From leaf to blend: CNN-enhanced multi-source feature fusion enables threshold-driven style control in digital tobacco formulation
Building on these insights, a probabilistic style modulation strategy was proposed and validated through case applications, transforming theoretical discoveries into actionable design strategies. This innovation establishes region ratio constraints based on threshold-defined boundaries, creating a data-driven framework that systematically achieves target formulation style through the threshold's predictive capacity. This framework advances tobacco engineering from empirical practices to predictive digital transformation, providing a template for agricultural product manufacturing systems facing similar formulation challenges.
Authors
- Zhongli Ye
- Yan Lin (ORCID: https://orcid.org/0000-0001-5507-8989)
- Guohua Cai
- Zechun Liu (ORCID: https://orcid.org/0000-0001-5856-2506)
- Di Wang (ORCID: https://orcid.org/0000-0002-3171-4001)
- Wei Xie (ORCID: https://orcid.org/0000-0002-8290-514X)
- Yi‐Ling Chen (ORCID: https://orcid.org/0000-0003-3758-0638)
- Qiaoling Li (ORCID: https://orcid.org/0000-0003-4995-3614)
- Qian Gu (ORCID: https://orcid.org/0000-0002-7394-5238)
- Di Wu (ORCID: https://orcid.org/0000-0002-9176-3518)
- Hui Liang
Institutions
- China Tobacco (CN)
- Tobacco Research Institute (CN)
- Fujian Tobacco Industry Limited Liability Company (China) (CN)
- Xiamen Tobacco Industry (China) (CN)
Publication Details
- Journal
- Biotechnology for Biofuels and Bioproducts
- Published
- 2025-10-08
- DOI
- https://doi.org/10.1186/s13068-025-02706-6
- Citations
- 1
- Primary Topic
- Spectroscopy and Chemometric Analyses
- Type
- article
- Field-Weighted Citation Impact
- 0.75
Funders
- China National Tobacco Corporation