Please use this identifier to cite or link to this item:
|Title:||Machine learning & automation to accelerate formulations for personal care & cosmetics||Authors:||Rodrigues, James Alexander||Keywords:||Engineering::Materials||Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Rodrigues, J. A. (2022). Machine learning & automation to accelerate formulations for personal care & cosmetics. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156788||Abstract:||Artificial Intelligence (AI) and Machine Learning (ML) has taken great strides in development. Commercial AI are used in a wide variety of automation applications from self-driving cars to tracking and identification of consumer preferences and behaviour. One of the key strengths of AI lies in its ability to process large data sets and identify key patterns which can in turn be used to simulate and predict potential outcomes. As AI technology matures, greater emphasis has been placed on using machine learning as a tool for accelerating such optimization processes, reducing time and manpower costs required to identify the necessary conditions for delivering the greatest output. One particular field that requires a significant amount of optimization is the pharmaceutical and cosmetics industry where poor formulation can lead to sub-optimal effects or may cause injury to the consumer. Hence identifying the ideal formulation for these products is an essential part of the industry and often requires extensive amounts of time dedicated to product testing. This paper details the use of ML as an optimization tool in the context of personal care & cosmetics formulation by using data collected from physical samples, focusing on viscosity and pH changes, in order to identify possible interactions between ingredients and predict such changes. By leveraging on data science and optimization techniques, we attempt active learning to drive discovery of new products that optimize the aforementioned objectives. By leveraging on data science and optimization techniques, we attempt active learning to drive discovery of new products that optimize the aforementioned objectives.||URI:||https://hdl.handle.net/10356/156788||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||MSE Student Reports (FYP/IA/PA/PI)|
Updated on May 27, 2022
Updated on May 27, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.