Download - Hydro pervasive2011 eric_larson
![Page 1: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/1.jpg)
design:use:build: ubicomp lab
universityofwashington sustainabilityresearchuniversityofwashington
A Longitudinal Study of Pressure Sensing to Infer Real-World Water Usage Events in the Home
Eric Larson, Jon Froehlich, Elliot Saba, Tim Campbell, Les Atlas, James Fogarty and Shwetak Patel
![Page 2: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/2.jpg)
kitchen sink 28 gallons
refrigerator 0.3 gallons
dishwasher 6.5 gallons
today‘s usage
![Page 3: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/3.jpg)
toilet 78.4 gallons
shower 62.4 gallons
bath 6.5 gallons
bathroom sink 1 4.2 gallons
bathroom sink 2 0.8 gallons
today‘s usage
![Page 4: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/4.jpg)
toilet 78.4 gallons
shower 10.4 gallons
bath 0.0 gallons
bathroom sink 1 1.2 gallons
bathroom sink 2 0.8 gallons
shower 52.4 gallons
bath 6.5 gallons
bathroom sink 1 3.2 gallons
bathroom sink 2 2.4 gallons
today‘s usage: hot vs. cold
![Page 5: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/5.jpg)
sustainability applications
![Page 6: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/6.jpg)
assisted living applications
last active: 10:03PM
last active: 10:08PM
last active: 7:20AM
last active: 10:09PM
last active: 10:33PM
![Page 7: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/7.jpg)
at ubicomp09, we introduced hydrosense
![Page 8: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/8.jpg)
• single, screw-on sensor • identifies fixture usage • estimates flow
hydrosense
Froehlich et al., UbiComp2009; Larson et al., PMC2010
![Page 9: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/9.jpg)
hydrosense uses pressure waves to identify usage
bath open
dishwasher open
upstairs toilet flush
downstairs toilet flush downstairs shower open
kitchen sink cold open
kitchen sink hot open
kitchen sink hot open
![Page 10: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/10.jpg)
controlled experiments • 2 researchers per site • 5 trials per valve
experimental script • valve opened full stop • pause for ~5 seconds • valve closed
ubicomp2009 feasibility study
![Page 11: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/11.jpg)
ubicomp2009 data collection
![Page 12: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/12.jpg)
successfully demonstrated the potential of using pressure waves to identify fixture usage
ubicomp2009 paper
evaluation method staged experiments all faucet handles were operated at approximately the same flow rates all fixtures were tested in isolation
algorithm each pressure wave treated independently did not consider context of usage was not probabilistic
![Page 13: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/13.jpg)
what we’re really interested in…
how well will hydrosense perform on real-world
water usage data?
![Page 14: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/14.jpg)
brushing teeth
![Page 15: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/15.jpg)
shaving
![Page 16: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/16.jpg)
bathing
![Page 17: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/17.jpg)
paw washing
![Page 18: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/18.jpg)
watertowerwater tower
thermalexpansion
tank
hosespigot
utility water meter
pressure regulator
laundry
bathroom 1
hot water heater bathroom 2
dishwasher
incomingcoldwaterfromsupplyline
kitchen compound events
![Page 19: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/19.jpg)
pervasive 2011 contributions longitudinal study of real-world water usage and the resulting dataset a new probabilistic approach to water usage classification demonstrate that this new approach can accurately classify real world data
1
2
3
![Page 20: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/20.jpg)
ground truth sensors
5-week deployment
classification algorithm
classification results
![Page 21: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/21.jpg)
ground truth sensors
5-week deployment
classification algorithm
classification results
![Page 22: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/22.jpg)
ground truth labels manual
kitchen sink cold open
cold close
kitchen sink hot
open hot
close
bathroom sink cold open
cold close
automatic
![Page 23: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/23.jpg)
watertower
thermalexpansion
tank
hosespigot
utility water meter
pressure regulator
laundry
bathroom 1
hot water heater bathroom 2
dishwasher
incomingcoldwaterfromsupplyline
kitchen
![Page 24: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/24.jpg)
how can we obtain water usage labels at the valve-level?
![Page 25: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/25.jpg)
this is actually a challenging question…
![Page 26: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/26.jpg)
kitchen sink bathroom sink
toilet
bath shower
laundry basin washing machine dishwasher
function across fixtures
![Page 27: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/27.jpg)
after many failed attempts
![Page 28: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/28.jpg)
reed switch
3-axis accelerometer
hall effect
unidirectional ball switch
omnidirectional ball switch
xbee wireless modem fixture usage sensor board
custom ground truth data collection system
![Page 29: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/29.jpg)
reed switch
3-axis accelerometer
hall effect
unidirectional ball switch
omnidirectional ball switch
xbee wireless modem fixture usage sensor board
custom ground truth data collection system
“wake up” sensors
![Page 30: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/30.jpg)
reed switch
3-axis accelerometer
hall effect
unidirectional ball switch
omnidirectional ball switch
xbee wireless modem fixture usage sensor board
custom ground truth data collection system
fixture handle position sensors
![Page 31: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/31.jpg)
accelerometer
![Page 32: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/32.jpg)
reed switch
3-axis accelerometer
hall effect
unidirectional ball switch
omnidirectional ball switch
xbee wireless modem fixture usage sensor board
custom ground truth data collection system
push button
xbee wireless
transmitter
fixture usage
sensor board
thermistor modified
kill-a-watt
![Page 33: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/33.jpg)
ground truth sensors
5-week deployment
classification algorithm
classification results
![Page 34: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/34.jpg)
residents 2 2 4 2 2
size 3000 sqft 750 sqft 1200 sqft 700 sqft 750 sqft
floors 3 2 2 3rd flr 6th flr
fixtures 17 8 13 8 8
valves 28 13 21 13 13
deployment sites
![Page 35: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/35.jpg)
deployment infrastructure ground truth sensor
on every valve
pressure sensor
a laptop running hydrologger
http
backend python hydroserver
![Page 36: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/36.jpg)
pressure sensor 1
(hot point)
pressure sensor 2
(cold point)
home 1 apartment 1
two pressure sensors per home
pressure sensor 2
(hot point)
pressure sensor 1
(cold point)
![Page 37: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/37.jpg)
![Page 38: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/38.jpg)
![Page 39: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/39.jpg)
![Page 40: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/40.jpg)
![Page 41: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/41.jpg)
![Page 42: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/42.jpg)
pressure stream red = hot line blue = cold line reed switches high = active low = inactive
![Page 43: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/43.jpg)
![Page 44: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/44.jpg)
hydrosense annotations 1. ground truth sensor
2. semi-automated label
3. review annotator 4. verification
5. final label
![Page 45: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/45.jpg)
dual pressure sensor
toilet
bathroom faucet
kitchen faucet
dishwasher
washing machine
bath/shower
bath/shower diverter
![Page 46: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/46.jpg)
dual pressure sensor
toilet
bathroom faucet
kitchen faucet
dishwasher
washing machine
bath/shower
bath/shower diverter
![Page 47: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/47.jpg)
toilet
bathroom faucet
kitchen faucet
dishwasher
washing machine
bath/shower
bath/shower diverter
dual pressure sensor
![Page 48: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/48.jpg)
![Page 49: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/49.jpg)
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%
5-week dataset
22% of all events were compound
![Page 50: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/50.jpg)
ground truth sensors
5-week deployment
classification algorithm
classification results
![Page 51: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/51.jpg)
toilet
natural water use
70
50
30
pres
sure
(psi)
kitchen sink kitchen sink bathroom sink
![Page 52: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/52.jpg)
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
signal behavior
bayesian inference
![Page 53: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/53.jpg)
toilet
unclassified event
term(i) template matching
compare across multiple signal transformations
dishwashe
r
kitche
nfaucet
show
er
event library
![Page 54: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/54.jpg)
unclassified event event library
toilet
unclassified event
dishwashe
r
kitche
nfaucet
detrendedshower
deriva:veshower
cepstrumshower
show
er
signa
l tra
nsfo
rms
![Page 55: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/55.jpg)
toilet
dishwashe
r
kitche
nfaucet
show
er
unclassified event event library
unclassified event assess similarity
15%
55%
18%
9%
signa
l tra
nsfo
rms
![Page 56: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/56.jpg)
hydrosense example pressure waves
bath open
dishwasher open
upstairs toilet flush
downstairs toilet flush downstairs shower open
kitchen sink cold open
kitchen sink hot open
kitchen sink hot open
![Page 57: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/57.jpg)
signa
l tra
nsfo
rms
![Page 58: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/58.jpg)
44
46
48
‐2
0
2
derivative (psi/s)
time (s)
smoothed pressure
(psi)
42
44
46
48
50
0 5 10 15 20 25 30 35 40 45
raw pressure (psi)
term(i): filter transforms
detrended
derivative
term(i) template matching filter transforms
signa
l tra
nsfo
rms
![Page 59: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/59.jpg)
44
46
48
bandpass derivative
(psi/s)
time (s)
smoothed pressure
(psi)
42
44
46
48
50
0 5 10 15 20 25 30 35 40 45
raw pressure (psi)
‐4
0
4
detrended
derivative
bandpass derivative
term(i) template matching filter transforms
signa
l tra
nsfo
rms
![Page 60: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/60.jpg)
frequency
42
44
46
48
50
0 5 10 15 20 25 30 35 40 45
raw pressure (psi)
detrended
derivative
bandpass derivative
‐10
10
30cepstral
amplitude
index
cepstrum
term(i) template matching filter transforms
signa
l tra
nsfo
rms
![Page 61: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/61.jpg)
unclassified event event library
toilet
unclassified event
dishwashe
r
kitche
nfaucet
show
er
detrended
derivative
bandpass derivative
cepstrum
signa
l tra
nsfo
rms
![Page 62: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/62.jpg)
unclassified event event library
toilet
unclassified event
dishwashe
r
kitche
nfaucet
detrended
derivative
bandpass derivative
cepstrum
55%
85%
65%
90%
detrended
derivative
bandpass derivative
cepstrum
signa
l tra
nsfo
rms
![Page 63: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/63.jpg)
signa
l tra
nsfo
rms
unclassified event event library
toilet
unclassified event
dishwashe
r
kitche
nfaucet
detrended
derivative
bandpass derivative
cepstrum
55%
85%
65%
90%
detrended
derivative
bandpass derivative
cepstrum
template comparisons P (S|V )
! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 64: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/64.jpg)
bath
toilet
unclassified event
term(i) signal features
shower
event library
![Page 65: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/65.jpg)
unclassified event
term(i) signal features
shower toilet
bath
toilet
pressure drop
![Page 66: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/66.jpg)
term(i) signal features
shower toilet
bath
toilet
resonance tracking
unclassified event
![Page 67: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/67.jpg)
term(i) signal features
shower toilet
bath
toilet
resonance tracking
unclassified event
signal feature comparisons
template comparisons P (S|V )
! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 68: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/68.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (i): templates and signal features
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 69: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/69.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (i): templates and signal features
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 70: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/70.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (ii): bigram language model
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 71: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/71.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (ii): bigram language model
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 72: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/72.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (ii): bigram language model
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 73: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/73.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (ii): bigram language model
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 74: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/74.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
term (ii): bigram language model
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 75: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/75.jpg)
70 50 30 pr
essu
re
P(kitchen sink hot open) 14%
P(kitchen sink cold open)
P(toilet open)
P(kitchen hot/cold close)
P(kitchen hot close)
P(toilet close)
3%
15%
2%
6%
1%
4.6%
4.3%
4.1%
term (ii): bigram language model
sequence 1
sequence 2
sequence 3
![Page 76: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/76.jpg)
70 50 30 pr
essu
re
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close
kitchen sink hot open
shower cold open
toilet open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
sequence 1
sequence 2
sequence 3
term (ii): bigram language model
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 77: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/77.jpg)
term(iii): grammar
opened closed opened closed
temperature consistency
1
2
3soft penalty P (S|V )
! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 78: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/78.jpg)
70 50 30 pr
essu
re
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close
bathroom sink hot open
shower cold open
toilet open
bathroom sink hot close
shower cold close
kitchen sink hot open
toilet close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
term(iii): grammar
sequence 1
sequence 2
sequence 3 P (S|V )
! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 79: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/79.jpg)
70 50 30 pr
essu
re
bathroom sink hot open
shower cold open
toilet open
bathroom sink hot close
shower cold close
kitchen sink hot open
toilet close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
term(iii): grammar
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 80: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/80.jpg)
70 50 30 pr
essu
re
bathroom sink hot open
shower cold open
toilet open
bathroom sink hot close
shower cold close
kitchen sink hot open
toilet close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
term(iii): grammar
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close P (S|V )
! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 81: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/81.jpg)
70 50 30 pr
essu
re
bathroom sink hot open
shower cold open
toilet open
bathroom sink hot close
shower cold close
kitchen sink hot open
toilet close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
term(iii): grammar
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close P (S|V )
! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 82: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/82.jpg)
fixture usage duration flow volume
term(iv): paired valve priors
50
60
70
0 20 40 60
estimated flow volume
30 150 60 90 120 seconds
bin
frequ
ency
3 9 6 estimated gallons
1 12
open close
faucet toilet
bath faucet
toilet
bath
paired
![Page 83: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/83.jpg)
70 50 30 pr
essu
re
term(iv): paired valve priors
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
bathroom sink hot open
shower cold open
toilet open
bathroom sink hot close
shower cold close
kitchen sink hot open
toilet close
kitchen sink hot close
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 84: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/84.jpg)
70 50 30 pr
essu
re
kitchen sink hot open
kitchen sink cold open
dishwasher open
bathroom sink hot close
kitchen sink hot close
toilet open
toilet close
kitchen sink hot close
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
bathroom sink hot open
shower cold open
toilet open
bathroom sink hot close
shower cold close
kitchen sink hot open
toilet close
kitchen sink hot close
term(iv): paired valve priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 85: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/85.jpg)
70 50 30 pr
essu
re
kitchen sink hot open
toilet open
bathroom sink hot open
bathroom sink hot close
kitchen sink hot close
kitchen sink hot open
kitchen sink hot close
toilet close
term(iv): paired valve priors toilet
kitchen sink kitchen sink bathroom sink
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
P (S|V )! "# $R!1%
r=0
fr(Sr|Vr)
# $! "(i) templates and
signal features
P (V )! "# $N!1%
n=0
P (vn|vn!1)
# $! "(ii) bigram
language model
%
i/"!
fp(vi)
# $! "(iii) grammar
K!1%
k=0
%
#a,b$"!
fk(!va, vb")
# $! "(iv) paired valve
priors
![Page 86: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/86.jpg)
ground truth sensors
5-week deployment
classification algorithm
classification results
![Page 87: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/87.jpg)
three levels of granularity
valve level e.g., upstairs bathroom faucet hot water activated
1
fixture level e.g., upstairs bathroom faucet activated
2
fixture category level e.g., faucet activated
3
![Page 88: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/88.jpg)
0%
20%
40%
60%
80%
100%
hydrosense classification results real-world water usage data
term (i)
fixture valve fixture category
![Page 89: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/89.jpg)
70.2% 72.5% 75.5% 83.42642 87.99408 89.4856 93.6% 95.4% 95.9% 0%
20%
40%
60%
80%
100%
term (i)-(iii) 70.2% 83.4% 93.6% 72.4% 88.0% 95.3% 75.5% 89.5% 95.9%
terms (i)-(iv)
hydrosense classification results real-world water usage data
term (i)
*error bars = std error
fixture valve fixture category
*10-fold cross validation
![Page 90: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/90.jpg)
70.2% 72.5% 75.5% 83.4% 88.0% 89.5% 93.6% 95.4% 95.9% 50%
60%
70%
80%
90%
100%
hydrosense classification results real-world water usage data
terms (i)-(iv) term (i)-(iii)
*error bars = std error
fixture valve fixture category
*10-fold cross validation
term (i) 70.2% 83.4% 93.6% 72.4% 88.0% 95.3% 75.5% 89.5% 95.9%
![Page 91: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/91.jpg)
70.2% 72.5% 75.5% 83.4% 88.0% 89.5% 93.6% 95.4% 95.9% 50%
60%
70%
80%
90%
100%
65.6% 72.8% 72.3% 80.8% 87.2% 86.2% 94.1% 96.1% 95.2% 50%
60%
70%
80%
90%
100%
term (i)
*error bars = std error
terms (i)-(iv)
fixture valve fixture category
compound events real-world water usage data
*10-fold cross validation
65.6% 80.8% 94.0% 72.8% 87.2% 96.0% 72.3% 86.2% 95.2%
term (i)-(iii)
![Page 92: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/92.jpg)
hydrosense classification results real-world water usage data
75.5% 89.5% 95.9% 0%
20%
40%
60%
80%
100% one sensor, terms(i)-(iv)
fixture category fixture valve
*error bars = std error *10-fold cross validation
![Page 93: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/93.jpg)
75.5% 89.5% 95.9% 82.4% 93.5% 97.7% 0%
20%
40%
60%
80%
100%
hydrosense classification results real-world water usage data
two sensors, terms(i)-(iv)
fixture category fixture valve
*error bars = std error *10-fold cross validation *terms (i)-(iv)
one sensor, terms(i)-(iv)
![Page 94: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/94.jpg)
…what about training?
![Page 95: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/95.jpg)
0
20
40
60
80
100
0 2 4 6 8 10 Days of Training Data
hydrosense training results real-world water usage data
*error bars = std error
terms (i)-(iv)
![Page 96: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/96.jpg)
60
70
80
90
100
0 2 4 6 8 10 Days of Training Data
hydrosense training results real-world water usage data
*error bars = std error
terms (i)-(iv)
![Page 97: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/97.jpg)
pervasive 2011 contributions longitudinal study of real-world water usage and the resulting dataset a new probabilistic approach to water usage classification demonstrate that this new approach can accurately classify real world data
1
2
3
![Page 98: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/98.jpg)
future work additional features segmentation ease of training
1
2
3
![Page 99: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/99.jpg)
![Page 100: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/100.jpg)
![Page 101: Hydro pervasive2011 eric_larson](https://reader034.vdocuments.us/reader034/viewer/2022051818/5499803eb47959035a8b45f8/html5/thumbnails/101.jpg)
design:use:build: ubicomp lab
universityofwashington sustainabilityresearchuniversityofwashington
A Longitudinal Study of Pressure Sensing to Infer Real-World Water Usage Events in the Home
Jon Froehlich, Elliot Saba, Tim Campbell, Les Atlas, James Fogarty and Shwetak Patel
Eric Larson [email protected]