ABSTRACT
Koji making is an important craft with critical significance for assessing the quality of liquor. However, under the same physicochemical environment, due to the difference in koji reproductive habits, different levels of koji have different content scores distribution, so, there are great challenges in predicting multiple scores of koji accurately. To address this issue, we proposed a multi-task learning approach by leveraging a shared bottom-level representation layer to extract shared features from the data and joint training on multiple koji rating tasks to learn the relationships between different levels of koji. We conduct experimental evaluations on a real-world koji making dataset. The results demonstrate that the proposed method exceeds other benchmark learning methods in predicting koji scores and capturing the relationships between different levels of koji, thereby enhancing the accuracy and robustness of predictions.
- Yuan, W., Zhao, Y., Wang, Y., Lan, M., Zhang, L., Chen, S., Wu, Q., Ying, L., Sheng, C. and Wang, S., “Study on the Dynamic Changes of Hydrolase System and Physicochemical Properties during the High Temperature Daqu Production Process,” Brewing 50(4), 31–36. 2023. http://doi.org/10.3969/j.issn.1002-8110.2023.04.010Google ScholarCross Ref
- Zhang, Z., Li, Z., Shu, Z., Liang, J., Bai, W., Fei, Y., Zhao, W. and Zhao, S., “Effects of different koji making methods on volatile flavor components in the production of fermented soybean flavor Baijiu koji,” Journal of Food Safety and Quality Testing 14(14), 105–114. 2023. http://doi.org/10.19812/j.cnki.jfsq11-5956/ts.2023.14.008Google ScholarCross Ref
- Li, Z., Feng, H., Wu, D., He, J., Mao, H. and Zhang, C., “Study on the Changes of Physical and Chemical Indexes and Flavor during High Temperature Daqu Fermentation,” Brewing Technology(10), 40–45. 2022. http://doi.org/10.13746/j.njkj.2022116Google ScholarCross Ref
- Cardoso Schwindt, V., Coletto, M. M., Díaz, M. F. and Ponzoni, I., “Could QSOR Modelling and Machine Learning Techniques Be Useful to Predict Wine Aroma?,” Food Bioprocess Technol 16(1), 24–42. 2023. https://doi.org/10.1007/s11947-022-02836-xGoogle ScholarCross Ref
- Tiwari, P., Bhardwaj, P., Somin, S., Parr, W. V., Harrison, R. and Kulasiri, D., “Understanding Quality of Pinot Noir Wine: Can Modelling and Machine Learning Pave the Way?,” 19, Foods 11(19), 3072. 2022. https://doi.org/10.3390/foods11193072Google ScholarCross Ref
- Wang, X., Jing, X., Zhao, H., Tian, Y., Li, H., Han, Y. and Jia, L., “Optimization of koji making process for saccharifying enzyme producing strain M1 using response surface methodology,” Brewing 46(5), 79–83. 2019. http://doi.org/10.3969/j.issn.1002-8110.2019.05.022Google ScholarCross Ref
- Liu, M., Zhou, Y., Yuan, L., Liu, X. and Bian, M., “Screening of High Yield Saccharifying Enzyme Fungi in Liquor Yeast and Optimization of Solid State Fermentation Conditions for Enzyme Production,” Food and Fermentation Industry 44(10), 118–123. 2018. http://doi.org/10.13995/j.cnki.11-1802/ts.017311Google ScholarCross Ref
- Lu, Qi., Li, Z., Zhang, G., Feng, H. and Song, B., “The Effect of Different Xiaoqu on the Production of Fragrant Xiaoqu Liquor,” Brewing Technology(12), 73–77. 2017.Google Scholar
- He, G., Huang, J., Zhou, R., Wu, C. and Jin, Y., “Effect of Fortified Daqu on the Microbial Community and Flavor in Chinese Strong-Flavor Liquor Brewing Process,” Frontiers in Microbiology 10. 2019. http://doi.org/10.13746/j.njkj.2017293Google ScholarCross Ref
