Computer Science in Progress

Home   Artificial Intell.   Bio-exact   Chemistry   Computer Sci. BSc   Earth Sciences   Mathematics   Physics & Astr.   Science Educ.   Submit   Webmaster        


Displaying theses 1-10 of 268 total
Previous  1  2  3  4  5  6  7  8  9  10  11  Next  Search:

A.H. Yerlibucak
Bachelor programme: Informatica August 17th, 2017
Institute: UvA / Other Research group: UvA / Other Graduation thesis Supervisor: Taco Walstra
photo of the author
Automatical Music Genre Classification with Mel-Frequency Cepstral Coefficient
This study discribes what is needed to automatically classify music genres. The research consists of two parts; First of all, the feature extraction method and secondly, the classification of music using those features. Feature extraction is done by calculating the Mel-Frequency Cepstral Coefficients (MFCC). Classifying the pieces of music uses two supervised learning algorithms; Artificial Neural Network (ANN) and the k-nearest neighbor (k-NN). It is also investigated whether the classification of an entire piece of music differs from the classification of a fragmented piece of music. When classifying a fragmented piece of music, the fragments are classified separately. Then a Majority vote is performed to determine the genre of the entire piece of music.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 3430K)

B.J. van den Aardweg
Bachelor programme: Informatica August 11th, 2017
Institute: UvA / Other Research group: UvA / Other Graduation thesis Supervisor: Jurjen Helmus
Update of electric vehicle spotter system by combining data with pictures
The pressure to switch to electric vehicles is increasing. By reducing carbon emissions, air quality can be improved and climate change can be counteracted. To make the roll-out and use of electric vehicle charging stations as efficient as possible, the IDO-laad program was created. The research group uses a unique dataset that contains data of more than 5 million sessions in the Netherlands. However, this dataset does not contain information about the electric vehicles that have been charged during a charging session. Therefore, a system has been developed that recognizes vehicles with license plate recognition by means of photographs. After determining the charging station, this data is stored together with the information about the vehicle. In this thesis, some system failures were fixed and the information from the system is linked to charging sessions in the IDO-laad dataset. An analysis has been performed to demonstrate the added value and capabilities of the new data. In addition, it is discussed what the quality of the new dataset is. The results are promising: with a dataset of 400 recognized vehicles, information can be linked to over 100,000 charging sessions.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 2758K)

S. de Vries
Bachelor programme: Informatica August 11th, 2017
Institute: Informatics Institute Research group: Lecturer's Group Graduation thesis Supervisor: Martijn Stegeman
photo of the author
Code quality: generating good feedback on function decomposition
When teaching programming it is important to give feedback. This allows students to improve on their programming. As class size increases it gets harder to give enough good feedback to all students. For this reason it is useful to create tools that give automated feedback. In this project a tool to automatically generate feedback is created. This tool focuses on function decomposition in programming assignments of beginning programmers. It was then evaluated by comparing the detections and output of the tool against the feedback given by teaching assistants (TAs). The tool found around half the problems that were detected by the TAs and has a low rate of false positives. The feedback produced by the tool also matched the general line of the feedback given by the TAs and would therefore be useful to students.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 279K)

L.R. Lokhoff
Bachelor programme: Informatica July 17th, 2017
Institute: Informatics Institute Research group: Lecturer's Group Graduation thesis Supervisor: Robert Belleman
Algorithm that manages and edits video footage from the digital operating theatre
This thesis is about an algorithm that schedules processes on a videoserver. The processes are started only when enough resources remain on the videoserver to protect the most important process: recording videos.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 895K)

M.W.Y. Mo
Bachelor programme: Informatica July 13th, 2017
Institute: UvA / Other Research group: UvA / Other Graduation thesis Supervisor: Ana Varbanescu
Block-iterative methods in tomography
In this thesis we explain the main idea in tomography and show how we can make a mathematical model of an X-ray scanner setup. In the algebraic method, we will deal with a system of linear equations Ax=b where the matrix A is very large and sparse. We first look at several iterative methods which solve these systems. We then continue with their general form as a block-iterative method, and investigate the influence of their parameters. We also look at implementations of these methods on a GPU, and discuss an optimization strategy.
picture that illustrates the research done
Scientific abstract (pdf 2K)   Full text (pdf 2588K)

D.M. Kruidenberg
Bachelor programme: Informatica July 9th, 2017
Institute: Informatics Institute Research group: Institute for Informatics - Other Graduation thesis Supervisor: Adam Belloum
Finding life trends using data analysis in Cookery
The application that was developed during this project finds life trends bases on emails. These emails were retrieved from the Gmail servers and were analysed by the Google Prediction API. The results are displayed graph in Jupyter Notebook. The project was made in Cookery. This is a cloud-based tool to develop scientific applications. It creates an abstraction layer between the developers and the scientists. This project was used to show the possibilities of Cookery.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 1454K)

P. Goddijn
Bachelor programme: Informatica June 28th, 2017
Institute: Other Research group: eScience center Graduation thesis Supervisor: Rob van Nieuwpoort
The applicability of Divide-and- Conquer: Graph Traversal in parallel on a computational grid
The Divide-and-Conquer programming system Satin was designed to make grid computing and other parallel computing forms easier and more efficient in use. In this thesis we look at how expressive it is by investigating how well graph traversal can be done using it. If it is concluded that a Divide-and-Conquer graph traversal program can be created using Satin, and if it is efficient, Satin and Divide-and-Conquer are more expressive and usefull than currently valued.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 429K)

M.B. van Mill
Bachelor programme: Informatica June 27th, 2017
Institute: Informatics Institute Research group: System and Network Engineering Graduation thesis Supervisor: Adam Belloum
A Cookery extension to simplify cloud service integrations
In recent years cloud services have become essential in our everyday lives. The linking of these cloud services allows people to have more powerful applications. The Cookery frame- work is a development tool which can be used to write cloud applications without having a deep understanding of programming. It is developed at the UvA and currently has not got a module which allows for integration with cloud service providers. This thesis proposes an architecture for a Cookery extension that allows for connections with cloud services. This architecture implements the OAuth 2.0 protocol for convenient authorization and just as the Cookery framework itself, the extension also supports Jupyter notebook integration. A working Github commit watcher is used as a proof of concept for the architecture. How- ever, more research is needed to enhance redundant aspects of the architecture and to add more cloud services to increase the value of the Cookery framework. The code developed in this thesis for the architecture and the proof of concept application will be available as a part of the Cookery Github.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 1516K)

T. van Zalingen
Bachelor programme: Informatica June 11th, 2017
Institute: Informatics Institute Research group: Lecturer's Group Graduation thesis Supervisor: dr. R.G. Belleman
Integrating digital microscopy images in an Electronic Data Capture system
Digitisation for clinical research allows for better sharing. Whole slide imaging is the creation of digital slides from a microscopy slide and viewing these images through a computer instead of a microscope. In this thesis a model is presented to predict hardware specifications for a whole slide imaging system according to future demand. The validity of the model is tested.
picture that illustrates the research done
Scientific abstract (pdf 1K)   Full text (pdf 1588K)

A. Pelser
Bachelor programme: Informatica June 9th, 2017
Institute: Informatics Institute Research group: Computer Systems Architecture Graduation thesis Supervisor: Sebastian Altmeyer
Using Automated Trace Generation for Trace-based Design-space exploration
This thesis is about finding or designing optimal embedded hardware architectures for software applications (also known as Design Space Exploration). Several tools exist that are specifically designed for this purpose, and many of them require the execution traces of a program. However, to make sure that the resulting hardware configurations will run the application fast and reliably enough under all circumstances, the execution traces given to these tools should include the ones belonging to a program’s ‘corner cases’ - its worst case behaviour with respect to various metrics, related to what instructions the program may execute. Examples of these metrics are the number of memory accesses, and the total number of instructions executed. The goal of this project was to automate this process, by finding the correct tools for the individual steps, and connecting them by means of a Python script. The ideal end result would be a tool chain that makes it easy for users to generate a good estimate of a program’s corner cases, as well as the corresponding input values and execution traces.
picture that illustrates the research done
Scientific abstract (pdf 2K)   Full text (pdf 229K)

Previous  1  2  3  4  5  6  7  8  9  10  11  Next  

This page is maintained by thesis@science.uva.nl