katayoun_farrahidata

Katayoun Farrahi

Katayoun Farrahi is a lecturer at Goldsmiths, University of London, and is involved in designing course material for the Data Science masters programme, particularly on big data applications.

The focus of her research is on methods (based on machine learning) for mining meaningful information from large scale data. Much of her research has focused on mobile phone data. She also works on mobile phone sensed data-driven applications – applications which can make use of knowledge about human behaviour extracted from mobile sensed data. One example is the simulation of epidemics from mobile phone sensed physical proximity data.

Prior to joining Goldsmiths, Katayoun was a research assistant at Idiap Research Institute. She obtained her PhD in Computer Science from Swiss Federal Institute of Technology in Lausanne (EPFL) in 2011.

Research

Epidemics & Mobile Phone Data
What if you use more realistic human interaction patterns from mobile phones (Bluetooth) to simulate epidemics? We take this one step further and propose to use communication logs obtained by mobile phones for contact tracing. Mobile phones have the potential to provide a “global sensor” for research in epidemiology and my work explores different methods for integrating this data in this domain.
Sequence Modeling with Latent Topic Models
The particular problem of mining long sequences from large-scale location data is of relevance for problems relating to mobile sensing and Reality Mining applications. Latent topic models are of particular interest for big data mining applications due to their unsupervised nature and ability to handle noise. The distant n-gram topic model (DNTM), visualized, is an extension of Latent Dirichlet Allocation (LDA), which can incorporate sequence data. This model has been tested on location data, particularly GPS and cell tower connection data to mine long duration sequences of location patterns.

Publications

Journal Articles

K. Farrahi, R. Emonet, M. Cebrian
Epidemic Contact Tracing via Communication Traces
PLoS ONE 9(5): e95133. May 1, 2014. doi: 10.1371/journal.pone.0095133

K. Farrahi and D. Gatica-Perez
A Probabilistic Approach to Mining Mobile Phone Data Sequences
Personal and Ubiquitous Computing, published online Feb. 2013, Vol. 18, No. 1, pp. 223-238, Jan. 2014

K. Zia, A. Riener, K. Farrahi, A. Ferscha
An Agent-Based Parallel Geo-Simulation of Urban Mobility during City-scale Evacuation
Simulation: Transactions of the Society for Modeling and Simulation, SAGE, May 2013

A. Ferscha, K. Farrahi, J. van den Hoven, D. Hales, A. Nowak, P. Lukowicz, D. Helbing
Socio-inspired ICT
The European Physical Journal Special Topics, Springer, Vol. 214, No. 1, pp. 401-434, Nov. 2012

A. Madan, M. Cebrian, S. Moturu, K. Farrahi, and A. Pentland
Sensing the `Health State` of our Society
IEEE Pervasive Computing, Vol. 11, No. 4, Oct.-Dec. 2012

K. Farrahi and D. Gatica-Perez
Discovering Routines from Large-Scale Human Locations using Probabilistic Topic Models
ACM Transactions on Intelligent Systems and Technology, Special Issue on Activity Recognition, Vol. 2. No. 1, 2011

K. Farrahi and D. Gatica-Perez
Probabilistic Mining of Socio-Geographic Routines From Mobile Phone Data
IEEE Journal of Selected Topics in Signal Processing, Special Issue on Signal and Information Processing for Social Networks, Vol. 4, No. 4, pp. 746 – 755, Aug. 2010

Thesis

K. Farrahi
A Probabilistic Approach to Socio-Geographic Reality Mining Ecole Polytechnique Federale de Lausanne, Thèse No. 5018, March 2011.

Conference Articles

K. Farrahi, R. Emonet, M. Cebrian
Predicting a Community’s Flu Dynamics with Mobile Phone Data
in CSCW, Vancouver, Canada, March 2015

M. Schedl, D. Hauger, K. Farrahi, M. Tkalcic
On the Influence of User Characteristics on Music Recommendation
in ECIR, Vienna, Austria, March 2015

K. Farrahi, M. Schedl, A. Vall, D. Hauger, M. Tkalcic
Impact of Listening Behavior on Music Recommendation
in ISMIR, Taipei Taiwan, Oct 2014

M. Schedl, A. Vall, K. Farrahi
User Geospatial Context for Music Recommendation in Microblogs
in ACM Special Interest Group On Information Retrieval (SIGIR), Australia, July 2014

K. Farrahi, K. Zia, A. Sharpanskykh, A. Ferscha, L. Muchnik
Agent Perception Modeling for Movement in Crowds
in Int. Conf. on Practical Applications of Agents and Multi-Agent Systems (PAAMS) Salamanca, May 2013

K. Farrahi, R. Emonet, and A. Ferscha
Socio-Technical Network Analysis from Wearable Interactions
in Proc. IEEE Int. Symp. on Wearable Computers (ISWC), Newcastle, Jun. 2012

K. Farrahi and D. Gatica-Perez
Extracting Mobile Behavioral Patterns with the Distant N-Gram Topic Model
in Proc. IEEE Int. Symp. on Wearable Computers (ISWC), Newcastle, Jun. 2012
Best Paper Award Nominee

A. Madan, K. Farrahi, D. Gatica-Perez, and A. Pentland
Pervasive Sensing to Model Political Opinions in Face-to-Face Networks
in Proc. Int. Conf. on Pervasive Computing (Pervasive), San Francisco, Jun. 2011

K. Farrahi and D. Gatica-Perez
Mining Human Location-Routines using a Multi-Level Approach to Topic Modeling
in IEEE Int. Conference on Social Computing, Symposium on Social Intelligence and Networking (SocialCom-SIN), Minneapolis, Aug. 2010

K. Farrahi and D. Gatica-Perez
Learning and Predicting Multimodal Daily Life Patterns from Cell Phones
in Proc. Int. Conf. on Multimodal Interfaces (ICMI-MLMI), Cambridge, Nov. 2009

K. Farrahi and D. Gatica-Perez
What Did You Do Today? Discovering Daily Routines from Large-Scale Mobile Data
in Proc. ACM Int. Conf. on Multimedia (MM), Vancouver, Oct. 2008

K. Farrahi and D. Gatica-Perez
Discovering Human Routines from Cell Phone Data with Topic Models
in Proc. IEEE Int. Symposium on Wearable Computers (ISWC), Pittsburgh, Sep. 2008

K. Farrahi and D. Gatica-Perez
Daily Routine Classification from Mobile Phone Data
in Proc. Workshop on Machine Learning and Multimodal Interaction (MLMI), Utrecht, Sep. 2008