Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

of

LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 1 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 2 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 3 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 4 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 5 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 6 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 7 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 8 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 9 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 10 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 11 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 12 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 13 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 14 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 15 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 16 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 17 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 18 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 19 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 20 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 21

YouTube videos are no longer supported on SlideShare

View original on YouTube

YouTube videos are no longer supported on SlideShare

View original on YouTube

LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 24 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 25 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 26 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 27 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 28

YouTube videos are no longer supported on SlideShare

View original on YouTube

LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 30 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 31 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 32 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 33 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 34 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 35 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 36 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 37 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 38 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 39 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 40 LifeFlow: Understanding Millions of Event Sequences in a Million Pixels Slide 41
Upcoming SlideShare
EventFlow Presentation
Next
Download to read offline and view in fullscreen.

Share

LifeFlow: Understanding Millions of Event Sequences in a Million Pixels

Download to read offline

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all
  • Be the first to like this

LifeFlow: Understanding Millions of Event Sequences in a Million Pixels

  1. 1. event event event event eventevent event event LIFE event event event event event event event event
  2. 2. Time Event type ( 7:00 am, Wake up ) event event event event eventevent event event LIFE event event event event event event event event
  3. 3. event event event event eventevent event event LIFE event event event event event event event event “Event Sequence”
  4. 4. Human Activities( 7:00 am, Wake up ) ( 7:10 am, Shower ) ( 7:30 am, Breakfast )
  5. 5. Traffic Incidents Logs( 9:30 am, Notification ) ( 9:55 am, Units arrived) ( 10:30 am, Scene cleared )
  6. 6. Event Sequences Human Activities Electronic Health Records Traffic Incident Logs Usability Study Logs Web logs and more…
  7. 7. Physicians atWashington Hospital Center
  8. 8. Electronic Health Records•  E.g. patient transfers in the hospital•  Event types: ARRIVAL Arrive the hospital EMERGENCY Emergency room ICU Intensive Care Unit FLOOR Normal room DISCHARGE-ALIVE Leave the hospital alive DIE Leave the hospital dead
  9. 9. Improve the Quality of Care! Patient ID: 45851733 Patient ID: 45851732!"#$"#"$$%&!(") &*++,-./& Emergency Department!"#$"#"$$%&!(")ID: 45851731 Patient &012+32456& !"#$"#"$$%&!(") &*++,-./& 6,000+!"#$"#"$$%&""( &789& !"#$"#"$$%&!(") &012+32456& !"#$"#"$$%&!(") &*++,-./&!"#$:#"$$%&$:($; &</==+& !"#$"#"$$%&""( &789& !"#$"#"$$%&!(") &012+32456&!"#$%#"$$%&!$($" &</==+& !"#$:#"$$%&$:($; &</==+& !"#$"#"$$%&""( &789&!"#!#"$$%&$)(!> &?,@5A.+32& !"#$%#"$$%&!$($" &</==+& !"#$:#"$$%&$:($; &</==+&& !"#!#"$$%&$)(!> &?,@5A.+32& !"#$%#"$$%&!$($" &</==+& & !"#!#"$$%&$)(!> &?,@5A.+32& patients per month &
  10. 10. Visualizing event sequences
  11. 11. From one event sequence...•  Single record [Cousins91], [Harrison94], [Plaisant98], … Patient ID: 45851737 !"#$"#"$$%&!(") &*++,-./& !"#$"#"$$%&!(") &012+32456& !"#$"#"$$%&""( &789& !"#$:#"$$%&$:($; &</==+& !"#$%#"$$%&!$($" &</==+& !"#!#"$$%&$)(!> &?,@5A.+32& & Time Patient #45851737 Arrival Emergency Room ICU Floor Discharge compact
  12. 12. To multiple event sequences...•  Search [Fails06], [Wang08], [Vrotsou09], …
  13. 13. To multiple event sequences...•  Search [Fails06], [Wang08], [Vrotsou09], …
  14. 14. To multiple event sequences...•  Search [Fails06], [Wang08], [Vrotsou09], …•  Group [Phan07], [Burch08], [Wang09], … 1 { 2 {
  15. 15. Summarizee.g. 1) What happened to the patients after they arrived? Arrival! ? ? 2) What happened to the patients before & after ICU? ICU! ? ? ? ?
  16. 16. Overview / Summary Millions of records!
  17. 17. Challenges•  Display millions of records on one screen –  Limited space (typical monitors) –  Scalability (millions of records?) –  Aggregation•  While preserve important information –  All possible sequences –  Gap between each pair of events
  18. 18. LIFEFLOW Picture > 1000 wordsLifeFlow > 1000 event sequences
  19. 19. LIFEFLOW… is novel… is scalable… provides the missing overview… summarizes all possible sequences and time gap between events
  20. 20. VIDEO esign wDLifeFlo
  21. 21. DEMO emonstration wDLifeFlo
  22. 22. Case Study#1: Medical6,000+ Improve the Quality of Care!patients per month Feedback •  Big picture + anomalies •  Less worry about query formulation, more time thinking about new questions •  Long-term monitoring
  23. 23. Case Study#2: Transportation200,000+ Compare traffic agencies ! traffic incidents
  24. 24. 100 years!
  25. 25. Clean the data.
  26. 26. Video
  27. 27. Case Study#2: Transportation200,000+ Compare traffic agencies ! traffic incidents Feedback •  Reveal unexpected sequences •  Identify data errors •  Can ask more questions, faster, and richer
  28. 28. Other Datasetse.g. researchers’ publications (from Springer)
  29. 29. 9,000+ JOURNAL (1ST) researchers JOURNAL BOOK CHAPTER (1ST) BOOK CHAPTER
  30. 30. DataKitchenMake your raw data ready to eat
  31. 31. Take away messages•  Life is full of event sequences.•  LifeFlow is a visual summary that supports an exploration of event sequences.•  We will be happy to try LifeFlow with your data.
  32. 32. Acknowledgement•  Washington Hospital Center Phuong Ho, Mark Smith, David Roseman http://www.whcenter.org•  National Institutes of Health (NIH) Grant RC1CA147489-02 http://www.nih.gov•  Center for Integrated Transportation Systems Management (CITSM) (a Tier 1 Transportation Center at the University of Maryland) Michael Pack, Michael VanDaniker, Nikola Ivanov http://www.cattlab.umd.edu
  33. 33. Take away messages•  Life is full of event sequences.•  LifeFlow is a visual summary that supports an exploration of event sequences.•  We will be happy to try LifeFlow with your data. Contact me kristw@cs.umd.edu! www.cs.umd.edu/hcil/lifeflow

Views

Total views

15,243

On Slideshare

0

From embeds

0

Number of embeds

12,013

Actions

Downloads

29

Shares

0

Comments

0

Likes

0

×