University of Cambridge > Talks.cam > Centre for Mobile, Wearable Systems and Augmented Intelligence Seminar Series > Context and Behaviour Modelling of User and Urban Activities

Context and Behaviour Modelling of User and Urban Activities

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact ss2138.

Abstract: Context is the most influential signal in analysing human behaviours. Effective and efficient techniques for analysing contexts inherent in the spatio-temporal sensor data from the urban environment are paramount. It is important to observe and learn the context from which the data is generated in, particularly when dealing with heterogenous high-dimensional data from individuals and groups of users, generated either from personal devices or sensors embedded in buildings, cities, and urban areas. One main challenge in modelling user activities in urban areas is to discover meaningful correlations among the numerous sensor channels and other types of data from multiple domains. Data-driven models need to also reflect on the personalised behaviours of different users. On the other side of the coin, often data is generated by many companies without any information of individuals. However the analysis still needs to reflect different activity profiles. I will present our generic temporal segmentation techniques that we have used for multiple applications. A new concept of cyber, physical, social contexts will be introduced, and how they translate in various domain applications of our research for analysing occupant behaviours, and for personalised intelligent assistants. Finally, the data-driven models can be used as input for recommender systems for individuals and/or groups, and for optimising the routes and/or itineraries in multiple applications, from visitors in a shopping mall, to travelling parking inspectors and police officers.

Bio: Flora Salim is an Associate Professor at the Computer Science and IT (CSIT) discipline, School of Science, RMIT University, Melbourne, Australia, and a Deputy Director of the RMIT Centre for Information Discovery and Data Analytics (CIDDA). She leads the Context Recognition and Urban Intelligence group in CIDDA . A/Prof. Flora’s research interests include context-aware situational intelligence and spatio-temporal analysis, specifically in human mobility tracking, context and behaviour modelling, time-series prediction, and cross-domain data fusion and learning. She obtained her PhD from Monash University in 2009. She has received numerous awards for her work, including the Humboldt-Bayer Research Fellowship by Alexander von Humboldt Foundation and the Bayer Science & Education Foundation in 2019, Humboldt Fellowship for experienced researcher, Victoria Fellow 2018 (awarded by the Victorian government), the RMIT Vice-Chancellor’s Award for Research Excellence – Early Career Researcher 2016; the RMIT Award for Research Impact – Technology 2018; Victorian iAwards (2014), Australian Research Council (ARC) Postdoctoral Research Industry Fellow (2012-2015); IBM Smarter Planet Industry Skills Innovation Award (2010); and a Google Anita Borg Scholar (2008). Prior to her faculty appointment in CSIT , she was a postdoc in the Spatial Information Architecture Lab, part of the RMIT School of Architecture and Design, working on multiple design modelling and optimisation problems in architecture, engineering, and construction projects. Prior to her PhD, she was a Senior Software Engineer in mediaproxy, developing realtime signal and content monitoring solutions for TV & broadcasting companies. She is an Associate Editor of the PACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) and an Area Editor of Pervasive and Mobile Computing.

This talk is part of the Centre for Mobile, Wearable Systems and Augmented Intelligence Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity