Powerpoint template for scientific posters Swarthmore College

1
Mining Sensor Data in Smart Environment for
Temporal Activity Prediction Vikramaditya R.
Jakkula Diane J. CookWashington State
University First International Workshop on
Knowledge Discovery from Sensor Data (Sensor-KDD
'07)

• Introduction
• Use Allens Temporal Relations 3 to identify
  temporal relations among Activities in Daily Life
  of the resident.
• Allens relations form the basic representation
  of the temporal intervals, which when used with
  constraints become a powerful method of
  expressing expected temporal orderings between
  events in a smart environment.
• In this poster we consider the problem of
  activity prediction based on the discovery and
  application of temporal relations.
• Smart Home Goals

Temporal Relations It is common to describe
scenarios using time intervals rather than time
points - James F.
Allen
Step 3 Temporal Rules Enhancement to the
Prediction.
Experimentation Results Step 1 Process raw
data to form temporal intervals
Pseudo code Temporal Rules Enhanced
prediction. 1 Get the current predicted output
and check for any rule which satisfies it. If yes
proceed else goto next predicted. 2 Now we
check for the relation and based on the evidence
as calculated by equation displayed below if it
is greater than Mean2 Std. Dev. Then add this
to the predicted. 3 If relation is after the
evidence becomes cumulative until greater then
Mean 2Std. Dev.
Time Interval ?
Algorithm Temporal Interval Analyzer   Input
data timestamp, event name and state Repeat
While Event Event 1 found
Find paired ON or OFF events in data to
determine temporal range.
Read next event and find temporal range.
Identify relation type between event pair from
possible relation types (see
Table 1). Record relation type and
related data. Increment Event Pointer
Loop until End of Input.  
Food
Figure 3. Smart Home Scenario illustrated using
temporal relations.

• Equation to calculate evidence using Probability
  of occurrence
• P(ZY) After(Y,Z) During(Y,Z)
  OverlappedBy(Y,Z) MetBy(Y,Z)
  Starts(Y,Z) StartedBy(Y,Z)
  Finishes(Y,Z) FinishedBy(Y,Z)
  Equals(Y,Z) / Y

Water
Pills
Results
Food Contains water or Water Before
pills or Food Meets pills or Food
Contains water before pills

• Real data had 1.86 and synthetic data had 7.81
  prediction improvements.
• Good model for offline prediction of multiple
  events.
• Cannot adapt to online dynamic model of the
  environment.

Why Temporal Relations?
Data Collection Environment

• Step 2 Association rule generation using Weka
• Use Apriori classifier in Weka 2 for generating
  best rules with a given support and confidence.

Online Model Enhance existing ALZ prediction
4. PredictioncP(CP)
P(CP)SEQP(CP)TEM/Global (a P(CP)TEM)
Where a CPHRASE / CGLOBAL .
Conclusions

• Unique and new Approach.
• Real data had 1.86 and synthetic data had 7.81
  improvement.
• Larger datasets would be incorporated.
• Extended model includes direct application of
  temporal relations based probability to calculate
  the prediction.
• expansion of the temporal relations by including
  more temporal relations, such as until, since,
  next, and so forth, to create a richer collection
  of useful temporal relations.

Figure 1. MavHome Smart Home Architecture 1

• The major goal of MavHome project is to design an
  environment that acts as an intelligent agent and
  can acquire information about the resident and
  the environment in order to adapt the environment
  to the residents and meet the goals of comfort
  and efficiency.
• This sensor network consists of around 100
  sensors include motion, devices, light, pressure,
  humidity and more.
• Unified project incorporating varied AI
  techniques cross disciplinary with mobile
  computing, databases ,multimedia, and others.

Literature cited
1 G. Michael Youngblood, Lawrence B. Holder,
and Diane J. Cook. Managing Adaptive
Versatile Environments. Proceedings of the IEEE
International Conference on Pervasive
Computing and Communications, 2005. 2 Ian H.
Witten, Eibe Frank. 2005. Data Mining Practical
Machine Learning Tools and Techniques,
2nd Edition. Morgan Kaufmann, San Francisco.
3James F. Allen, and George Ferguson, Actions
and Events in Interval Temporal Logic,
Technical Report 521, July 1994. 4 K.
Gopalratnam D. J. Cook (2004). Active LeZi An
Incremental Parsing Algorithm for
Sequential Prediction. International Journal of
Artificial Intelligence Tools.
14(1-2)917-930.
Figure 2. Real Synthetic Datasets.
Allens 13 Relations
3
Temporal Relation Usable Before
X After
? During
? Contains
X Overlaps
X Overlapped-By ? Meets
X Met-by
? Starts
? Started-By
? Finishes
? Finished-By ? Equals
?
Acknowledgments This work is supported by NSF
grant IIS-0121297. Contact Us Vikramaditya R.
Jakkula vikramaditya_at_wsu.edu Diane J.
Cook cook_at_eecs.wsu.edu

• Due to small datasets used, we use the top rules
  generated with a minimum confidence of 0.5 and a
  minimum support of 0.01.
• Confidence level above 0.5 and support above 0.05
  could not be used, as they could not result in
  any viable rules.

.