Visual Analytics of User Behavior Project Description: Analyze and predict user behavior in a virtual world to inform dynamic modifications to the environment.

Slides:



Advertisements
Similar presentations
Mobile Shelf Monitor Shop organization for profit maximization.
Advertisements

Sheldon Brown, UCSD, Site Director Milton Halem, UMBC Director Yelena Yesha, UMBC Site Director Tom Conte, Georgia Tech Site Director Fundamental Research.
Kien A. Hua Division of Computer Science University of Central Florida.
White Master Replace with a graphic 5.5” Tall & 4.3” Wide © 2010 Adobe Systems Incorporated. All Rights Reserved. Video Distribution Philippe Degery DMO.
XProtect® Expert 2013 Product presentation
Data Mining Glen Shih CS157B Section 1 Dr. Sin-Min Lee April 4, 2006.
Sheldon Brown, UCSD, Site Director Milton Halem, UMBC Director Yelena Yesha, UMBC Site Director Tom Conte, Georgia Tech Site Director Fundamental Research.
Richard Furuta Texas A&M University Center for the Study of Digital Libraries and The Department of Computer Science Firing a transition.
How Clients and Servers Work Together. Objectives Learn about the interaction of clients and servers Explore the features and functions of Web servers.
Microsoft SharePoint 2013 SharePoint 2013 as a Developer Platform
Video Game Spectator Steven Drucker Microsoft Research.
Knowledge is Power Marketing Information System (MIS) determines what information managers need and then gathers, sorts, analyzes, stores, and distributes.
Remote Surveillance System Presented by: Robarin Holdings Limited Telephone: Facsimile:
Video management and analytics intelligent security systems intl 1 Videoo Management & ANALYTICS.
Check Disk. Disk Defragmenter Using Disk Defragmenter Effectively Run Disk Defragmenter when the computer will receive the least usage. Educate users.
Chapter 2: Business Intelligence Capabilities
1 Efficient Management of Data Center Resources for Massively Multiplayer Online Games V. Nae, A. Iosup, S. Podlipnig, R. Prodan, D. Epema, T. Fahringer,
Part or all of this lesson was adapted from the University of Washington’s “Web Design & Development I” Course materials.
“Would You Like to Play a Game?” :: Megan Winget :: University of Texas at Austin A Review of Challenges and Current Practice in Game-Related Collections.
Chapter 1 The Challenges of Networked Games. Online Gaming Desire for entertainment has pushed the frontiers of computing and networking technologies.
Annual SERC Research Review - Student Presentation, October 5-6, Extending Model Based System Engineering to Utilize 3D Virtual Environments Peter.
SAP Dashboard Mohammed Wahaj. What is SAP Dashboard “Interactive analytics is an analytic capability and “Dashboard” is an information delivery capability.”
“S ixth Sense is a wearable gestural interface device that augments the physical world with digital information and lets people use natural hand gestures.
What is Business Intelligence? Business intelligence (BI) –Range of applications, practices, and technologies for the extraction, translation, integration,
IST722 Data Warehousing Business Intelligence Design and Development Michael A. Fudge, Jr.
V. Chandrasekar (CSU), Mike Daniels (NCAR), Sara Graves (UAH), Branko Kerkez (Michigan), Frank Vernon (USCD) Integrating Real-time Data into the EarthCube.
AppVision © Integrated approach to system management Building automation Energy Management Security ManagementProcess Management (SCADA) AppVision.
© 2010 IBM Corporation © 2011 IBM Corporation September 6, 2012 NCDHHS FAMS Overview for Behavioral Health Managed Care Organizations.
Ihr Logo Data Explorer - A data profiling tool. Your Logo Agenda  Introduction  Existing System  Limitations of Existing System  Proposed Solution.
Research paper: Web Mining Research: A survey SIGKDD Explorations, June Volume 2, Issue 1 Author: R. Kosala and H. Blockeel.
N. Laskaris. [ IEEE SP Magazine, May 2004 ] N. Laskaris, S. Fotopoulos, A. Ioannides ENTER-2001.
DEVSView: A DEVS Visualization Tool Wilson Venhola.
LuxRiot is a Digital Video Recording (DVR) software package for Microsoft Windows 2000/XP/2003 Server. LuxRiot, as every modern video recording and surveillance.
COMP 410 & Sky.NET May 2 nd, What is COMP 410? Forming an independent company The customer The planning Learning teamwork.
material assembled from the web pages at
Module 10: Monitoring ISA Server Overview Monitoring Overview Configuring Alerts Configuring Session Monitoring Configuring Logging Configuring.
Cinematography in Augmented Reality Richard Shemaka.
CHAPTER TEN AUTHORING.
© 2006 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice HP Library Encryption - LTO4 Key.
Game City In this project you will learn the basics of visual programming to start creating your own games. The tool you will be using to do this is Microsoft.
Integrating Virtual Environment and GIS for 3D Virtual City Development and Urban Planning Bin Chen, Fengru Huang, Yu Fang Peking University.
Advanced Scientific Visualization
1 CS430: Information Discovery Lecture 18 Usability 3.
V Material obtained from summer workshop in Guildford County, July-2014.
I Robot.
Visual Analytics of User Behavior Project Description: Analyze and predict user behavior in a virtual world to inform dynamic modifications to the environment.
Observing users. The aims Discuss the benefits & challenges of different types of observation. Describe how to observe as an on-looker, a participant,
Web-Mining …searching for the knowledge on the Internet… Marko Grobelnik Institut Jožef Stefan.
Introduction to Interactive Media Interactive Media Tools: Authoring Applications.
Architecture View Models A model is a complete, simplified description of a system from a particular perspective or viewpoint. There is no single view.
Search Engine using Web Mining COMS E Web Enhanced Information Mgmt Prof. Gail Kaiser Presented By: Rupal Shah (UNI: rrs2146)
Distributed Data Analysis & Dissemination System (D-DADS ) Special Interest Group on Data Integration June 2000.
Participatory Simulations: immersive learning environments Emotionally engaging, “first-person” experience Identification with and use of tangible objects.
Improving O&M Skills Through the Use of VE for People Who Are Blind: Past Research and Future Potential O. Lahav School of Education, Tel Aviv University.
Spring 2007 COMP TUI 1 Computer Vision for Tangible User Interfaces.
Performance Testing Test Complete. Performance testing and its sub categories Performance testing is performed, to determine how fast some aspect of a.
Distributed Pattern Recognition System, Web-based by Nadeem Ahmed.
Microsoft Dynamics CRM Jeanett Heller Product Marketing Manager, Dynamics Microsoft Danmark.
The Virtual Observatory and Ecological Informatics System (VOEIS): Using RESTful architecture and an extensible data model to provide a unique data management.
Overview Presentation December 2007 MKT-NVO-P-002E.
Flame & Smoke Detection System Flame & Smoke Vision Detection is an intelligent vision-based analytics system which can timely detect suspicious fire or.
© Copyright AD Group Overview Presentation. © Copyright AD Group Introduction  Entry-level Video Server to the DV-IP Range  Offers incredible price–beating.
Live Global Sports Events
VIDEO.
Advanced Scientific Visualization
Business Intelligence Design and Development Michael A. Fudge, Jr.
Data Warehouse.
Introduction to Events
About Thetus Thetus develops knowledge discovery and modeling infrastructure software for customers who: Have high value data that does not neatly fit.
Objective Explain concepts used to create digital animation.
Presentation transcript:

