.3390/foods13223580.
    9. Bhargava, A., Bansal, A., Goyal, V., & Bansal, P. (2022). A review on tea quality and safety using emerging parameters. Journal of Food Meas-urement and Characterization, 16(2), 1291-1311. https://doi.org/10.1007/s11694-021-01232-x.
    10. Food and Agriculture Organization (FAO) of the United Nations. (2022). International tea market: Market situation, prospects and emerging issues. https://www.fao.org/documents/card/en/c/ cc0238en/.
    11. Arhin, I., Li, J., Mei, H., Amoah, M., Chen, X., Jeyaraj, A., Li, X., & Liu, A. (2022). Looking into the future of organic tea production and sustain-able farming: a systematic review. International Journal of Agricultural Sustainability, 20(5), 942-954. https://doi.org/10.1080/14735903.2022.2028398.
    12. Wang, H., Gu, J., & Wang, M. (2023). A review on the application of computer vision and machine learning in the tea industry. Frontiers in Sus-tainable Food Systems, 7, 1-16. https://doi.org/10.3389/fsufs.2023.1172543.
    13. Choudhary, M., & Kaur, P. (2025). Integrating AI with Machine Learning (ML) for Real-Time Detection in Food Industry. In Artificial Intelligence in the Food Industry (pp. 297-315). CRC Press. https://doi.org/10.1201/9781032633602-15.
    14. Yin, Y., Li, J., Ling, C., Zhang, S., Liu, C., Sun, X., & Wu, J. (2023). Fusing spectral and image information for characterization of black tea grade based on hyperspectral technology. Lwt, 185, 1-9. https://doi.org/10.1016/j.lwt.2023.115150.
    15. Ding, Y., Zeng, R., Jiang, H., Guan, X., Jiang, Q., & Song, Z. (2024). Classification of tea quality grades based on hyperspectral imaging spatial information and optimization models. Journal of Food Measurement and Characterization, 18(11), 9098-9112. https://doi.org/10.1007/s11694-024-02862-7.
    16. Ding, Y., Yan, Y., Li, J., Chen, X., & Jiang, H. (2022). Classification of tea quality levels using near-infrared spectroscopy based on CLPSO-SVM. Foods, 11(11), 1-10. https://doi.org/10.3390/foods11111658.
    17. Yang, J., Wang, J., Lu, G., Fei, S., Yan, T., Zhang, C., Lu, X., Yu, Z., Li, W., & Tang, X. (2021). TeaNet: Deep learning on Near-Infrared Spec-troscopy (NIR) data for the assurance of tea quality. Computers and Electronics in Agriculture, 190, 106431. https://doi.org/10.1016/j.compag.2021.106431.
    18. Li, T., Lu, C., Huang, J., Chen, Y., Zhang, J., Wei, Y., Wang, Y., & Ning, J. (2023a). Qualitative and quantitative analysis of the pile fermentation degree of Pu-erh tea. Lwt, 173, 1-9. https://doi.org/10.1016/j.lwt.2022.114327.
    19. Shi, Y.; Gong, F.; Wang, M.; Liu, J.; Wu, Y.; Men, H. (2019). A deep feature mining method of electronic nose sensor data for identifying beer olfactory information. J. Food Eng. 263, 437–445. https://doi.org/10.1016/j.jfoodeng.2019.07.023.
    20. Suhandy, D., & Yulia, M. (2019, April). Potential application of UV-visible spectroscopy and PLS-DA method to discriminate Indonesian CTC black tea according to grade levels. In IOP Conference Series: Earth and Environmental Science (Vol. 258, No. 1, p. 012042). IOP Publishing. https://doi.org/10.1088/1755-1315/258/1/012042.
    21. Jin, S., Li, M., Liu, Z., Liu, R., Li, Y., Zhu, Y., Yuan, Y., Li, P., Li, P., Chen C., Sun, Y., & Sun, Y. (2024). Study on the correlation between color and taste of beauty tea infusion and the pivotal contributing compounds based on UV–visible spectroscopy, taste equivalent quantification and me-tabolite analysis. Food Chemistry: X, 21, 101192. https://doi.org/10.1016/j.fochx.2024.101192.
    22. Wang, L., Xie, J., Wang, Q., Hu, J., Jiang, Y., Wang, J., Tong, H., Yuan, H., & Yang, Y. (2024). Evaluation of the quality grade of Congou black tea by the fusion of GC-E-Nose, E-tongue, and E-eye. Food Chemistry: X, 23, 1-9. https://doi.org/10.1016/j.fochx.2024.101519.
