BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Smartphones\, Crowds\, and the Cloud: Population Guided Sensing Sy
 stems - Nic Lane (Microsoft Research Asia)
DTSTART:20131115T140000Z
DTEND:20131115T150000Z
UID:TALK48845@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Sensor-enabled smartphones are creating new application domain
 s and transforming existing ones -- from mobile health to quantified-self\
 , mobile sensing is radically changing the way we collect and mine informa
 tion about people’s activities\, contexts\, and social networks. A numbe
 r of challenges stand in the way of delivering mobile sensing to the masse
 s. For example\, how do we develop mobile sensing systems that are capable
  of dealing with population diversity at scale\; more specifically\, how c
 an conventional approaches to classifying high-level human behavior cope w
 ith the level of diversity among users (e.g.\, demographics\, behavioral p
 atterns\, and lifestyle) and contexts found in large-scale systems.\nOver 
 the last few years I have been spearheading the development of population 
 guided sensing systems. These systems are designed to have a deep understa
 nding of both individual and group behaviors and utilize this information 
 to create symbiotic relationships between users and systems. In this talk\
 , I will present two key ideas that can help scale mobile sensing systems 
 from 100s of people to potentially 100s of millions based on population gu
 ided sensing. The first idea\, Community Similarity Networks (CSN)\, is an
  activity recognition framework that incorporates inter-person similarity 
 measurements into the classifier training process. CSN exploits crowdsourc
 ed sensor data to personalize classifiers with data contributed from other
  similar users. Second\, I will discuss CrowdSense@Place (CSP)\, which com
 bines crowd labeling and data collection with a series of multi-modal clas
 sifiers to link place visits to place categories (e.g.\, shopping\, gym\, 
 and restaurant). These techniques combine to move mobile sensing forward: 
 nailing it before we scale it.\n\nBio: Nic Lane is a researcher at Microso
 ft Research Asia (MSRA) working in the mobile and sensing systems group (M
 ASS). Nic received his Ph.D. from Dartmouth College (2011) where he worked
  with his co-advisors Andrew Campbell and Tanzeem Choudhury at the interse
 ction of machine learning and mobile sensing. His dissertation helped pion
 eer community-guided techniques for learning models of human behavior that
  enable mobile sensing systems to better cope with diverse user population
 s encountered in the real-world. Nic is an experimental computer scientist
  who builds novel mobile sensing applications and systems based on well-fo
 unded computational models. His work has received a number of awards inclu
 ding best paper awards from Ubicomp ’12\, Mobicase ’12 and PhoneSense 
 ’11\, and a best paper nomination\n
LOCATION:FW26\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR