Krist Wongsuphasawat John Alexis Guerra Gomez Catherine Plaisant Taowei David Wang Ben Shneiderman Meirav Taieb-Maimon Presented by Ren Bauer.

Slides:



Advertisements
Similar presentations
Alina Pommeranz, MSc in Interactive System Engineering supervised by Dr. ir. Pascal Wiggers and Prof. Dr. Catholijn M. Jonker.
Advertisements

1 Evaluation Rong Jin. 2 Evaluation  Evaluation is key to building effective and efficient search engines usually carried out in controlled experiments.
Kien A. Hua Division of Computer Science University of Central Florida.
Workshop: Interactive Visual Exploration of Electronic Health Records David Wang, Catherine Plaisant, Ben Shneiderman University of Maryland College Park,
LifeLines:Visualizing Personal Histories Plaisant, Milash, Rose, Widoff, Shneiderman Presented by Girish Kumar and Rajiv Gandhi.
Targeting Business Users With Decision Table Classifiers Ron Kohavi and Daniel Sommerfield Presented by Andi Baritchi on 10/14/99 CSE 6362 Data Mining,
LifeLines: Visualizing Personal Histories Catherine Plaisant, Brett Milash, Anne Rose, Seth Widoff, Ben Shneiderman.
Visualizing Temporal Patterns also including… Twinlist for Medication Reconciliation Catherine Plaisant Human-Computer Interaction Lab University Of Maryland,
LifeFlow Case Study: Comparing Traffic Agencies' Performance from Traffic Incident Logs This case study was conducted by John Alexis Guerra Gómez and Krist.
Lifelines: Visualizing Personal Histories Class overview Jen Golbeck 04 Feb 02.
Evaluating Visual and Statistical Exploration of Scientific Literature Networks Robert Gove 1,3, Cody Dunne 1,3, Ben Shneiderman 1,3, Judith Klavans 2,
Patternfinder 3.0 : Sparse Temporal Data Visual Query Application Hyunyoung Song, Nathaniel Ayewah, Gleneesha Johnson Department of Computer Science, University.
1 SIMS 247: Information Visualization and Presentation Marti Hearst Oct 24, 2005.
Retrieval Evaluation. Brief Review Evaluation of implementations in computer science often is in terms of time and space complexity. With large document.
Learning-Based Anomaly Detection in BGP Updates Jian Zhang Jennifer Rexford Joan Feigenbaum.
© Anselm Spoerri Lecture 13 Housekeeping –Term Projects Evaluations –Morse, E., Lewis, M., and Olsen, K. (2002) Testing Visual Information Retrieval Methodologies.
Data Mining CS 341, Spring 2007 Lecture 4: Data Mining Techniques (I)
INF 132 Usability Testing Presentation 5. Overview of the System.
1 User Centered Design and Evaluation. 2 Overview My evaluation experience Why involve users at all? What is a user-centered approach? Evaluation strategies.
Jesper Kjeldskov Mikael B. Skov Jan Stage HCI-Lab Department of Computer Science Aalborg University Denmark Does Time Heal? A Longitudinal Study of Usability.
SpaceTree An Interactive Visualization of Traditional Node-Link Tree Diagrams Jesse Grosjean Catherine Plaisant Ben Bederson Human-Computer Interaction.
TimeCleanser: A Visual Analytics Approach for Data Cleansing of Time-Oriented Data Theresia Gschwandtner, Wolfgang Aigner, Silvia Miksch, Johannes Gärtner,
Lifelines2: Hypothesis Generation in Multiple EHRs Taowei David Wang Catherine Plaisant Ben Shneiderman Shawn Murphy Mark Smith Human-Computer Interaction.
FINDING PATTERNS IN TEMPORAL DATA KRIST WONGSUPHASAWAT TAOWEI DAVID WANG CATHERINE PLAISANT BEN SHNEIDERMAN HUMAN-COMPUTER INTERACTION LAB UNIVERSITY OF.
Data Mining – Intro.
SpaceTree: Supporting Exploration in Large Node Link Tree, Design Evolution and Empirical Evaluation Catherine Plaisant, Jesse Grosjean, Benjamin B.Bederson.
Presented by Dorian S. Conger Conger-Elsea, Inc Riveredge Parkway, Suite 740 Atlanta, GA phone fax
State of Connecticut Core-CT Project Query 4 hrs Updated 1/21/2011.
2 For Exponential Smoothing we will use the Excel Spreadsheet in this module. I created the spreadsheet so there is no copyright; do as you please Statistical.
