1. enabling eco-feedback and out-of-clinic health sensing
indirect
University of Washington
Eric C. Larson
UbiComp Lab
electrical
engineering
computer
science and engineering
ubiquitous sensing
15. digital signal
processing
digital signal
processing
machine
learning
machine
learning
HCI
mobile
phone
embedded references
image
processing
time
series
evol.
comp.
ensemble/
graphical
HCI
mobile
phone
embedded references
thermal
imaging
CHI 2010
ESPA 2012
facial
analysis
IJAEC 2010
image
fidelity
ICIP 2009
JEI 2010
power
harvesting
UbiComp 2010
gas
sensing
Pervasive 2010
water
sensing
UbiComp 2009
Pervasive 2011
CHI 2012
cough
sensing
UbiComp 2011
lung
function
UbiComp 2012
DEV 2013
interaction&
imageanalysis
sustainabilityhealth
16. digital signal
processing
digital signal
processing
machine
learning
machine
learning
HCI
mobile
phone
embedded references
image
processing
time
series
evol.
comp.
ensemble/
graphical
HCI
mobile
phone
embedded references
thermal
imaging
CHI 2010
ESPA 2012
facial
analysis
IJAEC 2010
image
fidelity
ICIP 2009
JEI 2010
power
harvesting
UbiComp 2010
gas
sensing
Pervasive 2010
water
sensing
UbiComp 2009
Pervasive 2011
CHI 2012
cough
sensing
UbiComp 2011
lung
function
UbiComp 2012
DEV 2013
interaction&
imageanalysis
sustainabilityhealth
17. digital signal
processing
digital signal
processing
machine
learning
machine
learning
HCI
mobile
phone
embedded references
image
processing
time
series
evol.
comp.
ensemble/
graphical
HCI
mobile
phone
embedded references
thermal
imaging
CHI 2010
ESPA 2012
facial
analysis
IJAEC 2010
image
fidelity
ICIP 2009
JEI 2010
power
harvesting
UbiComp 2010
gas
sensing
Pervasive 2010
water
sensing
UbiComp 2009
Pervasive 2011
CHI 2012
cough
sensing
UbiComp 2011
lung
function
UbiComp 2012
DEV 2013
interaction&
imageanalysis
sustainabilityhealth
18. digital signal
processing
digital signal
processing
machine
learning
machine
learning
HCI
mobile
phone
embedded references
image
processing
time
series
evol.
comp.
ensemble/
graphical
HCI
mobile
phone
embedded references
thermal
imaging
CHI 2010
ESPA 2012
facial
analysis
IJAEC 2010
image
fidelity
ICIP 2009
JEI 2010
power
harvesting
UbiComp 2010
gas
sensing
Pervasive 2010
water
sensing
UbiComp 2009
Pervasive 2011
CHI 2012
cough
sensing
UbiComp 2011
lung
function
UbiComp 2012
DEV 2013
interaction&
imageanalysis
sustainabilityhealth
19. digital signal
processing
digital signal
processing
machine
learning
machine
learning
HCI
mobile
phone
embedded references
image
processing
time
series
evol.
comp.
ensemble/
graphical
HCI
mobile
phone
embedded references
thermal
imaging
CHI 2010
ESPA 2012
facial
analysis
IJAEC 2010
image
fidelity
ICIP 2009
JEI 2010
power
harvesting
UbiComp 2010
gas
sensing
Pervasive 2010
water
sensing
UbiComp 2009
Pervasive 2011
CHI 2012
cough
sensing
UbiComp 2011
lung
function
UbiComp 2012
DEV 2013
interaction&
imageanalysis
sustainabilityhealth
20. digital signal
processing
digital signal
processing
machine
learning
machine
learning
HCI
mobile
phone
embedded references
image
processin
g
time
series
evol.
comp.
ensembl
egraphic
al
HCI
mobile
phone
embedded references
thermal
imaging
CHI 2010
ESPA 2012
facial
analysis
IJAEC 2010
image
fidelity
ICIP 2009
JEI 2010
power
harvesting
UbiComp 2010
gas
sensing
Pervasive 2010
UbiComp 2009
Pervasive 2011
CHI 2012
cough
sensing
UbiComp 2011
UbiComp 2012
DEV 2013
interaction
imageanalysis
sustainabilityhealth
water
sensing
lung
function
64. initial study
Froehlich, J., Larson, E., Campbell, T., Haggerty, C., Fogarty, J., and Patel, S.N. HydroSense: infrastructure-mediated single-point sensing of whole-home water
activity. Proceedings of the 11th ACM international conference on Ubiquitous computing, (2009), 235–244.
