KNOWLEDGE MANAGEMENT

AND DISCOVERY LAB

The KMD Lab presented two papers at Computer-Based Medical Systems 2016, Dublin, Ireland and Belfast, Northern Ireland .

• "Learning Pressure Patterns for Patients with Diabetic Foot Syndrome" by Uli Niemann, Myra Spiliopoulou, Fred Samland, Thorsten Szczepanski, Jens Gruetzner, Antao Ming, Juliane Kellersmann, Jan Malanowski, Silke Klose and Peter R. Mertens
• "Identifying relevant features for a multi-factorial disorder with constraint-based subspace clustering" by Tommy Hielscher, Myra Spiliopoulou, Henry Voelzke and Jens-Peter Kuehn

Myra Spiliopoulou gives a tutorial on "Medical Mining" at PAKDD 2016, Auckland, New Zealand, together with Ernestina Menasalvas (Univ. Polytecnica de Madrid) and Pedro Pereira Rodrigues (Univ. Porto) on April 2016.

Tutorial webpage of the PAKDD2016

Stefan Räbiger is the recipient of the award "Studentischer Forschungspreis 2015" for the paper "A Framework for Validating the Merit of Properties that Predict the Influence of a Twitter User", which was co-written by Prof. Myra Spiliopoulou. It was awarded by the faculty of Computer Science of the Otto-von-Guericke University. The paper is based on his master's thesis which was also supervised by Prof. Spiliopoulou.

Mrs. Nedime Tugce Habip, student of the Master Digital Engineering, is the recipient of the 2015 award "Otto-von-Guericke-Stipendium". The city of Magdeburg gives this award since 2003 to international students with excellent academic performance and social engagement. Next to her superior performance in her studies, Mrs. Habip engages in mentoring international students from the Master Digital Engineering and Master Data & Knowledge Engineering degrees and in further social activities in the University and in our city. Mrs. Habip was nominated by the studies coordinator of the Master Data & Knowledge Engineering, Prof. Myra Spiliopoulou.

The faculty of computer science Magdeburg has awarded KMD staff member Uli Niemann the faculty's 2014 Student Research Award for the article

U. Niemann, H. Völzke, J.-P. Kühn, and M. Spiliopoulou. Learning and inspecting classification rules from longitudinal epidemiological data to identify predictive features on hepatic steatosis. Expert Systems with Applications, (41)11:5405-5415, Elsevier BV, September 2014.

The article was written within the frame of scientific individual project during Uli's Master study of Business Information Systems and employs data from the Study of Health in Pomerania (SHIP). This work is a cooperation of the KMD research lab with the University Medicine Greifswald.

The prestigious journal Expert Systems with Applications (ESWA) from Elsevier emphasises on artificial intelligence and machine learning methods with a special focus on challenging practical applications. The article was submitted on 25.10.2013 and accepted on 20.02.2014. ESWA has an Impact Factor of 1.965 (2013) and a Five-Year Impact Factor of 2.254.

Myra Spiliopoulou and Georg Krempl will present a Tutorial on Mining Multiple Threads of streaming Data at PAKDD 2013, April 14-17, Gold Coast, Australia.

Stream mining is a mature area of research. However, several applications that require adaptive learning from evolving data do not seem to fit to the conventional stream mining paradigm. For example, a bank grants loans to customers and uses their data for model learning; the label (loan-payed-back YES or NO) arrives some years later, though, during which years the market may have changed drastically. Is this a stream mining problem? How many streams are there? We can distinguish between the stream of customers and the stream of their labels, which arrive with a time lag of years.

As another example, a hospital monitors patients with chronical diseases that come (ir)regularly to the hospital and undergo different tests; the streams of medical recordings and of signals (EEG, fMRI) can be used for learning. The hospital wants to learn a model on how the patients' health evolves in response to the disease and to medications. This problem seems completely different from the previous one, albeit streams of data are there in both cases.

In this tutorial, Myra Spiliopoulou and Georg Krempl bring together research advances on model learning and adaption for dynamic applications that collect and analyze different sources of dynamic data. In the introductory part of the tutorial, they present the classic stream mining paradigm and summarize the challenges being investigated in the state-of-the-art research.

Miro Schleicher has received the Marco Ramoni best paper award at the 20th Artificial Intelligence in Medicine (AIME) conference for his paper 'When can I expect the mHealth user to return? Prediction meets time series with gaps' (Miro Schleicher, Rüdiger Pryss, Winfried Schlee and Myra Spiliopoulou).

This work is within the frame of the UNITI project that encompasses machine learning methods for choosing the best treatment for each tinnitus patient. Treatments have an mHealth component, which assists the users towards self-empowerment and daily management of their disease. However, mHealth apps demand self-discipline; some users give up or interact very irregularly. The proposed method learns from the data of each user and from the absence of data, and it predicts if and when a user will start interacting again with the app.