raffay hamid amos johnson samir batta aaron bobick charles isbell graham coleman
Download
Skip this Video
Download Presentation
Raffay Hamid, Amos Johnson, Samir Batta, Aaron Bobick, Charles Isbell, Graham Coleman

Loading in 2 Seconds...

play fullscreen
1 / 47

a n - PowerPoint PPT Presentation


  • 294 Views
  • Uploaded on

Activity Discovery and Anomalous Activity Explanation Raffay Hamid, Amos Johnson, Samir Batta, Aaron Bobick, Charles Isbell, Graham Coleman Activity Discovery and Anomalous Activity Explanation Activity Discovery and Anomalous Activity Explanation

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'a n ' - oshin


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
raffay hamid amos johnson samir batta aaron bobick charles isbell graham coleman

Activity Discovery and Anomalous Activity Explanation

Raffay Hamid, Amos Johnson, Samir Batta, Aaron Bobick, Charles Isbell, Graham Coleman

activity discovery and anomalous activity explanation3
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
activity discovery and anomalous activity explanation4
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly
activity discovery and anomalous activity explanation5
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly
activity representation
Activity Representation
  • Previous representations include:
    • Stochastic Context Free Grammars
    • Expectation Grammars
    • …..
activity representation7
Activity Representation
  • Previous representations include:
    • Stochastic Context Free Grammars
    • Expectation Grammars
    • …..
  • Require some a priori information about activity structure
activity representation8
Activity Representation
  • Two pieces of information:
    • content
    • structure
  • Drawing from Natural Language Processing – treating documents as bags of words
  • Treat Activities as bags of event n-grams
  • Extraction of global structural information using local event statistics
activity representation9
Activity Representation
  • Two pieces of information:
    • content
    • structure
  • Drawing from Natural Language Processing – treating documents as bags of words –captures content well
  • Treat Activities as bags of event n-grams
  • Extraction of global structural information using local event statistics
activity representation10
Activity Representation
  • Two pieces of information:
    • content
    • structure
  • Drawing from Natural Language Processing – treating documents as bags of words –captures content well
  • Treat Activities as bags of event n-grams –captures activity structure
  • Extraction of global structural information using local event statistics
activity representation11
Activity Representation
  • Two pieces of information:
    • content
    • structure
  • Drawing from Natural Language Processing – treating documents as bags of words –captures content well
  • Treat Activities as bags of event n-grams –captures activity structure
  • Extraction of global structural information using local event statistics
activity discovery and anomalous activity explanation14
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly
activity discovery and anomalous activity explanation15
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly

- Occur frequently

- Are similar to each other

activity discovery and anomalous activity explanation16
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly

- Activity similarity

- Activity discovery

activity similarity
Activity Similarity
  • Two types of differences
    • core structural differences (csd)
    • event frequency differences (efd)
  • Sim (A,B) = w1*CSD(A,B) + w2*EFD(A,B)
  • Properties:
    • Identity
    • Commutative
    • Positive semi-definite
activity similarity18
Activity Similarity
  • Two types of differences
    • core structural differences (csd)
    • event frequency differences (efd)
  • Properties:
    • Identity
    • Commutative
    • Positive semi-definite
activity similarity19
Activity Similarity
  • Two types of differences
    • core structural differences (csd)
    • event frequency differences (efd)
  • Properties:
    • Identity
    • Commutative
    • Positive semi-definite
activity discovery and anomalous activity explanation20
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly

Activity similarity

- Activity discovery

activity sub class discovery
Activity Sub-Class Discovery
  • Recall: regular activities occur frequently and are similar to each other
  • Activity Sub-Class Discovery - a Graphic Theoretic problem of finding maximal cliques in edge-weighted graphs
  • Maximal Cliques: overall similarity between clique nodes greater than some value, addition of any other node would reduce the overall clique similarity
activity sub class discovery22
Activity Sub-Class Discovery
  • Recall: regular activities occur frequently and are similar to each other
  • Activity Sub-Class Discovery - a Graphic Theoretic problem of finding maximal cliques in edge-weighted graphs
  • Maximal Cliques: overall similarity between clique nodes greater than some value, addition of any other node would reduce the overall clique similarity
activity sub class discovery23
Activity Sub-Class Discovery
  • Recall: regular activities occur frequently and are similar to each other
  • Activity Sub-Class Discovery - a Graphic Theoretic problem of finding maximal cliques in edge-weighted graphs
  • Maximal Cliques: overall similarity between clique nodes greater than some value, addition of any other node would reduce the overall clique similarity
activity sub class discovery24
Activity Sub-Class Discovery
  • Sequentially find maximal cliques in edge weighted graph of activities
  • Activities different enough from all the regular activities are anomalies
activity sub class discovery25
Activity Sub-Class Discovery
  • Sequentially find maximal cliques in edge weighted graph of activities
  • Activities different enough from all the regular activities are anomalies
activity sub class discovery26
Activity Sub-Class Discovery
  • Sequentially find maximal cliques in edge weighted graph of activities
  • Activities different enough from all the regular activities are anomalies
activity discovery and anomalous activity explanation27
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly
activity discovery and anomalous activity explanation28
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly

Activity classification

- Anomaly detection

activity classification
Activity Classification
  • Compute weighted similarity between a new activity T and previous class members as:
  • Select membership sub-class as:
activity classification30
Activity Classification
  • Compute weighted similarity between a new activity T and previous class members as:
  • Select membership sub-class as:
activity discovery and anomalous activity explanation31
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly

Activity classification

- Anomaly detection

anomaly detection
Anomaly Detection
  • Define function
  • Learn the detection threshold from training data
anomaly detection33
Anomaly Detection
  • Define function
  • Represents the within-Class difference of the test activity w.r.t. previous class members
  • Pick a particular threshold to detect anomalies
anomaly detection34
Anomaly Detection
  • Define function
  • Represents the within-Class difference of the test activity w.r.t. previous class members
  • Pick (learn) a particular threshold to detect anomalies
activity discovery and anomalous activity explanation35
Activity Discovery and Anomalous Activity Explanation
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly
anomaly explanation
Anomaly Explanation
  • Explanatory features:
    • Consistent
    • Frequent
  • Explanation based on features that were:
    • Deficientfrom an anomaly but were frequently and consistentlypresent in regular members
    • Extraneous in an anomaly but consistently absentfrom the regular members
anomaly explanation37
Anomaly Explanation
  • Explanatory features:
    • Consistent
    • Frequent
  • Explanation based on features that were:
    • Deficientfrom an anomaly but were frequently and consistentlypresent in regular members
    • Extraneous in an anomaly but consistently absentfrom the regular members
anomaly explanation38
Anomaly Explanation
  • Explanatory features:
    • Consistent
    • Frequent
  • Explanation based on features that were:
    • Deficientfrom an anomaly but were frequently and consistentlypresent in regular members
    • Extraneous in an anomaly but consistently absentfrom the regular members
slide40

Experimental Setup – Loading Dock

  • Barns & Nobel Loading Dock Area
  • One month worth of data:
    • 5 days a week – 9 a.m. till 5 p.m.
  • Event Vocabulary – 61 events
  • 195 activities:
    • 150 train activities + 45 test activities

Bird’s Eye View of

Experimental Setup

slide41

Results

General Characteristics of

Discovered Activity Classes

  • UPS Delivery Vehicles
  • Fed Ex Delivery Vehicles
  • Delivery Trucks – multiple packages delivered
  • Cars and vans, only 1 or 2 packages delivered
  • Motorized cart used to pick and drop packages
  • Van deliveries – no use of motorized cart
  • Delivery trucks – multiple people
slide42

Results

General Characteristics of

Discovered Activity Classes

Few of the detected Anomalies

  • UPS Delivery Vehicles
  • Fed Ex Delivery Vehicles
  • Delivery Trucks – multiple packages delivered
  • Cars and vans, only 1 or 2 packages delivered
  • Motorized cart used to pick and drop packages
  • Van deliveries – no use of motorized cart
  • Delivery trucks – multiple people
  • Back door of delivery not closed
  • (b) More than usual number of people
  • involved in unloading
  • (c) Very few vocabulary events performed
slide43

Results

  • Are the detected anomalous activities ‘interesting’ from human view-point?

Anecdotal Validation:

    • Studied 7 users
    • Showed each user 8 regular activities selected randomly
    • Showed each user 10 test activities, 5 regular and 5 detected anomalous activities
    • 8 out of 10 activity-labels of the users matched the labels of our system
    • Probability of this match happening by chance is 4.4%
slide44

Experimental Setup – House Environment

  • House environment – Commercially available strain gages
  • Five month worth of daily data (151 days):
  • Event Vocabulary – 16 events
  • 151 activities

Top View of

Experimental Setup

activity discovery and anomalous activity explanation recap
Activity Discovery and Anomalous Activity Explanation - Recap
  • Anomaly - “deviation” from the “common” or “regular”
  • Key Questions:
    • ‘representation’ of activities
    • ‘regular’ activities
    • ‘different’ from regular
    • ‘explain’an anomaly
hard question s
Hard Question(s)
  • Importance of semantically meaningful activity-classes?
  • If not – can we construct a rules to translate computer-discovered classes to something human interpretable?
ad