SUNIL GAHLAWAT LU GAN MIYA SYLVESTER YIRAN WANG Usability and Utility of TopicLens a Visualization System for the Exploration of Topic Models.
Concussion Detection Research Tool Codi-Lee Hayes Samantha Mearns Rebecca Yaffe Dr. Thirimacho Bourlai Dr. Aaron Monseau.
Information Design and Visualization
Cristian Urs and Ben Riveira. Introduction The article we chose focuses on improving the performance of Genetic Algorithms by: Use of predictive models.
AuthorLink: Instant Author Co-Citation Mapping for Online Searching Xia Lin Howard D. White Jan Buzydlowski Drexel University Philadelphia,
Presented by Abirami Poonkundran.  Introduction  Current Work  Current Tools  Solution  Tesseract  Tesseract Usage Scenarios  Information Flow.
© 2010 Pearson Addison-Wesley. All rights reserved. Addison Wesley is an imprint of Designing the User Interface: Strategies for Effective Human-Computer.
Computing Fundamentals Module Lesson 19 — Using Technology to Solve Problems Computer Literacy BASICS.
Intuitive Database Query System, Zooming Query Results Previews Drawing upon existing literature on zooming interface technology, intuitive navigation.
Understanding The Semantics of Media Chapter 8 Camilo A. Celis.
Data Mining – Intro. Course Overview Spatial Databases Temporal and Spatio-Temporal Databases Multimedia Databases Data Mining.
Medical Informatics: Opportunities for Improving Patient Care Ben Founding Director ( ), Human-Computer Interaction.
Mingyang Zhu, Huaijiang Sun, Zhigang Deng Quaternion Space Sparse Decomposition for Motion Compression and Retrieval SCA 2012.
1 Test Selection for Result Inspection via Mining Predicate Rules Wujie Zheng
CS3041 – Final week Today: Searching and Visualization Friday: Software tools –Study guide distributed (in class only) Monday: Social Imps –Study guide.
Computing Fundamentals Module Lesson 6 — Using Technology to Solve Problems Computer Literacy BASICS.
March 31, 1998NSF IDM 98, Group F1 Group F Multi-modal Issues, Systems and Applications.
© 2010 Pearson Addison-Wesley. All rights reserved. Addison Wesley is an imprint of Designing the User Interface: Strategies for Effective Human-Computer.
NSF DUE ; Wen M. Andrews J. Sargeant Reynolds Community College Richmond, Virginia.
A Simulation Model for Bioterrorism Preparedness in An Emergency Room Lisa Patvivatsiri Department of Industrial Engineering Texas Tech University Presented.
On Using SIFT Descriptors for Image Parameter Evaluation Authors: Patrick M. McInerney 1, Juan M. Banda 1, and Rafal A. Angryk 2 1 Montana State University,
VizTree Huyen Dao and Chris Ackermann. Introducing example
Evaluation and Assessment of Instructional Design Module #4 Designing Effective Instructional Design Research Tools Part 2: Data-Collection Techniques.
Comp 15 - Usability & Human Factors Unit 12b - Information Visualization This material was developed by Columbia University, funded by the Department of.
Physiological Data Analysis of Neuro-Critical Patients Using Markov Models By Shashwat Bhoop sb3758.
Designing Clock View and Search View Visualization for Visual Analytics Law Enforcement Toolkit Chang Yoon Kim, Peter Adjiwibawa, Shantanu Joshi Ahmad.
Spider Charts: A Training Course
Data Mining – Intro.
Gedas Adomavicius Jesse Bockstedt
Welcome!.
Ben Shneiderman & Catherine Plaisant
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Usability & Human Factors
The Event Quartet: How Visual Analytics Works for Temporal Data Ben Shneiderman Founding Director ( ), Human-Computer Interaction.
Temporal Data Analysis and Electronic Health Records Ben Shneiderman, Catherine Plaisant, Taowei David Wang, Kris Wongsuphasawat
Stanley Lam Department of Computer Science University of Maryland
Information Design and Visualization
CHAPTER 7: Information Visualization
Computer Literacy BASICS
CHAPTER 14: Information Visualization
Presentation transcript:

Krist Wongsuphasawat John Alexis Guerra Gomez Catherine Plaisant Taowei David Wang Ben Shneiderman Meirav Taieb-Maimon Presented by Ren Bauer

 Motivation  Related Work ◦ Shortcomings  Visualization Techniques  Evaluation ◦ Case Studies ◦ User Study

 Washington Hospital Center ◦ Dr. Phuong Ho ◦ Bounce Backs ◦ Anomalous Patient Transfer Patterns  Previously viewed sequences in an MS Excel spreadsheet  Needed a more efficient option

 Temporal ◦ Timelines ◦ Spirals  Hierarchical ◦ Trees ◦ Icicle Plots

 Temporal Data Visualization

 Hierarchical Data Visualization

 Developed at the University of Maryland  Data mining tool focused on providing an overview of events ◦ Scales to any number of records ◦ Summarizes all possible sequences ◦ Highlights temporal spacing of events within sequences

 Input records  Form timelines  Combine common events  Form LifeFlow Representation

 Case Study 1: Medical Domain ◦ One dataset included 7,041 patients  ER patients from Jan 2010 ◦ Most Common: Arrival->ER->Discharge-Alive  4,591 (65.20%) ◦ 193 (2.74%) Patients LWBS, 38 (0.54%) AWOL  Can be compared with hospital standard for quality control

 Case Study 1: Medical Domain ◦ Interesting Patterns  Arrival->ER->Floor->IMC/ICU  “Step up”  Went from floor to ICU more quickly then floor to IMC  Captured screenshots to compare with standards ◦ Found 6 patients experiencing “bounce backs” ◦ Anomalous sequences  Patients being accepted into the ICU after being pronounced dead…

 Case Study 1: Medical Domain ◦ Measuring Transfer Time  Easy to make queries such as: “If patients went to the ICU, what was the average transfer time from the ER to the ICU?” ◦ Comparison  Hypothesis about IMC patients being transferred more quickly based on time of day  Found no significant difference

 Case Study 2: Transportation Domain ◦ 8 Traffic Response Agencies at U Maryland ◦ Noticed many incidents lasting 24 hours  12:30am Apr 10 th to 11:45pm Apr 10 th  Probable data entry error ◦ Ranked agencies based on performance  Fastest (Agency C) 5 minutes  Immediate Clearances  slowest (Agency G) 2 hours 27 minutes  Actually ranked fairly well for “incident”

 User Study  10 Grad students examining 91 medical records ◦ 12 minute training video ◦ 15 simple to complex tasks  “Where did patients usually go after they arrived”  “Retrieve IDs of all patients with this transfer pattern” ◦ Most tasks performed in under 20 seconds ◦ Final Task: 10 minutes to find 3 anomalies intentionally put in data  All students found first 2, most saw third but weren’t sure it was anomalous

 Motivation ◦ Need an efficient tool to compare sets of sequences ◦ Previous work insufficient  Solution ◦ LifeFlow visualization suite  Evaluation ◦ Case studies show usefulness ◦ User study shows usability

 Some of this information could be found with methods as simple as SQL searches, is this technology really necessary? ◦ What kind of information could it not help us find?  Traffic agencies were ‘ranked’ based on response time, but further investigation revealed these rankings may not mean anything, what are the dangers of technology such as this?