FixtureFinder: Discovering the Existence of Electrical and
Water Fixtures Vijay Srinivasan*, John Stankovic, Kamin Whitehouse
University of Virginia *(Currently affiliated to Samsung)
Slide 2
Motivation For Fixture Monitoring Cooking Toileting Home
Healthcare Applications 7 KW hours400 liters Resource conservation
applications
Slide 3
Fixture Monitoring Using Smart meters Whole house power or
water flow Time Power meter Water meter BathroomKitchen
BedroomLivingroom 2000 W 100 W 100 litres/hour Poor accuracy for
low power or low water flow fixtures False positive noise Identical
fixtures
Slide 4
Existing Fixture Monitoring Techniques Direct metering on each
fixtureIndirect sensing + smart meter Single-Point Infrastructure
sensing Images courtesy: HydroSense and Viridiscope (Ubicomp 2009)
Requires users to: Identify each fixture, and for each fixture:
Install a sensor, or Provide training data
Slide 5
FixtureFinder Power meter Water meter BathroomKitchen
BedroomLivingroom Automatically: Identify fixtures Infer usage
times Infer resource consumption 2 PM 5 PM Single-Point
Infrastructure sensing Training data 7 KW hours 400 liters Home
security or automation sensors Light and motion + Lights, sinks and
toilets
Slide 6
FixtureFinder Insights BathroomKitchen BedroomLivingroom
Fixtures identical in meter data Unique in (meter, sensor) data 100
W 100 W, 30 lux 100 W, 50 lux Light sensor Power meter Water
meter
Slide 7
FixtureFinder Insights BathroomKitchen BedroomLivingroom 100 W,
30 lux 100 W, 50 lux Light sensor False positive noise in meter and
sensor data 1.Eliminate noise events in one stream when no activity
in other stream 2.Eliminate unmatched noise Power meter Water meter
ON-OFF pattern Bedroom light sensor data Power meter data
Slide 8
Outline FixtureFinder algorithm Case studies Experimental setup
Evaluation results Conclusions
Slide 9
FixtureFinder Algorithm Inputs Stream 1 Stream 2 Power meter
Water meter Light or motion sensors or Four step algorithm
Slide 10
Step 1 Event Detection Stream 1 Stream 2 Time ON OFF ON OFF 40
500 60 40 140 60200 Stream 1 Stream 2 False positives events: True
positive events: 40 lux 100 Watts For example: Edge detection
algorithms Key challenge: Large number of false positives 100 40
100 Light sensor Power meter
Slide 11
Step 2 Data fusion Stream 1 Stream 2 Time ON OFF ON OFF 40 100
500 60 40 140 100 60200 40 Stream 1 Stream 2 40 lux 100 Watts For
example: Light sensor Power meter Fixture use creates events in
multiple streams simultaneously Compute event pairs Eliminate
temporally isolated false positives
Slide 12
Step 3 Matching Stream 1 Stream 2 Time ON OFF ON OFF 40 100 500
60 40 140 100 60200 40 Stream 1 Stream 2 40 lux 100 Watts For
example: Light sensor Power meter Fixture use occurs in an ON-OFF
pattern Match ON event pairs to OFF event pairs Eliminate unmatched
false positives High match probability
Slide 13
Step 3 Matching Stream 1 Stream 2 Time ON OFF ON OFF 40 100 60
100 60 40 Stream 1 Stream 2 40 lux 100 Watts For example: Light
sensor Power meter High match probability Two ON-OFF event pairs:
(40,100) or (40,60) ? True event pairs are more likely than noisy
event pairs High pair probability Use both match and pair
probabilities to compute ON-OFF event pairs Soft clustering and Min
Cost Bipartite matching (Described in paper) Low pair probability
All false positives eliminated in this example!
