Beruflich Dokumente
Kultur Dokumente
Minos Garofalakis
Michael Franklin
Intel Research Berkeley
UC Berkeley
VLDB 2001
of the window?
Smoothed
output
Smoothing Filter
Raw
readings
Time
Fido resting
Reality
Reality
Raw
Raw readings
readings
Small
Small window
window
Large
Large window
window
Need
Need to
to balance
balance completeness
completeness vs.
vs.
capturing
capturing tag
tag movement
movement
Itinerary
Introduction: RFID data cleaning
A statistical sampling perspective
SMURF
Per-tag cleaning
Multi-tag cleaning
Ongoing work
Conclusions
Tags
Read Cycle
Cycle
Read
(Epoch)
(Epoch)
E0
E1
E2
E3
E4
E5
E6
E7
E8
E9
Tag List
Tag 1
Epoch
TagID
ReadRate
Tag 2
.9
.6
.3
Tag 3
Tag 4
(For Alien readers)
Sampling
Sample trial
Reading
Single sample
Smoothing window
Repeated trials
Read rate
SMURF
Statistical Smoothing for Unreliable RFID Data
Adapts window based on statistical properties
Mechanisms for:
Si
pi
piavg
(Read rate
of tag i)
0
E0
E1
E2
E3
E4
E5
E6
E7
E8
Smoothing Window
wi Bernoulli trials
E9
Time
(epochs)
0
E0
Reading with a
low pi
E1
E2
E3
E4
E5
E6
E7
E8
E9
Time
(epochs)
1
wi avg
pi
* ln
Desired window
size for tag
i
With probability
Expected
epochs
needed to read 1-
1
pi
0
E0
E1
E2
E3
Statistically significant
difference
E4
E5
E6
E7
E8
E9
Time
(epochs)
|| Si | wi * p
avg
i
# observed # expected
readings
readings
| 2 wi * p
avg
i
* (1 p
avg
i
Is the difference
statistically significant?
SMURF in Action
Fido moving
Fido resting
SMURF
SMURF
Multi-tag Cleaning
Some applications only need aggregates
E.g., count of items on each shelf
Dont need to track each tag!
Aggregate Computation
estimators (Horvitz-Thompson)
Count:
1
N w iSw
i 1 (1 piavg ) w
Use small windows to capture movement
Use the estimator to compensate for lost readings
Window Adaptation
Upper bound window similar to per-tag
Transition based
1 on
variance
within
1
w avg * ln
subwindows p
Count
E0
E1
Nw
Var N w Var N w'
E2
E3
E4
E5
E6
E7
E8
Nw
E9
Time
(epochs)
Multi-tag Scenario
B
Reinforcement
D
Arbitration
A?addressed
B? A U B? by
A statistical
B? A? C?
All
are
framework!
U
Beyond RFID
Other
Other sensor
sensor data
data
Related Work
Commercial RFID middleware
Smoothing filters: need to set smoothing window
RFID-related work
Rao et al., StreamClean: complementary
Intel Seattle, HiFi, ESP: static window size
BBQ, MauveDB
Heavyweight, model-based
SMURF is non-parametric, sampling-based
Conclusions
Thanks!
Questions?