Browsing by Subject "Design of Experiments"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Contributions to Optimal Experimental Designs with Application to the Development of Machine Learning Based Systems
    (2023-03) Sunder, Gautham
    Design of experiments (DoE) is long-established as an indispensable methodology for reliableand expeditious product development across many domains. Over the years, the application context of DoE has evolved from agriculture experiments to industrial experiments, and more recently, to experiments on software products. The three studies in the thesis make methodological contributions to the optimal experimental design literature and propose experimentation strategies for the following objectives (i) for optimizing an unknown noisy black-box function, (ii) for estimating an unknown noisy black-box function, and (iii) for identifying the best surrogate model among m ≥ 2 candidate models that best approximate the unknown black-box function. The application context of the first two studies is hyperparameter optimization of machine learning models, a critical step in their training process. The application context of the third study is online evaluation of machine learning models, a critical step for validating the performance of the models prior to their deployment. We illustrate the utility of the proposed experimentation strategies through simulation studies on synthetic test functions and two case studies at a large medical device manufacturer in the context of automating visual quality inspections in manufacturing. Minimizing the total cost of experimentation and shortening the experimentation lifecycle for the development of reliable machine learning based systems are the key contributions of the methods proposed in this thesis.
  • Thumbnail Image
    Item
    Extracellular Matrix Guided Endothelial Differentiation
    (2022-08) Hall, Mikayla
    Cardiovascular disease is the leading cause of death worldwide. Due to recent advances including development of induced pluripotent stem cells, cardiac tissue engineering has emerged as a promising avenue for in vitro drug and device testing as well as eventual transplantation. Nutrient flow presents one of the major challenges to large scale engineered cardiac tissues which is necessary for many of the potential applications of engineered tissues. The lack of nutrient flow could be solved through tissue vascularization which requires endothelial cells lining vessels. The extracellular matrix (ECM) plays a vital role in tissue development and the majority of in vitro differentiation protocols rely on ECM substrates. Here we present two studies which investigate the role of the ECM in endothelial differentiation and the mechanisms activated by ECM engagement during differentiation. First, we investigate the role of individual ECM proteins in endothelial differentiation and elucidate pathways key to how ECM interactions promote differentiation. Second, a Design of Experiments approach was utilized to optimize the ECM composition for endothelial differentiation. The foundation of this work is a thorough knowledge of the role of the ECM during development, which guides protein selection and mechanistic investigation. An improved understanding of the role of ECM during in vitro differentiation will lead to better differentiation protocols and the potential for in situ differentiation. Ultimately, these studies will inform methods for engineered tissue vascularization to improve cell survival in large scale engineered tissues.