    23. Peng, Q., Li, S., Zheng, H., Meng, K., Jiang, X., Shen, R., Xue, J., & Xie, G. (2023). Characterization of different grades of Jiuqu hongmei tea based on flavor profiles using HS-SPME-GC-MS combined with E-nose and E-tongue. Food Research International, 172, 113198. https://doi.org/10.1016/j.foodres.2023.113198.
    24. Ren, G., Wu, R., Yin, L., Zhang, Z., & Ning, J. (2024). Description of tea quality using deep learning and multi-sensor feature fusion. Journal of Food Composition and Analysis, 126, 105924. https://doi.org/10.1016/j.jfca.2023.105924.
    25. Zhu, Y., Chen, S., Yin, H., Han, X., Xu, M., Wang, W., Zhang, Y., Feng, X., & Liu, Y. (2024). Classification of oolong tea varieties based on computer vision and convolutional neural networks. Journal of the Science of Food and Agriculture, 104(3), 1630-1637. https://doi.org/10.1002/jsfa.13049.
    26. Kumar, P., & Sharma, M. (2022). Data, machine learning, and human domain experts: none is better than their collaboration. International Journal of Human–Computer Interaction, 38(14), 1307-1320. https://doi.org/10.1080/10447318.2021.2002040.
    27. Palta, P., Kumar, A., & Palta, A. (2024). Leveraging Dielectric Properties, Remote Sensing, and Sensor Technology in Agriculture: A Perspective on Industry and Emerging Technologies. Industry 5.0 and Emerging Technologies: Transformation Through Technology and Innovations, 89-109. https://doi.org/10.1007/978-3-031-70996-8_5.
    28. Harshvardhan, FNU, "From Data to Decisions: Machine Learning for Enterprise Demand Forecasting. " PhD diss., University of Tennessee, 2025.
    29. https://trace.tennessee.edu/utk_graddiss/12366.
    30. Pan, S. Y., Nie, Q., Tai, H. C., Song, X. L., Tong, Y. F., Zhang, L. J. F., ... & Liang, C. (2022). Tea and tea drinking: China’s outstanding contribu-tions to the mankind. Chinese medicine, 17(1), 1-40. https://doi.org/10.1186/s13020-022-00571-1.
    31. Banerjee, S., & Tyagi, P. K. (2024). Exploring the booming tea tourist industry and unconventional tourism through the ritual of drinking tea in In-dia. Journal of Ethnic Foods, 11(1), 1-19. https://doi.org/10.1186/s42779-023-00215-1.
    32. Alijoyo, F. A., Janani, S., Santosh, K., Shweihat, S. N., Alshammry, N., Ramesh, J. V. N., & El-Ebiary, Y. A. B. (2024). Enhancing AI interpreta-tion and decision-making: Integrating cognitive computational models with deep learning for advanced uncertain reasoning systems. Alexandria Engineering Journal, 99, 17-30. https://doi.org/10.1016/j.aej.2024.04.073.
    33. Dey, A., & Ashok, S. D. (2024). Fuzzy logic based qualitative indicators for promoting extended producer responsibility and sustainable food packaging waste management. Environmental and Sustainability Indicators, 24, 1-12. https://doi.org/10.1016/j.indic.2024.100534.
    34. Widayat, I. W., Arsyad, A. A., Mantau, A. J., Adhitya, Y., & Köppen, M. (2024). Fuzzy Methods in Smart Farming: A Systematic Re-view. Informatica, 36(2), 453-489. https://doi.org/10.15388/24-INFOR579.
    35. Gill, G. S., Kumar, A., & Agarwal, R. (2013). Nondestructive grading of black tea based on physical parameters by texture analysis. Biosystems Engineering, 116(2), 198-204. https://doi.org/10.1016/j.biosystemseng.2013.08.002.
    36. Yu, D., & Gu, Y. (2021). A machine learning method for the fine-grained classification of green tea with geographical indication using a MOS-based electronic nose. Foods, 10(4), 1-17. https://doi.org/10.3390/foods10040795.
    37. Kelly, J. W., Degenhart, A. D., Siewiorek, D. P., Smailagic, A., & Wang, W. (2012, August). Sparse linear regression with elastic net regularization for brain-computer interfaces. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 4275-4278). IEEE. https://doi.org/10.1109/EMBC.2012.6346911.
