Hydro pervasive2011 eric_larson

656 views
603 views

Published on

A Longitudinal Study of Pressure Sensing to Infer Real-World Water Usage Events in the Home

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
656
On SlideShare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
9
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Hydro pervasive2011 eric_larson

  1. 1. 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 design:
 use:
 build:
 ubicomp lab university
of
washington
university
of
washington
 sustainability
research

  2. 2. today‘s usage refrigerator 0.3 gallons kitchen sink 28 gallons dishwasher 6.5 gallons
  3. 3. today‘s usage shower 62.4 gallons bathroom sink 1 bathroom sink 2 4.2 gallons 0.8 gallons bath 6.5 gallons toilet 78.4 gallons
  4. 4. today‘s usage: hot vs. cold shower52.4 gallons shower 10.4 gallons bathroom sink 1 bathroom sink 1 bathroom sink 2 3.2 gallons 1.2 gallons 0.8 gallons bath bath bathroom sink 2 6.5 gallons 0.0 gallons 2.4 gallons toilet 78.4 gallons
  5. 5. sustainability applications
  6. 6. assisted living applications last active: 10:09PM last active: 10:08PM last active: 10:03PM last active: last active: 10:33PM 7:20AM
  7. 7. at ubicomp09, we introduced hydrosense
  8. 8. hydrosense •  single, screw-on sensor •  identifies fixture usage •  estimates flowFroehlich et al., UbiComp2009; Larson et al., PMC2010
  9. 9. hydrosenseuses pressure waves toidentify usage upstairs toilet flushbath open kitchen sink kitchen sink hotdishwasher open opencold open downstairs shower flush downstairs toilet open
  10. 10. ubicomp2009 
feasibility study controlled experiments •  2 researchers per site •  5 trials per valve experimental script •  valve opened full stop •  pause for ~5 seconds •  valve closed
  11. 11. ubicomp2009 data collection
  12. 12. ubicomp2009 paper successfully demonstrated the potential of using pressure waves to identify fixture usage evaluation method algorithm staged experiments each pressure wave treated independently all faucet handles were operated at approximately the same flow rates did not consider context of usage all fixtures were tested in isolation was not probabilistic
  13. 13. what we’re really interested in… how well will hydrosense perform on real-world water usage data?
  14. 14. brushing teeth
  15. 15. shaving
  16. 16. bathing
  17. 17. paw washing
  18. 18. water
tower
 water tower bathroom 1 hose
 spigot
 compound events kitchenincoming
cold
 water
from
 dishwasher supply
line
 thermal

 expansion

 utility water pressure regulator tank
 meter hot water heater laundry bathroom 2
  19. 19. pervasive 2011 contributions 1 longitudinal study of real-world water usage and the resulting dataset 2 a new probabilistic approach to water usage classification 3 demonstrate that this new approach can accurately classify real world data
  20. 20. ground truth 5-week classification classification sensors deployment algorithm results
  21. 21. ground truth 5-week classification classification sensors deployment algorithm results
  22. 22. ground truth labels manual automatic kitchen sink kitchen sink bathroom sink cold cold hot hot cold cold open close open close open close
  23. 23. water
tower
 bathroom 1 hose
 spigot
 kitchenincoming
cold
 water
from
 dishwasher supply
line
 thermal

 expansion

 utility water pressure regulator tank
 meter hot water heater laundry bathroom 2
  24. 24. how can we obtain water usage labels at the valve-level?
  25. 25. this is actually a challenging question…
  26. 26. function across fixtures kitchen sink bathroom sink bath shower toilet laundry basin washing machine dishwasher
  27. 27. after many failed attempts
  28. 28. custom ground truth datacollection system xbee wireless modem fixture usage sensor board hall reed 3-axis unidirectional ball omnidirectional effect switch accelerometer switch ball switch
  29. 29. custom ground truth datacollection system “wake up” sensors xbee wireless modem fixture usage sensor board hall reed 3-axis unidirectional ball omnidirectional effect switch accelerometer switch ball switch
  30. 30. custom ground truth datacollection system fixture handle position sensors xbee wireless modem fixture usage sensor board hall reed 3-axis unidirectional ball omnidirectional effect switch accelerometer switch ball switch
  31. 31. accelerometer
  32. 32. custom ground truth datacollection system xbee push wireless button ter transmit sage fixture u ard o sensor b xbee wireless modem fixture usage sensor board modified or kill-a-wa tt thermist hall reed 3-axis unidirectional ball omnidirectional effect switch accelerometer switch ball switch
  33. 33. ground truth 5-week classification classification sensors deployment algorithm results
  34. 34. deployment sites 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
  35. 35. deployment infrastructureground truth sensor on every valve backend python a laptop running hydroserver hydrologger http pressure sensor
  36. 36. two pressure sensors per home home 1 apartment 1 pressure sensor 1 (cold point) pressure sensor 2 (hot point) pressure pressure sensor 2 sensor 1 (cold point) (hot point)
  37. 37. pressure streamred = hot lineblue = cold linereed switcheshigh = activelow = inactive
  38. 38. hydrosense annotations 1. ground truth sensor 2. semi-automated label 3. review annotator 4. verification 5. final label
  39. 39. dual pressure sensortoiletbathroom faucetkitchen faucetdishwasherwashing machinebath/showerbath/shower diverter
  40. 40. dual pressure sensortoiletbathroom faucetkitchen faucetdishwasherwashing machinebath/showerbath/shower diverter
  41. 41. 5-week dataset totals days 33 33 30 27 33 156 events 2374 3075 4754 2499 2578 14,960events/day 71.9 93.2 158.5 92.6 78.1 95.9compound 22.2% 21.8% 16.6% 32% 21.3% 21.9% 22% of all events were compound
  42. 42. ground truth 5-week classification classification sensors deployment algorithm results
  43. 43. natural water use toilet 70 kitchen sink kitchen sink bathroom sinkpressure (psi) 50 30
  44. 44. bayesian inference signal behavior P (S|V ) P (V )R−1 N−1 K−1 ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 ) fp (vi ) f k ( v a , vb )r=0 n=0 i∈β / k=0 a,b ∈β(i) templates and (ii) bigram (iv) paired valve signal features language model (iii) grammar priors
  45. 45. term(i) template matching unclassified event event library shower
 kitchen

faucet
 dishwasher
 toilet
 compare across multiple signal transformations
  46. 46. signal transforms unclassified event unclassified event event library shower
 kitchen

faucet
 dishwasher
 toilet

  47. 47. unclassified event event library shower
 kitchen

faucet
 unclassified event assess similarity dishwasher
 toilet
 15%signal transforms 55% 18% 9%
  48. 48. hydrosenseexample pressure waves upstairs toilet flushbath open kitchen sink kitchen sink hotdishwasher open opencold open downstairs shower flush downstairs toilet open
  49. 49. signal transforms
  50. 50. term(i) template matching filter transforms 50
 48
 raw pressure 46
 (psi) 44
 detrended 42
 0
 5
 10
 15
 20
 48
signal transforms derivative smoothed pressure 46
 (psi) 44
 2
 derivative (psi/s) 0
 ‐2
 time (s)
  51. 51. term(i) template matching filter transforms 50
 48
 raw pressure 46
 (psi) 44
 detrended 42
 0
 5
 10
 15
 20
 48
signal transforms derivative smoothed pressure 46
 (psi) bandpass 44
 derivative 4
 bandpass derivative 0
 (psi/s) ‐4
 time (s)
  52. 52. term(i) template matching filter transforms 50
 48
 raw pressure 46
 (psi) 44
 detrended 42
 0
 5
 10
 15
 20
signal transforms derivative frequency bandpass derivative 30
 cepstral cepstrum amplitude 10
 ‐10
 index
  53. 53. unclassified event event library shower
 unclassified event kitchen
faucet
 dishwasher
 toilet
 detrendedsignal transforms derivative bandpass derivative cepstrum
  54. 54. unclassified event event library unclassified event kitchen
faucet
 dishwasher
 toilet
 detrended detrended 55%signal transforms derivative derivative 85% bandpass bandpass derivative derivative 65% cepstrum cepstrum 90%
  55. 55. unclassified event event library unclassified event kitchen
faucet
 dishwasher
 template comparisons toilet
 P (S|V ) detrended detrended 55% R−1 N −1 ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 )signal transforms derivative r=0 derivative n=0 85% (i) templates and (ii) bigram signal features language model bandpass bandpass derivative derivative 65% cepstrum cepstrum 90%
  56. 56. term(i) signal features event library unclassified event shower
 toilet
 bath

  57. 57. term(i) signal featurespressure drop unclassified event shower
 toilet
 toilet
 bath

