Our paper (Y. Xue, M. Hauskrecht) on active learning of multi-class classifiers from ordered class set feedback has been accepted to AAAI 2019.
Our paper (S. Liu, A. Wright, M. Hauskrecht) on anomaly detection for Rule-count time series was accepted for publication in Artificial Intelligence in Medicine journal.
MS in Computer Science, Department of Computer Science, Slovak Technical University, Bratislava, Slovakia, May 1988.
PhD in Computer Science, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, August 1997.
The main areas of my research interest are: machine learning and data mining; time series modeling and analysis; and, planning and optimization in the presence of uncertainty. The majority of my research work is driven by biomedical informatics problems. More specifically, my current work focuses on the development of modern machine learning technologies for analysis of
high dimensional time-series data in electronic health record (EHR), and their application to real-time adverse event detection, and real-time clinical monitoring and alerting.
Machine learning methods for high-throughput bioinformatics data. Statistical methods for identification of hidden regulatory pathways
from gene expression data. Algorithms for preprocessing and analysis of high-throughput MS proteomic and genomic data and for biomarker discovery. Methods for protein ID in whole sample proteomics using prior knowledge
Current research funding:
NIH/NIGMS R01GM088224. R01 Real-time detection of deviations in clinical care in ICU data streams (Principal Investigator)
NIH/NLM R01LM011966. Improving Clinical Decision Support Reliability Using Anomaly Detection Methods (PI: Adam Wright, Partners Healthcare, Milos serves as a UPitt PI)
NIH/NLM. Learning Electronic Medical Record. (PI: Shyam Visweswaran, Milos is a co-investigator)
