October 28, 2014 - October 28, 2014
Webinar: Design of Experiments in pSeven to improve further data analysis or optimization operations
Design of Experiment (DoE) is an important starting point for most data analysis and optimization tasks. It is a method of choosing the values of parameters varied in a series of experiments or measurements, supporting the initial stage of constructing surrogate models, performing sensitivity analysis and optimization.
During this webinar, various pSeven’s techniques and capabilities to perform DoE are demonstrated:
- Application of Space filling techniques, providing the uniformity in the design space for a specified number of samples
- Capabilities to generate training and test samples, construct approximations and calculate errors of approximation
- Application of Adaptive DoE techniques, allowing to control the process of surrogate modeling via adaptive sampling plan, which improves the quality of the approximation: you get as accurate approximation as possible for the smallest possible sample size