Open Data Laboratory (OpenDataLab)

The OpenDataLab is an open laboratory that was established in cooperation with Profinit EU. It is mainly intended for students; however, also other people interested in open data can come and visit us following prior arrangement. Our main goal is to provide ideas, help and topics for students’ course projects and theses.

More about us

What we do

In our laboratory, we primarily focus on processing of available data, of which huge amounts exist, but whose use lags behind. In the lab, new applications, analyses and conclusions can be created using this data that will make everyday life simpler. In this way, processing of this data provides an opportunity to spare or streamline the existing processes and improve people’s everyday lives.

You can sample some of our projects at GitHub. The projects concern, for example, invoices from ministries and other organizations, public procurement, bid prices or the Prague Integrated Transport system. However, with each year, the number of published data increases, there are datasets of provided solar energy subsidies and EU subsidies, weather, electoral participation, personal bankruptcies, etc.

The laboratory is involved in research in the field of open and linked data. We also focus on efficient exploration of the linked data environment or data administration in heterogeneous and dynamic environments. This helps in the solution of practical tasks in the above mentioned areas, but not only in them. At the same time, this helps create demand for opening and linking of other interesting sources of data of the public administration that can subsequently be publicly accessible in the National Open Data Catalogue.

Another interesting avenue is the research into the use of knowledge graphs and bases for enrichment of open data and vice versa. The increasing amount of open data from various fields can significantly enrich the knowledge bases that are used in a number of other applications.

We also solve tasks related to text processing. For instance, the register of contracts contains a large amount of machine-readable documents. We have solutions for categorization of documents, searching for addresses, contact information and common parts of documents in a scope comparable to that of commercial apps. We have also been tasked with processing of images and sound.

In the lab, students can work with open data sources. This provides them with a unique opportunity to study data on transportation services, the government’s economic policy, the environment and many other areas in their course projects and theses.

Equipment

Students usually work independently from home or from school. We also have four working stations with monitors for OpenDataLab students at the International Business Center. Students can also use our internal GPU or the CTU computational cluster.

The lab’s activities are focused on these topics

Publications

Anomaly detection in particulate matter pollution open data

Authors
Podsztavek, O.; Kuchař, J.
Year
2019
Published
DATA A ZNALOSTI & WIKT 2019. Košice: Technická univerzita v Košiciach, 2019. p. 66-71. ISBN 978-80-553-3354-0.
Type
Proceedings paper
Annotation
The paper is focused on an anomaly detection in particulate matter pollution open data. There are several street lights in Prague (Karlín) providing measurements from various sensors, including PM10. In this paper, we use machine learning algorithms for the anomaly detection: linear regression and LSTM neural network.

Contact person

Where to find us

Open Data Laboratory
Department of Software Engineering
Faculty of Information Technology
Czech Technical University in Prague

Thákurova 7
Prague 6 – Dejvice
160 00

The Open Data Laboratory is operated by the Faculty of Information Technology CTU in cooperation with Profinit EU

International Business Center
Pobřežní 620/3
Prague 8

The person responsible for the content of this page: doc. Ing. Štěpán Starosta, Ph.D.