Larson, E., Froehlich, J., Campbell, T., et al. Disaggregated water sensing from a single, pressure- based sensor: An extended analysis of HydroSense using staged
experiments. Pervasive and Mobile Computing, (2010).
65. initial study
• 10 homes
Froehlich, J., Larson, E., Campbell, T., Haggerty, C., Fogarty, J., and Patel, S.N. HydroSense: infrastructure-mediated single-point sensing of whole-home water
activity. Proceedings of the 11th ACM international conference on Ubiquitous computing, (2009), 235–244.
Larson, E., Froehlich, J., Campbell, T., et al. Disaggregated water sensing from a single, pressure- based sensor: An extended analysis of HydroSense using staged
experiments. Pervasive and Mobile Computing, (2010).
66. initial study
• 10 homes
• staged calibration
Froehlich, J., Larson, E., Campbell, T., Haggerty, C., Fogarty, J., and Patel, S.N. HydroSense: infrastructure-mediated single-point sensing of whole-home water
activity. Proceedings of the 11th ACM international conference on Ubiquitous computing, (2009), 235–244.
Larson, E., Froehlich, J., Campbell, T., et al. Disaggregated water sensing from a single, pressure- based sensor: An extended analysis of HydroSense using staged
experiments. Pervasive and Mobile Computing, (2010).
67. initial study
• 10 homes
• staged calibration
• ~98% accuracy at
identifying fixtures
Froehlich, J., Larson, E., Campbell, T., Haggerty, C., Fogarty, J., and Patel, S.N. HydroSense: infrastructure-mediated single-point sensing of whole-home water
activity. Proceedings of the 11th ACM international conference on Ubiquitous computing, (2009), 235–244.
Larson, E., Froehlich, J., Campbell, T., et al. Disaggregated water sensing from a single, pressure- based sensor: An extended analysis of HydroSense using staged
experiments. Pervasive and Mobile Computing, (2010).
77. totals
days
33
33
30
27
33
156
events
2374
3075
4754
2499
2578
14,960
events/day
71.9
93.2
158.5
92.6
78.1
95.9
compound
22.2%
21.8%
16.6%
32%
21.3%
21.9%
data collection
Larson, E., Froehlich, J., Saba, E., et al. A Longitudinal Study of Pressure Sensing to Infer Real- World Water Usage
Events in the Home. Pervasive Computing, Springer (2011), 50–69.
78. totals
days
33
33
30
27
33
156
events
2374
3075
4754
2499
2578
14,960
events/day
71.9
93.2
158.5
92.6
78.1
95.9
compound
22.2%
21.8%
16.6%
32%
21.3%
21.9%
data collection
Larson, E., Froehlich, J., Saba, E., et al. A Longitudinal Study of Pressure Sensing to Infer Real- World Water Usage
Events in the Home. Pervasive Computing, Springer (2011), 50–69.
most comprehensive labeled dataset
of hot and cold water ever collected
133. how can indirect sensing and machine
learning be used for health?
134. SpiroSmart
a smartphone based spirometer
that leverages on-device
microphone to help you keep track
of your lung function.
135. SpiroSmart
a smartphone based spirometer
that leverages on-device
microphone to help you keep track
of your lung function.lung function
spirometer
262. enabling eco-feedback and out-of-clinic
health sensing
indirect
University of Washington
Eric C. Larson
UbiComp Lab
electrical
engineering
computer
science and engineering
ubiquitous sensing
eclarson.com
eclarson@uw.edu
@ec_larson
Thank You!
thermal
imaging
facial
analysis
image
fidelity
power
harvesting
gas
sensing
cough
sensing
interaction&
imageanalysis
sustainabilityhealth
water
sensing
lung
function
263.
264. enabling eco-feedback and out-of-clinic health sensing
indirect
University of Washington
Eric C. Larson
PhD Candidate in School of Electrical and Computer Engineering
UbiComp Lab
electrical
engineering
computer
science
ubiquitous sensing
eclarson.com
eclarson@uw.edu
@ec_larson
acknowledgments:
Jon Froehlich
Leah Findlater
Elliot Saba
Eric Swanson
Tim Campbell
Gabe Cohn
Mayank Goel
TienJui Lee
Sidhant Gupta
Josh Peterson
Conor Haggerty
Jeff Beorse
Shwetak Patel
Les Atlas
James Fogarty
Jeff Bilmes
Margaret Rosenfeld