Direkt zum Inhalt | Direkt zur Navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Sektionen
Benutzerspezifische Werkzeuge
Sie sind hier: Startseite Theses A web-tool for a Distributed Analytics platform

Contact

Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

A web-tool for a Distributed Analytics platform

Thesis type
  • Bachelor
Status Running
Supervisor(s)
Advisor(s)

Advanced analytics could power the data collected from numerous sources, such as data warehouses, data lakes or mobile apps and devices. 

Using this data for decision making and recommender systems could help to solve important social challenges such as improving the health and well-being of citizens. However, the sensitive nature of the data prohibits organizations from sharing the data. 

The Personal Health Train (PHT) is a novel approach, aiming to establish a distributed data analytics infrastructure enabling the (re)use of distributed healthcare data, while data owners stay in control of their data. The main principle of the PHT is that data remains in its original location, and analytical tasks visit data sources and are executed where data resides. The PHT provides a distributed, flexible approach to use data in a network of participants, incorporating the FAIR principles. 

It facilitates the responsible use of sensitive and/or personal data by adopting international principles and regulations. 

 

In general, this bachelor thesis includes the development of a web-based tool. Among (possible) additional features this tool should include:  

1) A monitoring component which visualizes different kinds of META-Data. For example, the current performance of the containerized PHT model, i.e. PHT train, or the current position of the PHT train inside the station network. First, a general PHT Architecture should be developed including all necessary components. In a further step, a basic META-Data specification for each component should be described. Based on the META-Data, the student should choose suitable methods to access the META-Data and suitable visualizing charts embedded in the monitoring component.  

2) An algorithm creation component which follows the policy of the visual programming paradigm. Instead of writing code, the user of this component should develop his/her algorithm by using geometric shapes defining the general structure of the algorithm. The tool automatically transforms the shapes into code and pushes it into a train. Those algorithms could include different ML algorithms or simple data querying procedures. 

During the development of this tool, the student should respect general software development principles like customizability and extendibility.  

 

If you are interested in this thesis, a related topic or have additional questions, please do not hesitate to send a message to welten@dbis.rwth-aachen.de 

 

References:

http://www.data-intelligence-journal.org/p/39/

Prerequisites

Web-/Frontend development experience

Artikelaktionen