BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computational Behavior Analysis through Wearables and Machine Lear
 ning -- Pushing the Boundaries towards usable Digital Health. - Thomas Plo
 etz (Georgia Tech)
DTSTART:20190221T150000Z
DTEND:20190221T160000Z
UID:TALK115786@talks.cam.ac.uk
CONTACT:Marco Caballero
DESCRIPTION:Abstract:\nWe live in an era in which the number of smartphone
 s is now greater than the number of humans living on Earth. As such\, the 
 field of mobile and ubiquitous computing is transforming many--if not all-
 -areas of our lives. With the next wave of technological breakthroughs now
  wearables\, such as smartwatches but also head-worn devices\, are becomin
 g mainstream. This overall transformation has great potential for many app
 lication areas. Most prominently\, it is now possible to continuously and 
 unobtrusively record rich behavior data that can inform objective health a
 ssessments thereby serving as basis for improved care and treatment\, and 
 thus wellbeing. \n\nThe basis for effective health assessments are robust 
 and reliable methods for human activity recognition -- more generally refe
 rred to as sensor-based Computational Behavior Analysis (CBA). From a tech
 nical perspective the analysis task translates into a time-series assessme
 nt problem\, yet with a number of domain-specific constraints and requirem
 ents. In this talk I will explore these specific challenges and give an ov
 erview of work in our group that is pushing the boundaries of CBA with spe
 cific focus on usable Digital Health. In response to challenges such as no
 isy sensor data\, ambiguous ground truth annotation\, and typically limite
 d size sample datasets we have developed and validated sensor data analysi
 s and machine learning methods that focus on these domain specifics and th
 us enable effective operation. I will illustrate how the constraints and r
 equirements of real-world application scenarios have allowed me and my tea
 m to push the boundaries of core sensor data analysis research. \n\nBio:\n
 Thomas Ploetz is a Computer Scientist with expertise and more than 15 year
 s of experience in Pattern Recognition and Machine Learning research (PhD 
 from Bielefeld University\, Germany). His research agenda focuses on appli
 ed machine learning\, that is developing systems and innovative sensor dat
 a analysis methods for real world applications. Primary application domain
  for his work is computational behaviour analysis where he develops method
 s for automated and objective behaviour assessments in naturalistic enviro
 nments\, thereby making opportunistic use of ubiquitous and wearable sensi
 ng methods. Main driving functions for his work are "in the wild" deployme
 nts and as such the development of systems and methods that have a real im
 pact on people's lives.\n\nIn 2017 Thomas joined the School of Interactive
  Computing at the Georgia Institute of Technology in Atlanta\, USA where h
 e works as an Associate Professor of Computing. Prior to this he was an ac
 ademic at the School of Computing Science at Newcastle University in Newca
 stle upon Tyne\, UK\, where he was a Reader (Assoc. Prof.) for "Computatio
 nal Behaviour Analysis" affiliated with Open Lab\, Newcastle's interdiscip
 linary research centre for cross-disciplinary research in digital technolo
 gies. 
LOCATION:LT2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR