Theses and Projects

An introduction to the Computer Networks group

See a poster for a general overview, an anchor to our research activities, a list of social computing related or networking-related publications, and the annual report(s) for our recent activities.

Open Theses and Student Project Topics

The Computer Networks Group is always looking for motivated students to work on various topics. If you are interested in any of the projects below, or if you have other ideas and are willing to work with us, please don't hesitate to contact us.

• (B) Bachelor thesis
• (M) Master thesis
• (P) Student project

Super resolution technique for efficient video delivery

• New! Video/image encoding is important for image/video storage/delivery on Internet. It reduces file size by eliminating spatial-temporal redundancy. Along with the development of Deep Neural Network in the computer vision(CV) community, video/image encoding for DNN applications is becoming more and more crucial. This project attempts to compare the difference between video/image encoding for QoE and DNN applications; and explore the design space in the video/image encoding for DNN applications. We expect you have Digital Image Process and Computer Vision background, as well as programming skills like Python and C/C++.

Please contact Weijun Wang [weijun.wang@informatik.uni-goettingen.de] (B/M/P)

Super resolution technique for efficient video delivery

• New! Super-resolution (SR) is one of the fundamental tasks in Computer vision. Video delivery on Internet or in WAN is important for various applications, eg., video analytics and video viewing. This project attempts to explore the potential of SR for video delivery. We expect you have Data Science and Computer Vision background, as well as programming skills like Python.

Please contact Weijun Wang [weijun.wang@informatik.uni-goettingen.de] (B/M/P)

Road anomaly and driver behavior detection

New! Road situations such as road traffic, roadworks and damages are critical for both human and autonomous driving. For driving (or assisted) with humans, its important to detect how the driver behaves facing dynamic road situations. This project attempts to detect anomalous road situations and driver behaviors with multi-source data mining, fusion and machine learning techniques. We expect you have some data analytics and machine learning background, as well as programming skills like Python. Please contact Prof. Xiaoming Fu (B/M/P).

Assessing city livability with big data

• New! City livability is related to a number of factors, such as quality of life, job satisfaction, environment (green space, CO2/PM2.5, schooling/health support etc), policy, commuting time, entertainment. We utilize different data sources to understand their relation to the city livability, and analyze the coherent features which offer an evaluation framework for a city's attractiveness and livability for different types of citizens. We expect you have some statistics and machine learning background, as well as programming skills like Python.

Please contact Prof. Xiaoming Fu (B/M/P).

Socioeconomic analysis on commuters

• New! Understanding the commuter behaviour and the factors that lead to commuting are more important today than ever before. With steadily increasing commuter numbers, the commuter traffic can be a major bottleneck for many cities. The increasing awareness of a good work-life balance leads to more people wanting shorter commuting distances. The commuter behaviour consequently plays an increasingly important role in city and transport planning and policy making. This topic aims to infer knowledge from commuter data, analyzing the influence of GDP, housing prices, family situation, income and job market on the decision to commute. We expect you have some statistics and machine learning background, as well as programming skills like Python.

Please contact Prof. Xiaoming Fu (B/M/P)

Socioeconomic Status and Internet Language Usage

• New! Numerous people write social media posts and exchange messages with colleagues, friends, acquaintances or even strangers on different platforms. We would like to understand how the underlying social class membership (socioeconomic status) affects Internet users' language use, by investigating the sociolinguistic features in users' posts/messages across a multitude of datasets and their relationship to their socioeconomic status. We expect you have some statistics and textual analysis/natural language processing background, as well as programming skills like Python.

Please contact Prof. Xiaoming Fu (B/M/P)

Multimedia Resource Allocation for QoE Improvement by Deep Learning

• New! Deep learning has been widely used in various real-time applications and systems. Dynamic resource allocation for multimedia (e.g. Video) to improve QoE is an interesting topic. We need three students for this topic. We expect you have a background in deep learning and computer network, as well as programming skills like Python and Go.

(1) one to realize and improve the system for video transmission and network configuration according to resource allocation policy;

• You will use QUIC [1] protocol (Go language) to implement network allocation and place the server part on AWS/other clouds.

(2) one to implement the deep learning algorithm to design the controller for dynamic resource allocations.

(3) one student for the QoE model using deep learning.

Please contact Dr.Tingting Yuan [tingting.yuan@cs.uni-goettingen.de ] and Weijun Wang [weijun.wang@informatik.uni-goettingen.de](B/M/P)

Low Power, Wide Area (LPWA) technologies on smart cities

• New!The LoRaWAN specification is a Low Power, Wide Area (LPWA) networking protocol, which is attracting a lot of attention due to their ability to offer affordable connectivity to the low-power devices distributed over very large geographical areas. In this project, we plan to exploit the LoRaWAN technologies to improve the performance of applications in smart cities. More details can be found in this link Please contact Yali Yuan (B/M/P)

Machine Learning & deep learning on electronic healthcare records

In recent years, large amounts of health data, such as patient Electronic Health Records (EHR), are becoming readily available. This provides an unprecedented opportunity for knowledge discovery and data mining algorithms to dig insights from them, which can, later on, be helpful to the improvement of the quality of care delivery. This project will be mainly on using machine learning to analyze electronic healthcare dataset. Please contact Yachao Shao (B/M/P)

Machine Learning or Deep learning Method (Graph-based) on Recommending system or Network Traffic

