Artificial intelligence in pharmaceutical product formulation: Neural computing
Abstract
The properties of a formulation are determined not only by the ratios in which the ingredients are combined but also by the processing conditions. Although the relationships between the ingredient levels, processing conditions, and product performance may be known anecdotally, they can rarely be quantified. In the past, formulators tended to use statistical techniques to model their formulations, relying on response surfaces to provide a mechanism for optimization. However, the optimization by such a method can be misleading, especially if the formulation is complex. More recently, advances in mathematics and computer science have led to the development of alternative modeling and data mining techniques which work with a wider range of data sources: neural networks (an attempt to mimic the processing of the human brain); genetic algorithms (an attempt to mimic the evolutionary process by which biological systems self-organize and adapt), and fuzzy logic (an attempt to mimic the ability... of the human brain to draw conclusions and generate responses based on incomplete or imprecise information). In this review the current technology will be examined, as well as its application in pharmaceutical formulation and processing. The challenges, benefits and future possibilities of neural computing will be discussed.
Keywords:
artificial neural networks / pharmaceutical formulation / genetic algorithms / fuzzy logic / optimizationSource:
CICEQ - Chemical Industry and Chemical Engineering Quarterly, 2009, 15, 4, 227-236Publisher:
- Savez hemijskih inženjera, Beograd
DOI: 10.2298/CICEQ0904227I
ISSN: 1451-9372
WoS: 000275477600005
Scopus: 2-s2.0-77149155363
Collections
Institution/Community
PharmacyTY - JOUR AU - Ibrić, Svetlana AU - Đurić, Zorica AU - Parojčić, Jelena AU - Petrović, Jelena PY - 2009 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/1188 AB - The properties of a formulation are determined not only by the ratios in which the ingredients are combined but also by the processing conditions. Although the relationships between the ingredient levels, processing conditions, and product performance may be known anecdotally, they can rarely be quantified. In the past, formulators tended to use statistical techniques to model their formulations, relying on response surfaces to provide a mechanism for optimization. However, the optimization by such a method can be misleading, especially if the formulation is complex. More recently, advances in mathematics and computer science have led to the development of alternative modeling and data mining techniques which work with a wider range of data sources: neural networks (an attempt to mimic the processing of the human brain); genetic algorithms (an attempt to mimic the evolutionary process by which biological systems self-organize and adapt), and fuzzy logic (an attempt to mimic the ability of the human brain to draw conclusions and generate responses based on incomplete or imprecise information). In this review the current technology will be examined, as well as its application in pharmaceutical formulation and processing. The challenges, benefits and future possibilities of neural computing will be discussed. PB - Savez hemijskih inženjera, Beograd T2 - CICEQ - Chemical Industry and Chemical Engineering Quarterly T1 - Artificial intelligence in pharmaceutical product formulation: Neural computing VL - 15 IS - 4 SP - 227 EP - 236 DO - 10.2298/CICEQ0904227I ER -
@article{ author = "Ibrić, Svetlana and Đurić, Zorica and Parojčić, Jelena and Petrović, Jelena", year = "2009", abstract = "The properties of a formulation are determined not only by the ratios in which the ingredients are combined but also by the processing conditions. Although the relationships between the ingredient levels, processing conditions, and product performance may be known anecdotally, they can rarely be quantified. In the past, formulators tended to use statistical techniques to model their formulations, relying on response surfaces to provide a mechanism for optimization. However, the optimization by such a method can be misleading, especially if the formulation is complex. More recently, advances in mathematics and computer science have led to the development of alternative modeling and data mining techniques which work with a wider range of data sources: neural networks (an attempt to mimic the processing of the human brain); genetic algorithms (an attempt to mimic the evolutionary process by which biological systems self-organize and adapt), and fuzzy logic (an attempt to mimic the ability of the human brain to draw conclusions and generate responses based on incomplete or imprecise information). In this review the current technology will be examined, as well as its application in pharmaceutical formulation and processing. The challenges, benefits and future possibilities of neural computing will be discussed.", publisher = "Savez hemijskih inženjera, Beograd", journal = "CICEQ - Chemical Industry and Chemical Engineering Quarterly", title = "Artificial intelligence in pharmaceutical product formulation: Neural computing", volume = "15", number = "4", pages = "227-236", doi = "10.2298/CICEQ0904227I" }
Ibrić, S., Đurić, Z., Parojčić, J.,& Petrović, J.. (2009). Artificial intelligence in pharmaceutical product formulation: Neural computing. in CICEQ - Chemical Industry and Chemical Engineering Quarterly Savez hemijskih inženjera, Beograd., 15(4), 227-236. https://doi.org/10.2298/CICEQ0904227I
Ibrić S, Đurić Z, Parojčić J, Petrović J. Artificial intelligence in pharmaceutical product formulation: Neural computing. in CICEQ - Chemical Industry and Chemical Engineering Quarterly. 2009;15(4):227-236. doi:10.2298/CICEQ0904227I .
Ibrić, Svetlana, Đurić, Zorica, Parojčić, Jelena, Petrović, Jelena, "Artificial intelligence in pharmaceutical product formulation: Neural computing" in CICEQ - Chemical Industry and Chemical Engineering Quarterly, 15, no. 4 (2009):227-236, https://doi.org/10.2298/CICEQ0904227I . .