Diploma Theses for the Academic Year 2019-2020

Brief Description:

Predicting stock behavior is an issue that has been studied by many scientists and engineers and it forms today’s cutting-edge research. Great interest can be found in the combination of the financial science and the IT science, as the correct prediction of stock shares is of great economic importance for the obvious reason that an application could be profitable for either the creator or the customer. Using computing power today, which has reached unprecedented levels of power, we can build more complex and computationally powerful applications than ever before. A typical example for approximately the past 10 years, is the exponential growth in the development and use of “Artificial Intelligence” applications. More and more people are seeing the prospects and the countless applications that such models in the real world could give, as countless companies are already providing these services, such as the colossal companies Google and Amazon. Therefore, using Python programming language and its libraries like SciKit Learn and Keras we can create stock behavior prediction models. More specifically, we will study linear models of the SciKit Learn library such as Linear Regression and Tree Decision as well as Deep Learning models of the Keras library such as Long Short-Term Memory, which is a more accurate model than the previous models in terms of stock forecasting. The purpose of the current thesis is to analyze these forecasting techniques and learn how they can be applied in the financial data, as well as to become familiar with the Python programming language and its capabilities in data analysis and processing.

Required background knowledge: Python, SciKit Learn, Keras, Linear Regression, Tree Decision, Machine Learning, Deep Learning

Place: ZB203 – Research Laboratory TelSiP

Supervisor: Dr. Grigorios Koulouras, Assistant Professor

Student: Emmanouil-Andreas Loukaidis

Brief Description:

Verifiable Voting System based on Blockchain technology.

Required background knowledge: Blockchain

Place: ZB203 – Research Laboratory TelSiP

Supervisor: Dr. Grigorios Koulouras, Assistant Professor

Student: George Kallimanis

Brief Description:

Nowadays, Traveling Salesman Problem (TSP) attracts much attention due to the huge interest of Logistics Companies to reduce cost and maximize time efficiency to be more effective and competitive from opponents. From the late ’50s, researchers try to define the problem and create algorithms for solving that NP-hard problem. In definition, the TSP is the challenge of finding the shortest route for a single vehicle to traverse in order to deliver goods to a given set of customers. The objective of the TSP is to decrease the total route cost. This bachelor’s thesis will try to solve the TSP by using different algorithms to compare them, as a result, to find an optimal algorithm for it. Afterward, the problem will be transferred to Real World occasions by using Google’s APIs for accessing data as polar coordinates and distances or durations from point to point. Finally, the application will export a map powered by Google with the optimal route plot on it, to make this more handheld for drivers.

Required background knowledge: Travelling Salesman Problem (TSP), Python, Co-Lab

Place: ZB203 – Research Laboratory TelSiP

Supervisor: Dr. Grigorios Koulouras, Assistant Professor

Student: Elefterios Gryparis