  58. 58. term(i) signal featuresresonance tracking unclassified event shower
 toilet
 toilet
 bath

  59. 59. term(i) signal featuresresonance tracking unclassified event template comparisons P (S|V ) R−1 N −1 ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 ) r=0 n=0 (i) templates and (ii) bigram signal features language model shower
 toilet
signal feature comparisons toilet
 bath

  60. 60. term (i): templates and signal features 70pressure 50 30 P (S|V ) R−1 N −1 P(kitchen sink hot open) 14% ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 ) P(kitchen sink cold open) 3% r=0 n=0 P(toilet open) 15% (i) templates and (ii) bigram signal features language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  61. 61. term (i): templates and signal features 70pressure 50 30 P (S|V ) R−1 N −1 P(kitchen sink hot open) 14% ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 ) P(kitchen sink cold open) 3% r=0 n=0 P(toilet open) 15% (i) templates and (ii) bigram signal features language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  62. 62. term (ii): bigram language model 70pressure 50 30 P (S|V ) P (S|V R−1 R−1 N −1 −1 P(kitchen sink hot open) 14% fr ( ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 )) P (vn |vn−1 P(kitchen sink cold open) 3% r=0 r=0 n=0 n=0 P(toilet open) 15% (i) templates and (i) templates (ii) bigram (ii) bigram signal features signal features language model language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  63. 63. term (ii): bigram language model 70pressure 50 30 P (S|V ) P (S|V R−1 R−1 N −1 −1 P(kitchen sink hot open) 14% fr ( ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 )) P (vn |vn−1 P(kitchen sink cold open) 3% r=0 r=0 n=0 n=0 P(toilet open) 15% (i) templates and (i) templates (ii) bigram (ii) bigram signal features signal features language model language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  64. 64. term (ii): bigram language model 70pressure 50 30 P (S|V ) P (S|V R−1 R−1 N −1 −1 P(kitchen sink hot open) 14% fr ( ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 )) P (vn |vn−1 P(kitchen sink cold open) 3% r=0 r=0 n=0 n=0 P(toilet open) 15% (i) templates and (i) templates (ii) bigram (ii) bigram signal features signal features language model language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  65. 65. term (ii): bigram language model 70pressure 50 30 P (S|V ) P (S|V R−1 R−1 N −1 −1 P(kitchen sink hot open) 14% fr ( ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 )) P (vn |vn−1 P(kitchen sink cold open) 3% r=0 r=0 n=0 n=0 P(toilet open) 15% (i) templates and (i) templates (ii) bigram (ii) bigram signal features signal features language model language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  66. 66. term (ii): bigram language model 70pressure 50 30 P (S|V ) P (S|V R−1 R−1 N −1 −1 P(kitchen sink hot open) 14% fr ( ˆ ˆ fr ( Sr |V r ) P (vn |vn−1 )) P (vn |vn−1 P(kitchen sink cold open) 3% r=0 r=0 n=0 n=0 P(toilet open) 15% (i) templates and (i) templates (ii) bigram (ii) bigram signal features signal features language model language model P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  67. 67. term (ii): bigram language model 70pressure 50 30 P(kitchen sink hot open) 14% 4.6% sequence 1 P(kitchen sink cold open) 3% P(toilet open) 15% 4.3% sequence 2 4.1% sequence 3 P(kitchen hot/cold close) 2% P(kitchen hot close) 6% P(toilet close) 1%
  68. 68. term (ii): bigram language model 70pressure 50 30 sequence 1 kitchen sink kitchen sink dishwasher bathroom sink kitchen sink toilet toilet kitchen sink hot open cold open open hot close hot close open close hot close sequence 2 kitchen sink shower toilet bathroom sink kitchen sink kitchen sink kitchen sink kitchen sink hot open cold open open hot close hot close hot open hot close hot close sequence 3 kitchen sink (S|Vtoilet P ) bathroom sink bathroom sink kitchen sink (V kitchen sink P ) kitchen sink toilet hot open (S|V open P ) hot open hot close hot close (V )hot open P hot close close R−1 R−1 N −1 N −1 K−1 K−1 ˆ ˆ fr (Sr ||Vr ) ˆ ˆ fr ( Sr V r ) P (vn |vn−1 ) P (vn |vn−1 ) fp (v ) fp (vii) fk ( va ,, vb ) f k ( v a vb r=0 r=0 n=0 n=0 ∈β i/ / i∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and (ii) bigram (ii) bigram (ii) bigram (iv) paired valve signal features features language model (iii) grammar (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve signal features language model language model priors priors priors
  69. 69. term(iii): grammar 1 opened closed 2 opened closed 3 temperature consistency P (S|V ) P (S|V ) soft penalty)) P (V P (VR−1R−1 N −1 N −1 K−1 K−1 ˆ ˆ fr (Sr ||Vr ) ˆ ˆ fr ( Sr V r ) P (vn |vn−1 ) P (vn |vn−1 ) fp (v ) fp (vii) fk ( va ,, vb ) f k ( v a vbr=0r=0 n=0 n=0 ∈β i/ / i∈β k=0 a,b ∈β k=0 a,b ∈β(i) templates and templates and(i) templates and (ii) bigram (ii) bigram (ii) bigram (iv) paired valve signal features features language model (iii) grammar (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve signal features language model language model priors priors priors
  70. 70. term(iii): grammar 70pressure 50 30 sequence 1 kitchen sink kitchen sink dishwasher bathroom sink kitchen sink toilet toilet kitchen sink hot open cold open open hot close hot close open close hot close sequence 2 bathroom sink shower toilet bathroom sink shower kitchen sink toilet kitchen sink hot open cold open open hot close cold close hot open close hot close sequence 3 kitchen sink (S|Vtoilet P ) bathroom sink bathroom sink kitchen sink (V kitchen sink P ) kitchen sink toilet hot open (S|V open P ) hot open hot close hot close (V )hot open P hot close close R−1 R−1 N −1 N −1 K−1 K−1 ˆ ˆ fr (Sr ||Vr ) ˆ ˆ fr ( Sr V r ) P (vn |vn−1 ) P (vn |vn−1 ) fp (v ) fp (vii) fk ( va ,, vb ) f k ( v a vb r=0 r=0 n=0 n=0 ∈β i/ / i∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and (ii) bigram (ii) bigram (ii) bigram (iv) paired valve signal features features language model (iii) grammar (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve signal features language model language model priors priors priors
  71. 71. term(iii): grammar 70pressure 50 30 kitchen sink kitchen sink dishwasher bathroom sink kitchen sink toilet toilet kitchen sink hot open cold open open hot close hot close open close hot close bathroom sink shower toilet bathroom sink shower kitchen sink toilet kitchen sink hot open cold open open hot close cold close hot open close hot close kitchen sink (S|Vtoilet P ) bathroom sink bathroom sink kitchen sink (V kitchen sink P ) kitchen sink toilet hot open (S|V open P ) hot open hot close hot close (V )hot open P hot close close R−1 R−1 N −1 N −1 K−1 K−1 ˆ ˆ fr (Sr ||Vr ) ˆ ˆ fr ( Sr V r ) P (vn |vn−1 ) P (vn |vn−1 ) fp (v ) fp (vii) fk ( va ,, vb ) f k ( v a vb r=0 r=0 n=0 n=0 ∈β i/ / i∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and (ii) bigram (ii) bigram (ii) bigram (iv) paired valve signal features features language model (iii) grammar (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve signal features language model language model priors priors priors
  72. 72. term(iii): grammar 70pressure 50 30 bathroom sink shower toilet bathroom sink shower kitchen sink toilet kitchen sink hot open cold open open hot close cold close hot open close hot close kitchen sink toilet bathroom sink bathroom sink kitchen sink kitchen sink kitchen sink toilet hot open open hot open hot close hot close hot open hot close close kitchen sink (S|V ) sink P kitchen dishwasher bathroom sink kitchen sink (V ) toilet P toilet kitchen sink P (S|V )open hot open cold open hot close hot close (V ) open P close hot close R−1 R−1 N −1 N −1 K−1 K−1 ˆ ˆ fr (Sr ||Vr ) ˆ ˆ fr ( Sr V r ) P (vn |vn−1 ) P (vn |vn−1 ) fp (v ) fp (vii) fk ( va ,, vb ) f k ( v a vb r=0 r=0 n=0 n=0 ∈β i/ / i∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and (ii) bigram (ii) bigram (ii) bigram (iv) paired valve signal features features language model (iii) grammar (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve signal features language model language model priors priors priors