This project will be provide students an opportunity to learn how to use machine learning or deep learning methods (espeically graph-based DL method) to solve problems in recommending systems or computer networks. The requirements include: 1) like (python) coding; 2) willing to learn DL knowledge; 3) willing to read and learn open source projects;4) Regular meeting and discussion via skype and email. Please contact [sding@cs.uni-goettingen.de Shichang Ding](B/M/P)

Machine Learning for Security and Privacy in Networks

1) QUIC protocol design for video streaming analysis. (B/M/P, at least familiar with one programming language). Please contact Yali Yuan (Assigned to Yuhan Wang and Pronaya Prosun Das)

2) Implement algorithms for improving the network anomaly detection. (B/M/P, at least familiar with one programming language). Please contact Yali Yuan ====

3) Implement algorithms for improving the privacy of vehicle communications. (B/M/P, at least familiar with one programming language). Please contact Yali Yuan

4) New! Privacy preservation for reinforcement learning. (B/M/P), at least familiar with one programming language-python. Please contact Dr. Tingting Yuan [tingting.yuan@cs.uni-goettingen.de ].

Completed Topics

Topic	Topic advisor	Initial readings	Description	Student
Bio-Data analysis (Student project)	Mayutan Arumaithurai			Assigned to Lindrit
Sentiment Analysis (Student project)	Hong Huang			Assigned to Beatrice Kateule
Analysis of Business Transitions: A Case Study of Yelp (Bachelor Thesis)	Hong Huang			Assigned to Marcus Thomas Khalil
Understanding Group Patterns in Q&A Services (Bachelor Thesis)	Hong Huang			Assigned to Jonas Koopmann
COPSS-lite : Lightweight ICN Based Pub/Sub for IoT Environments (Master Thesis)	Sripriya			Assigned to Haitao Wang
A ICN Gateway for IoT (Bachelor Thesis)	Sripriya			Assigned to Janosch Ruff
Build a personalized context-aware recommender system for customers according to their own interest.				Completed by Haile Misgna
Emotion Patterns Analysis in OSNs (Bachelor thesis Project)	Hong Huang,Xu Chen		We aim to study the emotion patterns in the Twitter service and predict the future emotion status of users.	Completed by Stefan Peters
Implementation of a pub/sub system (Student project)	Jiachen Chen Mayutan Arumaithurai		The aim of the work is to show how application layer intelligence cupled with network layer pub/sub can be beneficial to both users as well as network operators	Completed by Sripriya
Large Scale Distributed Natural Language Document Generation System (Student project at IBM)	Mayutan Arumaithurai		The work was done at IBM	Completed by Eeran Maiti
Investigate real time streaming tools for large scale data processing (Student project)	Mayutan Arumaithurai		The aim of the work is to compare real time streaming tools.	Completed by Ram
Software-Defined Networking and Network Operating System (Student project)	Mayutan Arumaithurai		SDN based ntwork operating system	Completed by Rasha
GEMSTONE goes Mobile (BSc Thesis/Student Project)	David Koll		Portation of a Decentralized Online Social Network to the Android Platform	Completed by Fabien Mathey and improved by Eeran Maiti
Transitioning of Social Graphs between Multiple Online Social Networks (BSc Thesis)	David Koll		Portation of friendship graphs between different Online Social Networks	Completed by Kai-Stephan Jacobsen
Prevention and Mitigation of (D)DoS Attacks in Enterprise Environments (BSc Thesis)	David Koll		An analysis of enterprise infrastructures and their vulnerarbility towards attacks from the outside.	Completed by David Kelterer
Sybils in Disguise: An Attacker View on OSN-based Sybil Defenses (Student Project and MSc Thesis)	David Koll		An analysis of fake detection approaches in social networks.	Completed by Martin Schwarzmaier
Design and Implementation of a distributed OSN on Home Gateways (Student project and Master's Thesis)	David Koll			Completed by Dieter Lechler

QUIC or Multipath QUIC Design

• New! Implement algorithms for improving QUIC or Multipath QUIC performance. (B/M/P, at least familiar with one programming language (eg. C++, go or Python).) Please contact Yali Yuan (Finished)

Segment Routing based SDN

• NEW! Winter 2018/2019 There are many topics opened for Master and Bachelor theses and projects. Please contact Osamah Barakat

Software Defined Networks (SDN)

• New! Implementing more Gavel application by exploiting Graph algorithms. (B/M/P) Osamah Barakat details

• New! Including a Graph Database engine into an SDN Controller. (B/M/P) Osamah Barakat details

• New! A graph database tuning. (B/M/P) Osamah Barakat details

Data Analysis with Bio data

• NEW! 2019 ' if you are interested in topics in this area please get in contact with Mayutan Arumaithurai

Data Crawling and analysis

• Large scale distributed Data crawling and analysis of a popular web service (B/M/P)

• New! Data crawling and analysis of Twitter (P) (Tao Zhao)

Massive Data Mining and Recommender System

• Data Mining of the Web : User Behavior Analysis (B/M/P) Hong Huang

• Building the Genealogy for Researchers (B/M/P)Hong Huang

• Recommender System Design (B/M/P)Hong Huang

• if you are interested in other topics in this area please get in contact with Hong Huang

Social Networking(finished)

• New! Goettingen Assistant: Android App Development (completed) (P) (Shichang Ding)
• Topic prediction in online social networks (B/M/P)(Hong Huang)
• Mining emotion patterns in online social networks (B/M/P)(Hong Huang)
• Mining human mobility pattern from intra-city traffic data (B/M/P) (Shichang Ding)

• For a full list of older topics please go here.