Random Diagnoses Trajectory Generator
Name
Artjom Valdas
Abstract
One of the first steps in data science is data collection. Sometimes the data is private and cannot be accessed in any way, especially those concerning personal data. This bachelor’s thesis is about creating a program that generates data about patients close to real ones, as well as times and diagnoses that can exacerbate or, conversely, reduce future diseases. Such data can be used to train artificial neural networks and predict future diseases. Because the data is completely random and generated based on a simple model, it does not pose a privacy risk to anyone, and secondly, it is known exactly which model the data is derived from. Thus, in the analysis of these data, it is possible to validate the usefulness of the analytical method for a particular model.
Graduation Thesis language
Estonian
Graduation Thesis type
Bachelor - Computer Science
Supervisor(s)
Jaak Vilo
Defence year
2021