Using GPS to learn significant locations and predict movement across multiple users Daniel Ashbrook, Thad Starner College Of Computing, Georgia Institute.

Slides:



Advertisements
Similar presentations
By Venkata Sai Pulluri ( ) Narendra Muppavarapu ( )
Advertisements

CPSC 502, Lecture 15Slide 1 Introduction to Artificial Intelligence (AI) Computer Science cpsc502, Lecture 15 Nov, 1, 2011 Slide credit: C. Conati, S.
Korea Univ. Division Information Management Engineering UI Lab. Korea Univ. Division Information Management Engineering UI Lab. S E M I N A R Predictive.
Spatiotemporal Pattern Mining For Travel Behavior Prediction UIC IGERT Seminar 02/14/2007 Chad Williams.
Generated Waypoint Efficiency: The efficiency considered here is defined as follows: As can be seen from the graph, for the obstruction radius values (200,
Context-aware Query Suggestion by Mining Click-through and Session Data Authors: H. Cao et.al KDD 08 Presented by Shize Su 1.
An Approach to Evaluate Data Trustworthiness Based on Data Provenance Department of Computer Science Purdue University.
Forecasting Presence and Availability Joe Tullio CS8803.
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
TRADING OFF PREDICTION ACCURACY AND POWER CONSUMPTION FOR CONTEXT- AWARE WEARABLE COMPUTING Presented By: Jeff Khoshgozaran.
Efficient and Robust Computation of Resource Clusters in the Internet Efficient and Robust Computation of Resource Clusters in the Internet Chuang Liu,
Simulation.
A Hierarchical Energy-Efficient Framework for Data Aggregation in Wireless Sensor Networks IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 55, NO. 3, MAY.
Online Data Gathering for Maximizing Network Lifetime in Sensor Networks IEEE transactions on Mobile Computing Weifa Liang, YuZhen Liu.
Learning the meaning of places IfGi Location based Services SS 06 Milad Sabersamandari.
Query Operations: Automatic Global Analysis. Motivation Methods of local analysis extract information from local set of documents retrieved to expand.
Information from Samples Alliance Class January 17, 2012 Math Alliance Project.
Defect prediction using social network analysis on issue repositories Reporter: Dandan Wang Date: 04/18/2011.
Query Log Analysis Naama Kraus Slides are based on the papers: Andrei Broder, A taxonomy of web search Ricardo Baeza-Yates, Graphs from Search Engine Queries.
Radial Basis Function Networks
Models of Influence in Online Social Networks
Learning Significant Locations and Predicting User Movement with GPS Daniel Ashbrook and Thad Starner Learning Significant Locations and Predicting User.
DANIEL ASHBROOK AND THAD STARNER COLLEGE OF COMPUTING GEORGIA INSTITUTE OF TECHNOLOGY PERSONAL AND UBIQUITOUS COMPUTING, 2003 Using GPS to Learn Significant.
Water Contamination Detection – Methodology and Empirical Results IPN-ISRAEL WATER WEEK (I 2 W 2 ) Eyal Brill Holon institute of Technology, Faculty of.
Friends and Locations Recommendation with the use of LBSN
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification on Reviews Peter D. Turney Institute for Information Technology National.
Detecting Movement Type by Route Segmentation and Classification Karol Waga, Andrei Tabarcea, Minjie Chen and Pasi Fränti.
Mining Interesting Locations and Travel Sequences from GPS Trajectories IDB & IDS Lab. Seminar Summer 2009 강 민 석강 민 석 July 23 rd,
WALKING IN FACEBOOK: A CASE STUDY OF UNBIASED SAMPLING OF OSNS junction.
Tweet Analysis for Real-Time Event Detection and Earthquake Reporting System Development.
When Experts Agree: Using Non-Affiliated Experts To Rank Popular Topics Meital Aizen.
Mining Shifting-and-Scaling Co-Regulation Patterns on Gene Expression Profiles Jin Chen Sep 2012.
Incident Threading for News Passages (CIKM 09) Speaker: Yi-lin,Hsu Advisor: Dr. Koh, Jia-ling. Date:2010/06/14.
Recognition of spoken and spelled proper names Reporter : CHEN, TZAN HWEI Author :Michael Meyer, Hermann Hild.
Center for E-Business Technology Seoul National University Seoul, Korea BrowseRank: letting the web users vote for page importance Yuting Liu, Bin Gao,
Intelligent Database Systems Lab N.Y.U.S.T. I. M. A Web 2.0-based collaborative annotation system for enhancing knowledge sharing in collaborative learning.
Friends and Locations Recommendation with the use of LBSN By EKUNDAYO OLUFEMI ADEOLA
