iTable – predictive policing


iTable – predictive policing


Policing is increasingly becoming an information game. In order to be prepared and do their job well, police officers must quickly and correctly interpret large amounts of data. To facilitate this, LIACS is working with the National Police and the University of Utrecht to develop a decision-support system that allows police officers to combine and make sense of data from different sources.

There are two sub-projects. Subproject 1 concerns the development of an interface for the <a href=”>surface-like</a&gt; “iTable”, a state-of-the-art visualization system that allows for intuitive and collaborative navigation through multiple data sources (e.g. maps, timelines, social nets). In subproject 2 the aim is to develop a system that, by learning from (open and closed) available data, aids the users of the iTable environment by suggesting new links between the data (e.g. scenarios, social relations).

Required skills:
– Visualization and user interfaces (subproject 1)
– Machine learning/data mining (subproject 2)
– Data modeling
– Programming

Experience with .NET and the Google Earth/Google Maps API is most likely to be highly desirable (particularly for subproject 1).
Ability to speak Dutch is a definite plus

LIACS/UU and National Police

Student Profile
CS, AI or technical ICT in Business

Time frame
Sept 2014 – start sooon

Scientific Challenge
Sensemaking and visualization (subproject 1)
State of the art data visualization is a challenge, and creating a flexible design that allows incorporation of future data sources even more so. The student will have to research the state-of-the-art in computer-supported collaborative sensemaking and find a way to correctly present multiple data sources to mutiple users simultaneously.

Machine learning and databases (subproject 2)
Learning new relations and patterns from existing data can be hard, especially when the data is fragmented and not uniformly formatted. The student will have to delve into the existing `big data’ research and come up with innovative ways to structure and combine different data sets.

Aske Plaat (LIACS)
Floris Bex (Univ Utrecht)


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s