  73. 73. term(iii): grammar 70pressure 50 30 bathroom sink shower toilet bathroom sink shower kitchen sink toilet kitchen sink hot open cold open open hot close cold close hot open close hot close kitchen sink toilet bathroom sink bathroom sink kitchen sink kitchen sink kitchen sink toilet hot open open hot open hot close hot close hot open hot close close kitchen sink (S|V ) sink kitchen P P (S|V dishwasher bathroom sink kitchen sink (V ) toilet P toilet kitchen sink P (S|V )open) hot open cold open hot close P hot close (V ) open P close hot close R−1 R−1R−1 N −1 N−1 N −1 K−1 K−1 K−1 fr (Srr(|Sˆr|) r ) ˆ ˆ fr (f r |ˆrrV ˆ V ˆ S V ) P P n |vn−1 ) P (v(v|v|vn−1 ) (vn n n−1 ) fpp(v ) ffp(vii) (v ffk (va ,av,bvb ) f( ( v a, v) kk v b r=0 r=0 r=0 n=0 n=0 n=0 ∈β i/∈β / i/ i∈β k=0 a,b ∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and and (i) templates (ii) bigram bigram (ii)(ii) bigram (ii) bigram (iv) paired valve (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve (iv) paired valve signal features features signal features signal features language model language model language model (iii) grammar (iii) grammar language model priors priors priors priors
  74. 74. term(iv): paired valve priors paired 70
 60
 estimated flow volume open close 50
 0
 20
 40
 60
bin frequency toilet toilet bath faucet bath faucet 30 60 90 120 150 1 3 6 9 12 seconds estimated gallons fixture usage duration flow volume
  75. 75. term(iv): paired valve priors 70pressure 50 30 bathroom sink shower toilet bathroom sink shower kitchen sink toilet kitchen sink hot open cold open open hot close cold close hot open close hot close kitchen sink toilet bathroom sink bathroom sink kitchen sink kitchen sink kitchen sink toilet hot open open hot open hot close hot close hot open hot close close kitchen sink (S|V ) sink kitchen P P (S|V dishwasher bathroom sink kitchen sink (V ) toilet P toilet kitchen sink P (S|V )open) hot open cold open hot close P hot close (V ) open P close hot close R−1 R−1R−1 N −1 N−1 N −1 K−1 K−1 K−1 fr (Srr(|Sˆr|) r ) ˆ ˆ fr (f r |ˆrrV ˆ V ˆ S V ) P P n |vn−1 ) P (v(v|v|vn−1 ) (vn n n−1 ) fpp(v ) ffp(vii) (v ffk (va ,av,bvb ) f( ( v a, v) kk v b r=0 r=0 r=0 n=0 n=0 n=0 ∈β i/∈β / i/ i∈β k=0 a,b ∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and and (i) templates (ii) bigram bigram (ii)(ii) bigram (ii) bigram (iv) paired valve (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve (iv) paired valve signal features features signal features signal features language model language model language model (iii) grammar (iii) grammar language model priors priors priors priors
  76. 76. term(iv): paired valve priors 70pressure 50 30 kitchen sink toilet bathroom sink bathroom sink kitchen sink kitchen sink kitchen sink toilet hot open open hot open hot close hot close hot open hot close close bathroom sink shower toilet bathroom sink shower kitchen sink toilet kitchen sink hot open cold open open hot close cold close hot open close hot close kitchen sink (S|V ) sink kitchen P P (S|V dishwasher bathroom sink kitchen sink (V ) toilet P toilet kitchen sink P (S|V )open) hot open cold open hot close P hot close (V ) open P close hot close R−1 R−1R−1 N −1 N−1 N −1 K−1 K−1 K−1 fr (Srr(|Sˆr|) r ) ˆ ˆ fr (f r |ˆrrV ˆ V ˆ S V ) P P n |vn−1 ) P (v(v|v|vn−1 ) (vn n n−1 ) fpp(v ) ffp(vii) (v ffk (va ,av,bvb ) f( ( v a, v) kk v b r=0 r=0 r=0 n=0 n=0 n=0 ∈β i/∈β / i/ i∈β k=0 a,b ∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and and (i) templates (ii) bigram bigram (ii)(ii) bigram (ii) bigram (iv) paired valve (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve (iv) paired valve signal features features signal features signal features language model language model language model (iii) grammar (iii) grammar language model priors priors priors priors
