BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Clustering insomnia pattern and learning sleep quality from daily 
 logs - Shaun Park (KAIST)
DTSTART:20190905T140000Z
DTEND:20190905T150000Z
UID:TALK128977@talks.cam.ac.uk
CONTACT:Marco Caballero
DESCRIPTION:Abstract:\n\nPrecision psychiatry is a new research field that
  uses advanced data mining over a wide range of neural\, behavioral\, psyc
 hological\, and physiological data sources for classification of mental he
 alth conditions. The talk will present a computational framework for predi
 cting sleep efficiency of insomnia sufferers. A smart band experiment is c
 onducted to collect heterogeneous data\, including sleep records\, daily a
 ctivities\, and demographics\, whose missing values are imputed via Improv
 ed Generative Adversarial Imputation Networks (Imp-GAIN). Equipped with th
 e imputed data\, we predict sleep efficiency of individual users with a pr
 oposed interpretable LSTM-Attention (LA Block) neural network model. We al
 so propose a model\, Pairwise Learning-based Ranking Generation (PLRG)\, t
 o rank users with high insomnia potential in the next day. We discuss the 
 implications of our findings from the perspective of a psychiatric practit
 ioner. Our computational framework can be used for other applications that
  analyze and handle noisy and incomplete time-series human activity data i
 n the domain of precision psychiatry.\n\nBio:\n\nSungkyu (Shaun) Park is a
  Ph.D. candidate in the Graduate School of Culture Technology at KAIST. He
  is interested in understanding human behaviors and psychiatric disorders 
 in the wild through the lens of large-scale data. His research focuses on 
 techniques for developing mobile/wearable applications to retrieve data an
 d for developing interpretable prediction models on mental health domains.
  He has interned at Nokia Bell Labs\, Cambridge this summer and owned a st
 artup aiming to launch an intervention app for insomnia\, developed based 
 on the current research.
LOCATION:FW26\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR