iCNS Distinguished Lecture: Lifting the Fog by Harnessing Interactions Across Diverse Systems

Silhouette of a young woman head with network hologram and graph over purple background with purple "machine learning" text

Department of Electrical and Computer Engineering

Location: Gateway North 103

Speaker: Zoran Obradovic, Laura H. Carnell Professor of Data Analytics, Data Analytics and Biomedical Informatics Center, Computer and Information Sciences Department, and Statistics Department, Temple University

ABSTRACT

This presentation will discuss our machine learning approaches for identifying, categorizing, and forecasting events of interest from limited data and imprecise labels. This is accomplished by integrating multimodal structured and unstructured information and jointly modeling multiple types of interactions in temporal multilayer networks. Our findings indicate that a learning framework that integrates information from various sources of differing quality and resolution can significantly enhance informed decision-making.

BIOGRAPHY

Portrait of Zoran Obradovic

Zoran Obradovic is a Distinguished Professor and Center Director at Temple University, an Academician at the Academia Europaea (the Academy of Europe), and a Foreign Academician at the Serbian Academy of Sciences and Arts. He has mentored approximately 50 postdoctoral fellows and Ph.D. students, many of whom have established independent research careers at academic institutions (e.g., Northeastern University, Ohio State University) and industrial research labs (e.g., Amazon, eBay, Facebook, Hitachi Big Data, IBM T.J. Watson, Microsoft, Yahoo Labs, Uber, Verizon Big Data, Spotify). Zoran serves as the editor-in-chief of the Big Data journal and is the steering committee chair for the SIAM Data Mining conference. He is also a member of the editorial boards for 13 journals and has held roles as general chair, program chair, or track chair for 11 international conferences. His research interests encompass data science and complex networks in decision support systems, addressing challenges related to big, heterogeneous, spatial, and temporal data analytics, motivated by applications in healthcare management, power systems, and earth and social sciences. His studies have received funding from AFRL, DARPA, DOE, NIH, NSF, ONR, the PA Department of Health, US Army ERDC, US Army Research Labs, and various industry sources. He has published around 450 articles and has been cited approximately 35,000 times (H-index 69). For more details, see http://www.dabi.temple.edu/zoran-obradovic.