Ekin Gedik is a computer scientist that aims to detect, analyse and enhance social experiences with the help of wearable sensing and machine learning. His expertise lies in automatic analysis of individual social behaviour, group interactions and how these concepts connect to the general social experience.
He received his B.Sc. and M.Sc. degrees in Computer Engineering from Middle East Technical University (METU), Turkey in 2010 and 2013, respectively. During his M.Sc. studies, he actively worked as a researcher in a remote sensing project in collaboration with two major defence firms in Turkey. This project focused on the automatic classification of satellite and aerial imagery. He developed various algorithms for the detection of various targets using image processing and machine learning techniques.
In 2014, he relocated to the Netherlands and started his Ph.D. studies in the Socialy Perceptive Computing Group of TU Delft, under the supervision of Hayley Hung. During his Ph.D. he worked on applied machine learning and investigated various research topics including transfer learning and domain adaption for creating personalised social action detection models, effects of the group cardinality on the detection of F-formations, automatic experience estimation and personality estimation. He also designed and conducted real-life data collection events.
He currently holds a postdoctoral researcher position in the Socially Perceptive Computing group. His research interests span variety of topics in applied machine learning and social science including time-series data analysis, social signal processing, affective computing, computational behavioral science, individual and group behaviour, human activity detection, domain adaptation and transfer learning.
Personal website: ekingedik.github.io