  77. 77. term(iv): paired valve priors toilet kitchen sink kitchen sink 70 bathroom sinkpressure 50 30 kitchen sink toilet bathroom sink bathroom sink kitchen sink kitchen sink kitchen sink toilet hot open open hot open hot close hot close hot open hot close close P (S|V ) P (S|V ) ) P (S|V P (V ) P P (V ) R−1 R−1R−1 N −1 N−1 N −1 K−1 K−1 K−1 fr (Srr(|Sˆr|) r ) ˆ ˆ fr (f r |ˆrrV ˆ V ˆ S V ) P P n |vn−1 ) P (v(v|v|vn−1 ) (vn n n−1 ) fpp(v ) ffp(vii) (v ffk (va ,av,bvb ) f( ( v a, v) kk v b r=0 r=0 r=0 n=0 n=0 n=0 ∈β i/∈β / i/ i∈β k=0 a,b ∈β k=0 a,b ∈β k=0 a,b ∈β (i) templates and templates and (i) templates and and (i) templates (ii) bigram bigram (ii)(ii) bigram (ii) bigram (iv) paired valve (iii) grammar (iii) grammar (iv) paired valve (iv) paired valve (iv) paired valve signal features features signal features signal features language model language model language model (iii) grammar (iii) grammar language model priors priors priors priors
  78. 78. ground truth 5-week classification classification sensors deployment algorithm results
  79. 79. three levels of granularity 1 valve level e.g., upstairs bathroom faucet hot water activated 2 fixture level e.g., upstairs bathroom faucet activated 3 fixture category level e.g., faucet activated
  80. 80. hydrosense classification results real-world water usage data valve fixture fixture category100% 80% 60% 40% 20% 0% term (i)
  81. 81. hydrosense classification results real-world water usage data valve fixture fixture category100% 80% 60% 40% 20% 70.2%83.42642 70.2% 83.4% 93.6% 87.99408 95.4% 72.4% 88.0% 95.3% 72.5% 75.5% 89.4856 75.5% 89.5% 95.9% 0% term (i) term (i)-(iii) terms (i)-(iv)*error bars = std error *10-fold cross validation
  82. 82. hydrosense classification results real-world water usage data valve fixture fixture category100% 90% 80% 70% 60% 70.2% 83.4% 93.6% 72.5% 88.0% 95.3% 72.4% 95.4% 75.5% 89.5% 95.9% 75.5% 89.5% 50% term (i) term (i)-(iii) terms (i)-(iv)*error bars = std error *10-fold cross validation
  83. 83. compound events real-world water usage data valve fixture fixture category100% 90% 80% 70% 60% 65.6% 80.8% 93.6% 94.1% 70.2% 83.4% 94.0% 72.8% 87.2% 95.4% 96.1% 72.5% 88.0% 96.0% 72.3% 86.2% 95.2% 75.5% 89.5% 95.9% 50% term (i) term (i)-(iii) terms (i)-(iv)*error bars = std error *10-fold cross validation
  84. 84. hydrosense classification results real-world water usage data one sensor, terms(i)-(iv)100% 80% 60% 40% 20% 75.5% 89.5% 95.9% 0% valve fixture fixture category*error bars = std error *10-fold cross validation
  85. 85. hydrosense classification results real-world water usage data one sensor, terms(i)-(iv) two sensors, terms(i)-(iv)100% 80% 60% 40% 20% 75.5% 82.4% 89.5% 93.5% 95.9% 97.7% 0% valve fixture fixture category*error bars = std error *10-fold cross validation *terms (i)-(iv)
  86. 86. …what about training?
  87. 87. hydrosense training results real-world water usage data 100 80 60 40 terms (i)-(iv) 20 0 0 2 4 6 8 10 Days of Training Data*error bars = std error
  88. 88. hydrosense training results real-world water usage data 100 90 80 terms (i)-(iv) 70 60 0 2 4 6 8 10 Days of Training Data*error bars = std error
  89. 89. pervasive 2011 contributions 1 longitudinal study of real-world water usage and the resulting dataset 2 a new probabilistic approach to water usage classification 3 demonstrate that this new approach can accurately classify real world data
  90. 90. future work 1 additional features 2 segmentation 3 ease of training
  91. 91. A Longitudinal Study of Pressure Sensing to Infer Real-World Water Usage Events in the Home Eric Larson eric.cooper.larson@gmail.com Jon Froehlich, Elliot Saba, Tim Campbell, Les Atlas, James Fogarty and Shwetak Patel design:
 use:
 build:
 ubicomp lab university
of
washington
university
of
washington
 sustainability
research


×