- Yi, Z., Jin, Y., Xiao, Y., Chen, L., Tan, L., Du, A., He, K., Liu, D., Luo, H., Fang, Y. and Zhao, H., “Unraveling the Contribution of High Temperature Stage to Jiang-Flavor Daqu, a Liquor Starter for Production of Chinese Jiang-Flavor Baijiu, With Special Reference to Metatranscriptomics,” Frontiers in Microbiology 10. 2019. https://doi.org/10.3389/fmicb.2019.00472Google ScholarCross Ref
- Wu, D., Liao, M.-W., Zhang, W.-T., Wang, X.-G., Bai, X., Cheng, W.-Q. and Liu, W.-Y., “YOLOP: You Only Look Once for Panoptic Driving Perception,” Mach. Intell. Res. 19(6), 550–562. 2022. https://doi.org/10.1007/s11633-022-1339-yGoogle ScholarCross Ref
- Ma, X., Zhao, L., Huang, G., Wang, Z., Hu, Z., Zhu, X. and Gai, K., “Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate,” The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 1137–1140, Association for Computing Machinery, New York, NY, USA. 2018. https://doi.org/10.1145/3209978.3210104Google ScholarDigital Library
- Tang, H., Liu, J., Zhao, M. and Gong, X., “Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations,” Proceedings of the 14th ACM Conference on Recommender Systems, 269–278, Association for Computing Machinery, New York, NY, USA. 2020. https://doi.org/10.1145/3383313.3412236Google ScholarDigital Library
- Liu, X., He, P., Chen, W. and Gao, J., “Multi-Task Deep Neural Networks for Natural Language Understanding,” Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 4487–4496, Association for Computational Linguistics, Florence, Italy. 2019. http://dx.doi.org/10.18653/v1/P19-1441Google ScholarCross Ref
- Worsham, J. and Kalita, J., “Multi-task learning for natural language processing in the 2020s: Where are we going?,” Pattern Recognition Letters 136, 120–126. 2020. https://doi.org/10.1016/j.patrec.2020.05.031Google ScholarCross Ref
- Seber, G. A. F. and Lee, A. J., [Linear Regression Analysis], John Wiley & Sons. 2003. https://books.google.com/books?id=mVSkEAAAQBAJGoogle ScholarCross Ref
- Chen, T. and Guestrin, C., “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794, Association for Computing Machinery, New York, NY, USA. 2016. https://dl.acm.org/doi/10.1145/2939672.2939785Google ScholarDigital Library
- Hecht-nielsen, R., “III.3 - Theory of the Backpropagation Neural Network**Based on ‘nonindent’ by Robert Hecht-Nielsen, which appeared in Proceedings of the International Joint Conference on Neural Networks 1, 593–611, June 1989. © 1989 IEEE.,” [Neural Networks for Perception], H. Wechsler, Ed., Academic Press, 65–93. 1992. https://doi.org/10.1016/B978-0-12-741252-8.50010-8Google ScholarCross Ref
- Hancock, J. T. and Khoshgoftaar, T. M., “CatBoost for big data: an interdisciplinary review,” Journal of Big Data 7(1), 94. 2020. https://doi.org/10.1186/s40537-020-00369-8Google ScholarCross Ref
- Lundberg, S. M. and Lee, S.-I., “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems 30, Curran Associates, Inc. 2017. https://doi.org/10.48550 /arXiv.1705.0787Google Scholar
Index Terms
- Quality Prediction of Brewing Koji based on Multitask Learning
Recommendations
Semi-supervised multitask learning
NIPS'07: Proceedings of the 20th International Conference on Neural Information Processing SystemsA semi-supervised multitask learning (MTL) framework is presented, in which M parameterized semi-supervised classifiers, each associated with one of M partially labeled data manifolds, are learned jointly under the constraint of a soft-sharing prior ...
Multitask Learning
Special issue on inductive transferMultitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. It does this by learning tasks in parallel while using a shared ...
Comments