Publication Date

5-2015

Date of Final Oral Examination (Defense)

2-20-2015

Type of Culminating Activity

Thesis

Degree Title

Master of Science in Computer Science

Department

Computer Science

Supervisory Committee Chair

Timothy Andersen, Ph.D.

Supervisory Committee Member

Jeff Habig, Ph.D.

Supervisory Committee Member

Elena A. Sherman, Ph.D.

Abstract

VPEvolve is a free and open source application that utilizes a Visual Programming Environment (VPE) for the setup of the Genetic Algorithm (GA), for optimization of computational models. Specifically, the User Interface uses connected glyphs to represent the genetic operators of mutation, reproduction, fitness and selection. These glyphs give the user an intuitive way to set the parameters for the GA, and better visualization of the population's flow through these operators.

VPEvolve is currently being developed alongside research being done in Biocomputing to create models of cellular regeneration based on the regenerative properties of Planaria or flatworms. Since these models are difficult to produce by hand, GAs can be particularly useful to facilitate the process of model creation and validation. VPEvolve is a client-side application that allows the user to setup the parameters for the GA, runs a search using the GA, utilizes a modeling platform, such as CellSim (Cellular Simulator), to perform simulations, evaluates the fitness of each individual with user-defined fitness evaluators and presents the fitness values of the individuals in a population to the user as the evolutionary search is performed.

Share

COinS