Model Based Event Detection in Sensor Networks

1

• Model Based Event Detection in Sensor Networks

Jayant Gupchup, Andreas Terzis, Randal Burns,
Alex Szalay
2
Outline

• Motivation
• Data Model
• Experiments and Results
• Discussion

3

• Motivation

4
Importance of detecting events

• Fixed Sampling
• High Freq gt too much data
• Low Freq gt miss temporal transients
• Detect Events Adaptive Sampling
• (increase of usable data)
• Conserve Energy
• Alarm Triggers
• Correlate events and observed
• phenomena in large databases

5
Sample Event
6
Solution Rough Sketch

• Model observed quantities using Principal
  Component Analysis (PCA).
• Project original data on a feature space
  (reduce dimensionality)
• Look for observations deviating from
  Average/Expected behavior in the feature space

7
Principal Component Analysis (PCA)

• PCA
• Finds axes of
• maximum
• variance
• Reduces original
• dimensionality
• (In e.g. from
• 2 variables gt
• 1 variable)

8
Motivation for Using PCA
9
Why Not Soil Moisture ?
Reaction to event
Reaction to event
10

• LifeUnderYourFeet Data
• Model Preparation

11
LifeUnderYourFeet data

• 10 MICAz Sensors
• Air Temperature (AT)
• Soil Temperature (ST)
• Soil Moisture
• Photo Sensor

12
Air Temp vs. Soil Temp
13
Data Preparation

• Model built on Air temperature and Soil
  Temperature.

Size of matrix ( of days x 10) X 144
14
(No Transcript)
15
PCA Bases (AT ST)
Eigenvector1 Is the Diurnal cycle
similarity eigenvector1 for ST eigenvector2 for
AT
16

• Methods and Results

17
Methods

• Three methods
• 1) Basic Method
• Projections on the first principal component for
  AT
• 2) Highpass Method
• Removes seasonal drift by looking at sharp
  changes in the local neighborhood.
• 3) Delta method
• Makes use of the inertia of the soil and seasonal
  drift

18
Test Data

• Test Period 225 days between September, 2005
  July, 2006
• 48 major events were known to occur (taken from
  the BWI weather station,
• http//www.wunderground.com/US/MD/Bwi_Airport.htm
  l)
• Offline Analysis

19
Method 1 Basic Method

• Considers only Air Temperature.
• First Basis Vector covers 55 of variation in the
  data

First Basis Vector (PC1)

X
1 day
Average
Day n
Day 1
Day 2
20
Method 1 Basic Method (cont.)

• Results
• Drawback
• Does not consider seasonal drift
• Does not make use of the inertia information of
  the soil.

21
Method 2 Highpass Method

• Again, Considers only Air Temperature
• Highpass filter on E1 series. Call this series
  S1
• Highpass filters detects sharp changes by
  considering the local neighborhood only gt
  Removing seasonal drift
• Threshold on S1, values below the threshold
  are tagged as events.

22
Method 2 Highpass Method (cont.)

• Results
• Drawback
• Does not make use of the inertia information of
  the soil.

23
Method 3 Delta Method

• Considers Air Temperature and Soil Temperature
• Create E1 series for AT and E1 series for ST
  separately as discussed before
• Highpass filter on AT_E1 ST_E1
• gt AT_S1 ST_S1
• Delta AT_S1 ST_S1 for all days.
• Set a threshold on the Delta series.

24
Method 3 Delta Method (cont.)

• Results

25
Event detection for 12/13/2005 01/02/2006
Due to the inertia of the soil, Delta method
shows sharper negative peaks for event days.
26

• Discussion

27
Future work

• Implement Online event detection
• Compute Basis vectors from historic data.
• Load the basis vectors and threshold values
  on the motes.
• Apply technique for faulty sensor detection
• Detect localized events by forming clusters of
  motes with similar eigencoefficients.
• Consider variants of PCA (Gappy-PCA, online-PCA).

28
Acknowledgements

• Ching-Wa Yip 1
• - PCA C library and Discussions.
• Katalin Szlavecz 2 Razvan Musaloui-E 3
• Domain expertise and data collection.
• Jim Gray 4 Stuart Ozer 4
• Online database
• 1 JHU, Dept of Physics Astronomy
• 2 JHU, Dept of Earth and Planetary science
• 3 JHU, Dept of Computer Science.
• 4 Microsoft Research

29
Future work

• Online event detection on the motes
• Apply this method for faulty sensor detection
• Detect localized events by forming clusters of
  motes with similar eigencoefficients.
• Consider incomplete days using Gappy-PCA.
• Explore incremental robust PCA techniques.

30
Training Set (Air Temp)

• Seasons exhibit Diurnal Cycles around their
  daily mean (DC component)
• Construct Zero-Mean Vectors for each Sensori for
  each day (remove DC Component)

• Remove outliers using a
• simple median filter to
• build the training set X