Ubiquitous physiological sensing has the potential to
profoundly improve our understanding of human behavior, leading to more
targeted treatments for a variety of disorders. The goal of this work is
the development of novel computational tools to support the study of
addiction in the context of cocaine use. In this talk, I will present
our initial investigation into the detection of cocaine use using
wearable electrocardiogram (ECG) sensors including the design of a novel
clinical study of cocaine use, the development of a graphical
models-based computational pipeline for inferring ECG morphological
structure from noisy ECG waveforms, and the evaluation of different
feature sets for cocaine use detection. This is joint work with the
Wireless Sensor Networks Research Group at UMass Amherst and the Cocaine
Research Clinic at the Yale School of Medicine.

Bio: Benjamin Marlin joined the University of Massachusetts Amherst as
an assistant professor of Computer Science in fall 2011 where he
co-founded and co-directs the Laboratory for Machine Learning and Data
Science. His research interests are in machine learning with a focus on
models and algorithms for multivariate time series data. His applied
work focuses on machine learning-based analytics for clinical and mobile
health (mHealth). Marlin was a fellow of the Pacific Institute for the
Mathematical Sciences and the Killam Trusts at the University of British
Columbia prior to joining UMass. He received his PhD in machine learning
from the University of Toronto. Marlin is a 2014
NSF CAREER award recipient and a 2013 Yahoo! Faculty Research Engagement
Program award recipient. Marlin has served on the senior program
committee of top machine conferences including UAI and NIPS, and is an
organizing committee member for ICML 2015. He served as general co-chair
of the 2014 Meaningful Use of Complex Medical Data symposium.