back to list

Project: Going from raw data to meaningful and personalized multivariate events

Description

Discrete multivariate event sequences are discrete records of a state with multiple attributes that form a chronologically ordered sequence. Discrete multivariate event sequences can be found in domains ranging from healthcare to transportation. Nevertheless, generating and analyzing such sequences from existing data is not straightforward, requiring visual-based human intervention, such as visual analytics systems, to aid in this process. For example, consider the medication intake of a patient. In this example, each medication intake is a discrete event. Each medication event has multiple attributes (multivariate), e.g. the doctor administering the medication and the patient's location. All these events form sequences of the medication intake per patient. In reality, it is sometimes unclear how to make these multivariate events from the raw data or compress the raw data to custom multivariate events based on the user's domain knowledge. For example, besides medication, the heart rate is also measured. How could one meaningfully combine these two variables to make multivariate events? Users may want events when a high heart rate is combined with specific medication values. In order to find these correlations or co-occurrences, users need help from visual analytics systems. In this project, you may use knowledge graphs to see if this shows these correlations and co-occurrences to go from raw event data to meaningful and personalized events. This master project involves four people; Fernando Paulovich, Stef van den Elzen, Leo Milhomem Franco Christino, and Sanne van der Linden. 

Details

Student

RL

Rianne van der Leeuw

Supervisor

Fernando Paulovich

Secondary supervisor

Stef van den Elzen