    38. Oliveira, M. M., Cerqueira, B. V., Barbon Jr, S., & Barbin, D. F. (2021). Classification of fermented cocoa beans (cut test) using computer vi-sion. Journal of Food Composition and Analysis, 97, 1-8. https://doi.org/10.1016/j.jfca.2020.103771.
    39. Liu, H., Yu, D., & Gu, Y. (2019). Classification and evaluation of quality grades of organic green teas using an electronic nose based on machine learning algorithms. IEEE Access, 7, 172965-172973. https://doi.org/10.1109/ACCESS.2019.2957112.
    40. Zhao, X. Y., He, Y. X., Zhang, H. T., Ding, Z. T., Zhou, C. A., & Zhang, K. X. (2024). A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model. Scientific reports, 14(1), 4166. https://doi.org/10.1038/s41598-024-54389-y.
    41. Li, L., Chen, Y., Dong, S., Shen, J., Cao, S., Cui, Q., Song, Y., & Ning, J. (2023b). Rapid and comprehensive grade evaluation of Keemun black tea using efficient multidimensional data fusion. Food Chemistry: X, 20, 1-10. https://doi.org/10.1016/j.fochx.2023.100924.
    42. Zhou, Q., Dai, Z., Song, F., Li, Z., Song, C., & Ling, C. (2023). Monitoring black tea fermentation quality by intelligent sensors: Comparison of image, e-nose and data fusion. Food Bioscience, 52, 102454. https://doi.org/10.1016/j.fbio.2023.102454.
    43. Xia, H., Chen, W., Hu, D., Miao, A., Qiao, X., Qiu, G., Liang, J., Guo, W., & Ma, C. (2024). Rapid discrimination of quality grade of black tea based on near-infrared spectroscopy (NIRS), electronic nose (E-nose) and data fusion. Food Chemistry, 440, 138242. https://doi.org/10.1016/j.foodchem.2023.138242.
    44. Liang, J., Guo, J., Xia, H., Ma, C., & Qiao, X. (2025). A black tea quality testing method for scale production using CV and NIRS with TCN for spectral feature extraction. Food Chemistry, 464, 141567. https://doi.org/10.1016/j.foodchem.2024.141567.
    45. Wu, L., Xu, Q., Su, C., Yin, X., Huo, X., Zhao, X., Zhou, Y., & Huang, J. (2025). Classification of quality grading of Anji white tea using hyper-spectral imaging and data fusion techniques. Journal of Food Composition and Analysis, 142, 107563. https://doi.org/10.1016/j.jfca.2025.107563.
    46. Zhang, Y., Li, X., Zhu, L., Xing, X., & Du, Y. (2025). A portable tea aroma detection stick system for identifying tea grades. Journal of Food Measurement and Characterization, 1-13. https://doi.org/10.1007/s11694-025-03348-w.
    47. Li, L., Wang, Y., Jin, S., Li, M., Chen, Q., Ning, J., & Zhang, Z. (2021b). Evaluation of black tea by using smartphone imaging coupled with micro-near-infrared spectrometer. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 246, 118991. https://doi.org/10.1016/j.saa.2020.118991.
    48. Xia, L., & Zhu, P. (2022, August). Application of Various Spectral Techniques in Quantitative Analysis of Tea Quality. In 2022 2nd International Conference on Frontiers of Electronics, Information and Computation Technologies (ICFEICT) (pp. 248-258). IEEE. https://doi.org/10.1109/ICFEICT57213.2022.00053.
    49. Pourjavad, E., & Mayorga, R. V. (2019). A comparative study and measuring performance of manufacturing systems with Mamdani fuzzy infer-ence system. Journal of Intelligent Manufacturing, 30(3), 1085-1097. https://doi.org/10.1007/s10845-017-1307-5.
    50. Bidwe, R., Mishra, S., Bajaj, S., & Kotecha, K. (2025). Leveraging hybrid model of ConvNextBase and LightGBM for early ASD detection via eye-gaze analysis. MethodsX, 14, 1-17. https://doi.org/10.1016/j.mex.2025.103166.

  • Downloads

  • How to Cite

    Sulaikha , C. M., & Somasundaram , A. . (2025). A Hybrid Decision Logic Framework Combining Fuzzy Systems and Machine Learning Classifier for Post-Fermentation ‎Tea Quality Grading. International Journal of Basic and Applied Sciences, 14(5), 390-402. https://doi.org/10.14419/3s15f186