Bachelor thesis - Design of database of technologies using renewable energy sources for small investors
- Title in czech: Návrh databáze technologií využívajících obnovitelné zdroje energie pro drobné investory
- The text of thesis is in czech, the source code is in english
- Link to download text of thesis pdf
- Link to download final presentation slides pdf
The thesis describes the database design according to the specific assignment, which is to create a database of technologies using renewable energy sources for small investors. The assignment is a reaction on the demand of ECO trend s.r.o. comapny. The aim is to examine the current situation of available databases in a similar fields, list the requirements of the application, describe the methodology of relational database design and propose specific database according to these requirements. In the context of the requirements, I focused mainly on their formulation. One of the requirements is also a draft of a form, which evaluates potential investments in products listed in the database. In a part of this draft I consider suitable methods of evaluation of the investments. In the context of database design, I focused on the conceptual, logical and physical design of a specific relational database. The main result of this work is the documentation of the requirements, database design for the specific application, and the script that may be used to create the database on the database server.
use cases, investment evaluation, relational database design, SQL script
- Title in czech: Predikce kriminality
- The text and source code are in english
- Link to download text of thesis pdf
- Link to download final presentation slides pdf
Emphasis on work efficiency and the increasing interest in data processing, Machine learning and Artificial Intelligence caused that the predictive analysis becomes part of the police activities especially in the domain of criminality prevention. For example, the police patrols are scheduled based on the predictive analysis the most risk areas in the city. This thesis is focused on supervised learning methods and their capability to find hidden patterns in the real historical crime data. The objective is to predict future crime with a certain probability using the algorithms based on decision trees and neural networks.
Criminality prediction, predictive policing, Data mining, Machine Learning, Supervised learning, Classification, Random Forest, Gradient Boosting Machines, Deep learning, Convolution neural net, Recurrent neural net.