Outline FixtureFinder algorithm Case studies Experimental setup
Evaluation results Conclusions
Slide 16
Light Fixture Discovery Power meter Water meter BathroomKitchen
BedroomLivingroom Apply FixtureFinder algorithm on every (light
sensor, power meter) 40 lumens, 100 watts 40 lumens, 150 watts
Unique fixture usage defined by: Light sensor location Light
intensity Power consumption
Slide 17
Light Fixture Discovery Bedroom light sensor data Bedroom light
fixture ON- OFF events Power meter data Large number of false
positives after step 1 False positives eliminated after steps 2 and
3
Slide 18
Water Fixture Discovery Power meter Water meter BathroomKitchen
BedroomLivingroom Fused motion sensor stream Apply FixtureFinder
algorithm on (fused motion sensor, power meter) Unique fixture
usage defined by: Motion sensor signature Flow rate 100 litres/hour
300 litres/hour
Slide 19
Water Fixture Discovery Two toilets with the same flow
signature but different motion signatures
Slide 20
Water Fixture Discovery Two toilets with the same motion
signature but different flow signatures Use event pair probability
to pair simultaneous toilet events with correct rooms
Slide 21
Outline FixtureFinder algorithm Case studies Experimental setup
Evaluation results Conclusions
Slide 22
In-Situ Sensor Deployments in Homes Power meter (TED 5000)
Water meter (Shenitech) X10 motion Custom light sensing mote One
per room in a central location (Except in 3 large rooms where two
sensors were used) One per home
Slide 23
In-Situ Sensor Deployments in Homes Smart switch Smart plug
Contact switches on water fixtures Ground truth for light fixtures
Ground truth for water fixtures All sensors deployed in 4 homes for
10 days (Except water meter deployed in 2 homes for 7 days)
Slide 24
Outline FixtureFinder algorithm Case studies Experimental setup
Evaluation results Conclusions
Slide 25
Fixture Discovery Results Discovered all sinks and toilets
across 2 homes Discovered 37 out of 41 light fixtures across 4
homes Undiscovered lights: - All in large kitchens - Task lighting
or under-cabinet lighting - Used rarely (1-3 times) - Low energy
consumption One false positive light with negligible energy
consumption
Slide 26
Fixture Usage Inference Results Recall: % of ground truth
fixture events detected by Fixture Finder Precision: % of detected
fixture events that are supported by ground truth Results shown for
light fixtures 99% precision 64% recall True positive ON-OFF events
from fixtures Single-Point Infrastructure sensing Training data
High precision usage data
Slide 27
Fixture Usage Inference Results Recall: % of ground truth
fixture events detected by Fixture Finder Results shown for light
fixtures 92% precision 82% recall Balanced precision and recall
Home Activity Monitoring applications Precision: % of detected
fixture events that are supported by ground truth
Slide 28
Analysis of FixtureFinder Steps Step 1: Event Detection ME:
Meter event detection SE: Sensor event detection Step 3: Matching
MM: Meter event matching SM: Sensor event matching Step 2: Data
Fusion SMF: Sensor meter data fusion FixtureFinder Small reduction
in recall Significant increase in precision with steps 2, 3, and
FixtureFinder Results shown for light fixtures
Slide 29
Light Fixture Energy Estimation 91% average energy accuracy for
top 90% energy consuming fixtures
Slide 30
Water Consumption Estimation 81.5% accuracy in Home 3 89.9%
accuracy in Home 4 Home 3Home 4 B Bathroom K Kitchen S Sink F
Flush
Slide 31
Outline FixtureFinder algorithm Case studies Experimental setup
Evaluation results Conclusions
Slide 32
FixtureFinder combines smart meters with existing home security
sensors to automatically: Identify fixtures Infer usage times Infer
resource consumption Demonstrated for light and water fixtures
Complements other fixture monitoring techniques by providing
training data without manual effort
Slide 33
Future Improvements Expand scope to include: Additional
electrical appliances and water fixtures Additional sensing
modalities such as routers, smart switches, infrastructure sensors
Extend algorithm to multi-state appliances Not just two-state
ON-OFF Explore temporal co-occurrence over multiple timescales
Slide 34
Thanks Questions?
Slide 35
FixtureFinder Approach Power meter Water meter Home security or
automation sensors + Automatically discover low power or low water
flow fixtures Lights, sinks, and toilets BathroomKitchen
BedroomLivingroom Light and motion
Slide 36
Step 3 Bayesian Matching Two matches possible (40,100) or
(40,60) Assumption: Edge pairs from true fixtures are more frequent
than noisy edge pairs P(40,100) >> P(40,60) Stream 1 Stream 2
Time ON OFF ON OFF 40 100 60 100 60 40 Hidden variables Stream 1
cluster Stream 1 edge Stream 2 edge Stream 2 cluster Observed
variables
Slide 37
Step 3 Bayesian Matching Incorporate edge pair probability into
a match weight function Perform optimal bipartite matching based on
match weight function Eliminate unlikely matches Stream 1 Stream 2
Time ON OFF ON OFF 40 100 60 100 60 40