סמינר מחלקתי

 Classification and Prediction in Multivariate Temporal Data via Time Intervals Mining

Dr. Robert Moskovitch  - Columbia University

Abstract:

Analysis of multivariate time stamped data, for purposes such as Temporal Knowledge Discovery, Clustering and Classification, introduces many challenges. Time stamped data can be sampled in a fixed frequency, commonly when measured by electronic means, but also in a non fixed frequency, often when made manually - a typical situation in biomedical data. Additionally, raw temporal data can represent durations of a continuous or nominal value represented by time intervals. Transforming time point series into meaningful time intervals, using a process often called Temporal Abstraction, is used to bring all the temporal variables, having various representations, into a uniform representation. In this talk KarmaLego, a fast time intervals mining method for the discovery of non-ambiguous Time Intervals Related Patterns (TIRPs) represented by Allen's temporal relations, will be presented. Then several uses of the discovered TIRPs will be demonstrated in the use for temporal knowledge discovery, classification of multivariate temporal data, using the KarmaLegoS framework, in which TIRPs are used as classification features. To increase the classification accuracy a novel supervised Temporal Discretization for Classification (TD4C) method will be introduced, consisting an evaluation on three real life datasets from the biomedical domain. Finally, preliminary results of the use of TIRPs for prediction of outcome events in patient data, such as clinical procedures, will be demonstrated on Columbia University Medical Center EHR data.

Bio:

Robert Moskovitch is currently a postdoctoral research scientist at the Department of Biomedical Informatics at Columbia University. Prior to that, he headed several Research and Development projects in Information Security at Deutsche Telekom Innovation Laboratories at BGU. He has served on several journal editorial boards, as well as on program committees of several conferences and workshops in Biomedical Informatics and in Information Security. He published more than fifty peer reviewed papers in leading journals and conferences, several of which had won best-paper awards. He holds a B.Sc., M.Sc., and a Ph.D. in Information Systems Engineering from Ben Gurion University, Israel. 

ההרצאה תתקיים ביום חמישי 27.11.14, בשעה 12:10 בחדר 206, בנין וולפסון הנדסה, הפקולטה להנדסה, אוניברסיטת תל-אביב.