Title: Distance Based Decision Fusion in a Distributed Wireless Sensor Network
1Distance Based Decision Fusion in a Distributed
Wireless Sensor Network
- Marco Duarte and Yu-Hen Hu
- Department of Electrical and Computer Engineering
Information Processing in Sensor Networks Palo
Alto, CA April 22-23, 2003
2Summary
- Sensor networks requires decision fusion
- Majority voting is the most popular decision
fusion method. It assumes all votes are equally
accurate. - Not all sensor decisions are equally accurate.
Those closer to the target or with higher SNR
will have better results.
3Summary (Contd)
- If source location can be estimated, such
discrepancy can be exploited to improve the
decision fusion accuracy. - We formulate three different methods to combine
sensor decisions based on their distance from the
target and SNR, and we found encouraging results.
4Sensor Network Signal Processing Tasks
- Target Detection (CFAR region fusion)
- Target Classification (ML region fusion )
- Target Localization (ML,EBL)
- Target Tracking (Kalman Filter)
D. Li, K.D. Wong, Y.H. Hu, A.M. Sayeed
Detection, Classification and Tracking of
Targets. IEEE Signal Processing Magazine Vol. 19
Issue 2 pp. 17-29
5Target Classification at Node Level
- Classify acoustic spectral features into AAV, DW,
or HMMWV on individual sensor nodes - 50-dimensional spectral feature PSD 0-960 Hz
from acoustic data (f 4960 Hz) - One feature vector for every 0.75 sec. of data
- Maximum Likelihood Classifier
AAV DW
HMMWV
6Not all sensors are equal
- Hypothesis Classification accuracy is a function
of target-sensor distance and SNR - Feature is perturbed by background noise
decision margin
shrinks - Each nodes classification rate depends on SNR.
- SNR is also roughly inversely proportional
vehicle-node distance due to acoustic energy
attenuation - Experiment Determine classification rate for
different levels of distance, SNR
7Distance vs. Classification Rate
8SNR vs. Classification Rate
9Classification Rate as a Function of SNR and
Distance
10Weighted Decision Fusion
- Optimal (linear) decision fusion perform
weighted voting of individual results (ei(x) for
node i) - Weights (wi for node i) are proportional to
classification rates
Z. Chair and P. Varshney Optimal Data Fusion
in Multiple Sensor Detection Systems, IEEE
Trans. AES, Vol. 22 No. 1, Jan. 1986, pp. 98-101
11Distance Based Decision Fusion (DBDF)
- Current system architecture allows detection and
localization prior to classification, giving
distance and SNR estimates. - Accurate localization allows for estimation of
probability of correct classification based on
distance. - Some events may be rejected by fusion algorithm
as the distance or SNR figures fall outside the
training data range. The majority voting can be
used as a backup fusion method. - Measurements classification rate and acceptance
rates.
12DBDF Approach 1 Maximum A Posteriori Decision
Fusion
- Weighting factor as function of distance and SNR,
determined using CFAR and EBL information. - We formulate a Maximum A Posteriori (MAP)
Probability Gating Network, using Bayesian
estimation - Parameters SNR, Distance grouping size
- P(xd,s)P(d,s) estimated from experiment data.
13DBDF Approach 2Distance Truncated Voting
- Simple majority voting performed among nodes
close enough to the target. Decisions from other
nodes are discarded. - Parameter max/threshold distance
- Reduces effect of localization error
- No decision will be made when vehicle is outside
the distance threshold
14DBDF Approach 3Nearest Neighbor Fusion
- Node closest to target will also have highest
SNR, and hence the highest probability of
correctness - Region will assign same label as that assigned by
the node closest to the target - Lowest computational and communicational burden
- Accuracy of node to target distance critical in
decision making
15Weighted Voting Schemes
- This amounts to assigning weights
- MAP Fusion
- Distance Truncated Voting
- Nearest Neighbor
- Baseline simple Majority voting (wi1 for all i)
16Experiments
- All 4 methods are compared
- Data from SensIT SITEX02, November 2001
- Distance groups by 20m, SNR groups by 5dB
- Distance truncated voting for 50m
- Nearest Neighbor
- Majority Voting
- Due to shortcomings in localization, experiments
are run with different error levels in location
estimate s 0m, s 12.5m, s 25m, s 50m.
17Experiment Results
18Experiment ResultsClassification Rate
DTV
19Experiment Results
- Closest node gives highest acceptance,
classification rates for accurate localization
estimates - MAP Fusion has smaller dependence on localization
error than other methods - All DBDF methods outperform simple majority
voting due to the use of distance and SNR
information.
20Further Work
- MAP Classifier allows for exclusion of those
samples with low classification rates (i.e. only
samples with wi gt 0.5 are allowed). - This will allow for reduction of communication
bandwidth used for classification fusion. - This method can be applied to other signal
processing tasks. - Website http//www.ece.wisc.edu/sensit