A transfer learning approach for predictive modeling of bioprocesses using small data
| Autor: | Keju Jing, Alexander W. Rogers, Jiangtao Yan, Ehecatl Antonio del Rio-Chanona, Fernando Vega-Ramon, Dongda Zhang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Structure (mathematical logic)
Small data Computer science business.industry Reliability (computer networking) Lutein Bioengineering Machine learning computer.software_genre Models Biological Applied Microbiology and Biotechnology Fault detection and isolation Machine Learning Kinetics Chlorophyceae Microalgae Benchmark (computing) Biomass Artificial intelligence Transfer of learning business computer Topology (chemistry) Biotechnology Interpretability |
| Zdroj: | Rogers, A W, Vega-Ramon, F, Yan, J, Río-Chanona, E A, Jing, K & Zhang, D 2022, ' A transfer learning approach for predictive modeling of bioprocesses using small data ', Biotechnology and Bioengineering, vol. 119, no. 2, pp. 411-422 . https://doi.org/10.1002/bit.27980 |
| ISSN: | 1097-0290 0006-3592 |
| DOI: | 10.1002/bit.27980 |
| Popis: | Predictive modeling of new biochemical systems with small data is a great challenge. To fill this gap, transfer learning, a subdomain of machine learning that serves to transfer knowledge from a generalized model to a more domain-specific model, provides a promising solution. While transfer learning has been used in natural language processing, image analysis, and chemical engineering fault detection, its application within biochemical engineering has not been systematically explored. In this study, we demonstrated the benefits of transfer learning when applied to predict dynamic behaviors of new biochemical processes. Two different case studies were presented to investigate the accuracy, reliability, and advantage of this innovative modeling approach. We thoroughly discussed the different transfer learning strategies and the effects of topology on transfer learning, comparing the performance of the transfer learning models against benchmark kinetic and data-driven models. Furthermore, strong connections between the underlying process mechanism and the transfer learning model's optimal structure were highlighted, suggesting the interpretability of transfer learning to enable more accurate prediction than a naive data-driven modeling approach. Therefore, this study shows a novel approach to effectively combining data from different resources for bioprocess simulation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text