BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling a Community's Health and Mobility Patterns with Mobile P
 hone Data - Katayoun Farrahi (Goldsmiths\, University of London)
DTSTART:20141016T140000Z
DTEND:20141016T150000Z
UID:TALK54141@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Mobility patterns and interactions sensed by mobile phones pro
 vide a new source for many applications both in research and industry. In 
 this talk\, I will discuss two mobile sensed data-driven applications\, on
 e based on mobility patterns and the other based on interaction patterns. 
 \n\nThe study of such human-centric massive datasets requires new mathemat
 ical models. A novel probabilistic topic model will be presented\, the dis
 tant n-gram topic model (DNTM)\, which has been developed to address the p
 roblem of learning long duration human location sequences. The DNTM is bas
 ed on Latent Dirichlet Allocation (LDA) and is advantageous for mining hum
 an behaviour patterns for many reasons.\n\nHuman interactions sensed ubiqu
 itously by cellphones can benefit many domains\, particularly for monitori
 ng the spread of disease. A community of 72's flu patterns have been colle
 cted simultaneous to their interactions sensed by mobile phone Bluetooth l
 ogs. The focus of this work is to determine the accuracy of incorporating 
 interaction data into dynamic epidemiology models for infection prediction
 . We obtain errors of less than 2 infected people on average (when predict
 ing the number of infected people over time considering a population of 72
  people) and precisions of approximately 30% (when predicting exactly whic
 h individual was infected at a given time).\n\n\nBiography\nKate (Katayoun
 ) Farrahi is a lecturer at the University of London\, Goldsmiths. Her rese
 arch focuses on large-scale human behavior modeling and mining\, with spec
 ial interest in data science\, computational social sciences\, mobile phon
 e sensor data\, and machine learning. Farrahi received her Ph.D. in Comput
 er Science from the Swiss Federal Institute of Technology (EPFL) Lausanne\
 , and the Idiap Research Institute\, Switzerland. She has spent time as an
  intern at MIT and is a recipient of the Google Anita Borg scholarship\, a
 nd the Idiap research award.\n
LOCATION:FW26\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR