Existing space-filling designs are based on the assumption that the experimental region is rectangular, while in practice this assumption can be violated. Motivated by a data center thermal management study, a class of probability-based Latin hypercube designs is proposed to accommodate a specific type of irregular regions. A heuristic algorithm is proposed to efficiently search for optimal des...

We give a new characterization of Elfving’s (1952) method for computing c-optimal designs in k dimensions which gives explicit formulae for the k unknown optimal weights and k unknown signs in Elfving’s characterization. This eliminates the need to search over these parameters to compute c-optimal designs, and thus reduces the computational burden from solving a family of optimization problems ...

Blocking is a useful technique to control systematic variation in experiments. Robust parameter design is widely used as an effective tool to reduce process variability by appropriate selection of control factors to make the process insensitive to noise. In this paper, we propose and study a method for selecting the optimal blocked robust parameter designs when some of the control-by-noise inte...

Metamodeling approach has been widely used due to the high computational cost of using high-fidelity simulations in engineering design. The accuracy of metamodels is directly related to the experimental designs used. Optimal experimental designs have been shown to have good “space filling” and projective properties. However, the high cost in constructing them limits their use. In this paper, a ...

Two designs for a fractional factorial experiment are equivalent if one can be obtained from the other by reordering the treatment combinations, relabeling the factors and relabeling the factor levels. Designs can be viewed as sets of points in pdimensional space, where p is the number of factors. It is shown that, in this setting, two designs are equivalent if the Hamming distances between the...

Computational models of creative design typically adopt a specific mechanism and apply that mechanism to a design space to demonstrate its potential for generating creative designs. For example, some computational models use analogy as a reasoning mechanism for developing novel designs from previous designs and others use evolutionary algorithms as a way of searching the design space to get to ...

(ABSTRACT) Bayesian optimal designs have received increasing attention in recent years, especially in biomedical and clinical trials. Bayesian design procedures can utilize the available prior information of the unknown parameters so that a better design can be achieved. However, a difficulty in dealing with the Bayesian design is the lack of efficient computational methods. In this research, a...

OF THE DISSERTATION The Use of Arti cial Intelligence to Improve the Numerical Optimization of Complex Engineering Designs by Mark A. Schwabacher Dissertation Directors: Thomas Ellman and Andrew Gelsey Gradient-based numerical optimization of complex engineering designs promises to produce better designs rapidly. However, such methods generally assume that the objective function and constraint ...

Scatter search is an evolutionary method that has been successfully applied to hard optimization problems. The fundamental concepts and principles of the method were first proposed in the 1970s, based on formulations dating back to the 1960s for combining decision rules and problem constraints. In contrast to other evolutionary methods like genetic algorithms, scatter search is founded on the p...

The Guided Search (GS) model, a quantitative model of visual search, was used to develop menu designs in a four-step process. First, a GS simulation model was defined for a menu search task. Second, model parameters were estimated to provide the best fit between model predictions and experimental data. Third, an optimization algorithm was used to identify the menu design that minimized model pr...