Visual Analytics of User Behavior Project Description: Analyze and predict user behavior in a virtual world to inform dynamic modifications to the environment to create a richer virtual experience. Major Accomplishments: –Identified virtual environmental differences that affect the user’s exploration affinity level –Extended game engine technology with visualization toolset to represent user position, velocity, time, map coverage, interaction events –Utilized deterministic nature of the engine to mine additional data of interest after original play session 1

Visual Analytics of User Behavior Support Complimentary grant support: NSF EAGER (EArly Grants for Exploratory Research): “Identifying and Integrating Creative Patterns of User Behavior and Experience in Virtual Worlds” Grant description: A new interdisciplinary methodology for both the analysis of user’s experiences in virtual worlds and how this analysis can influence the behavior of the world to produce more effective user experience. This is of particular value to virtual worlds which don’t have a single “winning condition” such as a game, but instead might support a wide variety of interactive behavior, all of which are valid, but can differ widely in simple analysis. 2

Visual Analytics of User Behavior Background Present state of knowledge in virtual world analysis –network analysis (connectivity, load, latency) –econometrics on virtual economies –profiling game play activities Primarily driven by game companies –during development (Microsoft Labs, Halo series) –for an ongoing MMOG (Blizzard, World of Warcraft) –over a game network service (Steam, Xbox Live) 3

Visual Analytics of User Behavior Background Currently, virtual world design is modified based on anecdotal observation of users during sessions and interviews afterwards. This won’t be possible with massive multi-user system. As virtual world becomes more complex, the ability to understand behavior of user and system diminishes. Multi-user system will need more robust analysis methods. These methods can modify world behavior so that different interaction types can have successful experiences. 4

Visual Analytics of User Behavior Methodology New methods: Cultural Analytics –“the use of computational methods for the analysis of patterns in visual and interactive media.” –Data mining, knowledge exploration, and information visualization as applied to cultural artifacts and experiences such as paintings, cartoons, or virtual worlds. Logging, visualizing, designing –Record events in the world and telemetry on the user –Record images of user and user’s view –Visualize spatial, temporal, and narrative patterns –Explore mechanisms to dynamically modify the virtual world based on behavior patterns 5

