On 14 November 2013, Emiel Caron has successfully defended his PhD thesis at Erasmus University Rotterdam with the title “Explanation of Expceptional Values in Multi-dimensional Business Databases”. Emiel has studied the question of extending the functionality of multi-dimensional business databases with diagnostic capabilities to support managerial decision-making. He developed formal methods for identifying exceptional values in OLAP approaches and offering automated explanations for these values. The methods Emiel developed will increase the efficiency of business analytics in this age of big data. Congratulations Emiel!
On 7 February 2013, Viorel Milea has successfully defended his PhD thesis at Erasmus University Rotterdam. The title of his thesis was “News Analytics for Financial Decision Support”. Viorel has investigated the incorporation of news into (automated) trading algorithms. This relates to three main tasks: i) the extraction of the information contained in news, ii) the representation of the information contained in news, and iii) the aggregation of this information into actionable knowledge. The approach was validated by designing and implementing three semantic systems: a system for the computational content analysis of European Central Bank statements, a system for incorporating news in stock trading strategies, and a time-aware system for trading based on analyst recommendations. Computational intelligence techniques form an integral part of Viorel’s approach, which led to publications in multiple scientific journals. Congratulations Viorel!
André Fialho has successfully defended his thesis today, at Instituto Superior Técnico of TU Lisbon. Like his colleague Federico, who graduated two days ago, André is one of the first bio-engineering graduates of the MIT-Portugal program. He received his degree with distinction. The title of André’s thesis was “Knowledge Discovery in Intensive Care Unit Shock Patients”. André studied advanced modeling and decision support techniques for the prognosis and the improvement of therapeutic interventions for shock patients in intensive care units (ICU), based on computational intelligence techniques. He has developed the very first of probabilistic fuzzy system models for decision support in the medical domain. These models were co-developed when André visited our group for six months in the past year. I and the whole healthcare cluster thank André for his companionship and wish him all the best in his future career.
Today, I have given an invited seminar at Instituto Superior Técnico on “process mining with clinial data: what is needed?” Process mining is a promising application of data mining. However, process mining from clinical data is not trivial. In my presentation, I discussed our healthcare cluster’s experience with process mining using data from an operation room and pointed out new research directions for increasing the applicability of process mining techniques when dealing with such data.
Today, Federico Cismondi has successfully defended his PhD thesis at Instituto Superior Técnico of TU Lisbon. Federico is one of the first bio-engineering graduates of the MIT-Portugal program and he received his degree with distinction. The title of his thesis was “Pre-Processing and Misclassifying Issues in Clinical Data Sets for Prediction and Intervention”. Federico has investigated how data pre-processing can be made effectively with clinical data. He proposed a novel classification scheme for the missing values in the data and has applied multi-objective model validation techniques to determine improved clinical decision making models. Federico shows that by using more advanced prediction models, many laboratory tests at intensive care units could be avoided, hence improving the quality of care for the patients and increasing the efficiency of the care processes. It is a nice example illustrating how intelligent decision support can change and improve care processes. It was a pleasure to have the discussion with you during your defense, Federico. Congratulations!