DOC PREVIEW
GT CS 7450 - Time Series Data

This preview shows page 1-2-3-19-20-38-39-40 out of 40 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 40 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

1Time Series DataCS 4460/7450 - Information VisualizationMarch 18, 2010John StaskoTime Series Data• Fundamental chronological component to the data set• Random sample of 4000 graphics from 15 of world‟s newspapers and magazines from ‟74-‟80 found that 75% of graphics published were time series Tufte, Vol. 1Spring 2010 2CS 4460/74502Data Sets• Each data case is likely an event of some kind• One of the variables can be the date and time of the event• Ex: sunspot activity, baseball games, medicines taken, cities visited, stock prices, etc.Spring 2010 3CS 4460/7450Meta Level• Consider multiple stocks being examined• Is each stock a data case, or is a price on a particular day a case, with the stock name as one of the other variables?• Confusion between data entity and data casesSpring 2010 4CS 4460/74503Data Mining• Data mining domain has techniques for algorithmically examining time series data, looking for patterns, etc.• Good when objective is known a priori• But what if not? Which questions should I be asking? InfoVis better for thatSpring 2010 5CS 4460/7450Tasks• What kinds of questions do people ask about time series data?Spring 2010 6CS 4460/74504Time Series User Tasks• Examples When was something greatest/least? Is there a pattern? Are two series similar? Do any of the series match a pattern? Provide simpler, faster access to the seriesSpring 2010 7CS 4460/7450Other Tasks• Does data element exist at time t ?• When does a data element exist?• How long does a data element exist?• How often does a data element occur?• How fast are data elements changing?• In what order do data elements appear?• Do data elements exist together?Muller & Schumann ‟03citingMacEachern „95Spring 2010 8CS 4460/74505Taxonomy• Discrete points vs. interval points• Linear time vs. cyclic time• Ordinal time vs. continuous time• Ordered time vs. branching time vs. time with multiple perspectivesMuller & Schumann ‟03citingFrank „98Spring 2010 9CS 4460/7450Fundamental Tradeoff• Is the visualization time-dependent, ie, changing over time (beyond just being interactive) StaticShows history, multiple perspectives, allows comparison Dynamic (animation)Gives feel for process & changes over time, has more space to work withSpring 2010 10CS 4460/74506Standard Presentation• Present time data as a 2D line graph with time on x-axis and some other variable on y-axisSpring 2010 11CS 4460/7450Classic ViewsSpring 2010 12CS 4460/74507Fun OneSpring 2010 CS 4460/7450 13What If Everybody in Canada Flushed At Once?http://www.patspapers.com/blog/item/what_if_everybody_flushed_at_once_Edmonton_water_gold_medal_hockey_game/Today’s Focus• Examination of a number of case studies• Learn from some of the different visualization ideas that have been created• Can you generalize these techniques into classes or categories?Spring 2010 14CS 4460/74508Nice overviewSpring 2010 15CS 4460/7450Example 1• Calendar visualization• Present series of events in context of calendarSpring 2010 16CS 4460/74509Tasks• See commonly available times for group of people• Show both details and broader contextSpring 2010 17CS 4460/7450One SolutionMackinlay, Robertson & DeLineUIST „94Spiral CalendarSpring 2010 18CS 4460/745010Another ViewTime Latticex - daysy - hoursz - peopleUses projected shadows on wallsSpring 2010 19CS 4460/7450Example 2• Personal histories Consider a chronological series of events in someone‟s life Present an overview of the events ExamplesMedical historyEducational backgroundCriminal historySpring 2010 20CS 4460/745011Tasks• Put together complete story• Garner information for decision-making• Notice trends• Gain an overview of the events to grasp the big picture Spring 2010 21CS 4460/7450Lifelines ProjectVisualize personalhistory in somedomainVideoDemoPlaisant et alCHI „96Spring 2010 22CS 4460/745012Medical DisplaySpring 2010 23CS 4460/7450Features• Different colors for different event types• Line thickness can correspond to another variable• Interaction: Clicking on an event produces more details• Certainly could also incorporate some Spotfire-like dynamic query capabilitiesSpring 2010 24CS 4460/745013Benefits• Reduce chances of missing information• Facilitate spotting trends or anomalies• Streamline access to details• Remain simple and tailorable to various applicationsSpring 2010 25CS 4460/7450Challenges• Scalability• Can multiple records be visualized in parallel (well)?Spring 2010 26CS 4460/745014New Work• Work with query results• Need to align, rank, and filter• Medical application: Look for temporal coincidence of two eventsFirst pneuomonia and asthma attack Medical professionals don‟t want to fool with zooming and panningSpring 2010 27CS 4460/7450LifeLines2: Focus on alignment along eventsWang et alCHI „08VideoSpring 2010 28CS 4460/745015Spring 2010 CS 4460/7450 29Example 3• Understand patterns of presence/events over time• Focus: People‟s presence/movements in some space• Situation: Workers punch in and punch out of a factory Want to understand the presence patterns over a calendar year• Alternate: Power plant electricity usage over a yearvan Wijk & van SelowInfoVis „99Particulars• Who is user? – Factory boss/manager• Problem – Show this large amount of data in an easily understandable and query-able manner• Data – Punch in/out times for workersSpring 2010 CS 4460/7450 3016Ideas• Any ideas on what we could do here?Spring 2010 CS 4460/7450 31Spring 2010 CS 4460/7450 32One IdeaGoodTypical daily patternSeasonal trendsBadWeekly patternDetails17Spring 2010 CS 4460/7450 33Approach Taken• Cluster analysis Find two most similar days, make into one new composite Keep repeating until some preset number left or some condition met• How can this be visualized? Ideas?Spring 2010 CS 4460/7450 34Display18Characteristics• Unique types of days (individual or cluster) get their own color• Contextually placed in calendar and line graph for it is shown• Stop clustering when a threshold met or at a predetermined number of clustersSpring 2010 CS 4460/7450 35Spring 2010 CS 4460/7450 36Interaction• Click on day, see its graph• Select a day, see similar ones• Add/remove clusters19Spring 2010 CS 4460/7450 37Insights• Traditional office hours followed• Most employees present in late morning• Fewer people are present on summer


View Full Document

GT CS 7450 - Time Series Data

Documents in this Course
Animation

Animation

23 pages

Load more
Download Time Series Data
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Time Series Data and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Time Series Data 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?