Visual Analytics of User Behavior Logging Event logging –Server-side code hooks fire when an event occurs –Events logged as time-stamped “triples” (subject-verb-object) Object / user interactions (Player1 activates Object5) World state changes User telemetry logging –Data is polled from client at set rate (1/sec) and logged on server User input (trackball direction, velocity) User avatar position / orientation User camera position / orientation / type 6

The Real-Fake Exhibition –[April 1 – May 28, 2011] –California State University, Sacramento University Library Gallery Student Population: 27,000 –The Scalable City was featured Video monitoring system installed –To track physical interactions Virtual World monitoring system enabled –To track events, world state and archive screen renders 7 Visual Analytics of User Behavior Exhibition

The Real-Fake Exhibition –The Scalable City Approx. 73 hours of playtime recorded 528,546 lines of tracking data 2,290,000 surveillance images (41 GB) 8 Visual Analytics of User Behavior Exhibition

Database of analytics data –Events categorized in triples (Subject – Verb – Object) 9 SubjectVerbObject HousePieceactivatesCity PlayercompletesGlobeMode ServerdeactivatesHousePiece entersLot exitsRoad joinsSimulation pauses resets starts unpauses Visual Analytics of User Behavior Exhibition

Database of analytics data –User data polled and logged for each player every second 10 MeasureDescription TimestampTime of recording Player IDServer’s identification integer for the player Trackball Input(x,y) movement of the trackball since last poll Num Input EventsNumber of unique input events since last poll Current CityThe city that the player currently occupies Player PositionWorld space location of the player Player DirectionDirection the player is facing Player Activity StateMeasure of current player activity [Very Active, Active, Inactive] Camera IDIndicates camera settings, based on activity levels Camera PositionCurrent world space camera position Camera Relative PositionPosition relative to the player’s position Camera OrientationIndicates where the camera is looking Visual Analytics of User Behavior Exhibition

Image data –View of User Video feed captures user interaction with physical interface Tracks bystanders experiencing but not interacting Still images archived at one frame / second –User’s view Screen renders presented to the user are sampled and archived ( one frame / second ) Long periods of inactivity disable archiving 11 Visual Analytics of User Behavior Image Data

View of User footage –A dimension of user behavior data typically disregarded Social influences come into play Were others waiting during a user’s play session? Did the user watch someone else interact first? Did some play sessions have multiple users taking turns? 12 Visual Analytics of User Behavior Image Data

User’s View (Screen Images) –What was the player seeing in the virtual world? –Visual experience influences behavior 13 Visual Analytics of User Behavior Image Data

Image Analysis –Color distribution –Object recognition –Feature analysis 14 Visual Analytics of User Behavior Image Data

User’s View (Screen Images) –Chroma Key Rendering prototype for simplification of object recognition –Requires two simultaneous render modes Real-time performance not to par for use in exhibition 15 Visual Analytics of User Behavior Image Data

Database of analytics data –679 unique play sessions identified –Additional data mined after original sessions Facilitated by deterministic nature of engine Example: city completion level 16 Visual Analytics of User Behavior Exhibition Data

Findings from Exhibition –Trackball analysis Users tended to go left instead of right 17 Visual Analytics of User Behavior Data

Findings from Exhibition –Number of Cities visited by each user 77 % visited just one city 18 Visual Analytics of User Behavior Data

Findings from Exhibition –Starting city type drives exploration affinity to other cities Starting in curly road pattern makes users much less likely to travel to other cities 19 Visual Analytics of User Behavior Data Frequency of multi-city exploration per starting city type

Findings from Exhibition (position) 20 Visual Analytics of User Behavior Data

Findings from Exhibition (camera position) 21 Visual Analytics of User Behavior Data

Visualization Toolset –Flash based gui integrated into virtual world –Avatar visual representation controls –Indicators for position, velocity & time data –Lighting / Time of Day controls –Playback controls –Real time data visualizations 22 Visual Analytics of User Behavior Visualization

Visualization Toolset 23 Visual Analytics of User Behavior Visualization

Visualization Toolset 24 Visual Analytics of User Behavior Visualization

Visualization Toolset 25 Visual Analytics of User Behavior Visualization

Visualization Toolset 26 Visual Analytics of User Behavior Visualization

Virtual world behavior driven by analysis –Real-time analysis will customize and enhance experience on a per-user basis –Categorize user on the fly Timid Speedy Immersed –Loading based on Navigation prediction Preload assets based on paths users typically take at certain decision points. 27 Visual Analytics of User Behavior Future Work

Virtual world behavior driven by analysis –Analytics Camera Navigation assistance Based on previous user patterns –Resetting behavior Reset to environments conducive to more fulfilling experience 28 Visual Analytics of User Behavior Future Work