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Wireless Sensor Network Wireless Sensor Network Based.
BotGraph: Large Scale Spamming Botnet Detection Yao Zhao, Yinglian Xie, Fang Yu, Qifa Ke, Yuan Yu, Yan Chen, and Eliot Gillum Speaker: 林佳宜.
Semantic Wordfication of Document Collections Presenter: Yingyu Wu.
1 A paper by Yi-Bing Lin IEEE Transactions on Mobile Computing Vol. 4, No. 2, March/April ’05 Presented by Derek Pennington Per-User Checkpointing For.
Preserving Privacy in GPS Traces via Uncertainty- Aware Path Cloaking Baik Hoh, Marco Gruteser, Hui Xiong, Ansaf Alrabady Presented by Joseph T. Meyerowitz.
Jiafeng Guo(ICT) Xueqi Cheng(ICT) Hua-Wei Shen(ICT) Gu Xu (MSRA) Speaker: Rui-Rui Li Supervisor: Prof. Ben Kao.
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Externally growing self-organizing maps and its application to database visualization and exploration.
Project Lachesis: Parsing and Modeling Location Histories Daniel Keeney CS 4440.
Session 15 IELTS WRITING : Tables. 2014LIU LINGLING2 Writing task five: tables Task description You will be given one table of figures. Your task is to.
Molecular Classification of Cancer Class Discovery and Class Prediction by Gene Expression Monitoring.
Post-Ranking query suggestion by diversifying search Chao Wang.
1 Jong Hee Kang, William Welbourne, Benjamin Stewart, Gaetano Borriello, October 2004, Proceedings of the 2nd ACM international workshop on Wireless mobile.
Improved Video Categorization from Text Metadata and User Comments ACM SIGIR 2011:Research and development in Information Retrieval - Katja Filippova -
Predicting the Location and Time of Mobile Phone Users by Using Sequential Pattern Mining Techniques Mert Özer, Ilkcan Keles, Ismail Hakki Toroslu, Pinar.
Graph Data Management Lab, School of Computer Science Personalized Privacy Protection in Social Networks (VLDB2011)
Algorithms For Solving History Sensitive Cascade in Diffusion Networks Research Proposal Georgi Smilyanov, Maksim Tsikhanovich Advisor Dr Yu Zhang Trinity.
Speaker : Yu-Hui Chen Authors : Dinuka A. Soysa, Denis Guangyin Chen, Oscar C. Au, and Amine Bermak From : 2013 IEEE Symposium on Computational Intelligence.
1 CS 430: Information Discovery Lecture 5 Ranking.
Is Context-Aware Computing Taking Control Away from the User? Three Levels of Interactivity Examined Louise Barkhuus and Anind Dey The IT University of.
Refined Online Citation Matching and Adaptive Canonical Metadata Construction CSE 598B Course Project Report Huajing Li.
An Energy-Efficient Approach for Real-Time Tracking of Moving Objects in Multi-Level Sensor Networks Vincent S. Tseng, Eric H. C. Lu, & Kawuu W. Lin Institute.
Predicting User Interests from Contextual Information R. W. White, P. Bailey, L. Chen Microsoft (SIGIR 2009) Presenter : Jae-won Lee.
1 Systematic Data Selection to Mine Concept-Drifting Data Streams Wei Fan Proceedings of the 2004 ACM SIGKDD international conference on Knowledge discovery.
Predicting Short-Term Interests Using Activity-Based Search Context CIKM’10 Advisor: Jia Ling, Koh Speaker: Yu Cheng, Hsieh.
Instance Discovery and Schema Matching With Applications to Biological Deep Web Data Integration Tantan Liu, Fan Wang, Gagan Agrawal {liut, wangfa,
Machine Learning in Practice Lecture 9 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
黃福銘 (Angus F.M. Huang) ANTS Lab, IIS, Academia Sinica Exploring Spatial-Temporal Trajectory Model for Location.
NTNU Speech Lab 1 Topic Themes for Multi-Document Summarization Sanda Harabagiu and Finley Lacatusu Language Computer Corporation Presented by Yi-Ting.
I owa S tate U niversity Laboratory for Advanced Networks (LAN) Coverage and Connectivity Control of Wireless Sensor Networks under Mobility Qiang QiuAhmed.
What is Mobile Network? Why is it called Ad Hoc?
Market-based Dynamic Task Allocation in Mobile Surveillance Systems
Presentation transcript:

Using GPS to learn significant locations and predict movement across multiple users Daniel Ashbrook, Thad Starner College Of Computing, Georgia Institute of Technology, From Personal and Ubiquitous Computing, vol 7, no 5,

Preface Early work in this area Very simple method with 324 citation!! Both authors’ magnum opus And the papers cite it also have large number of citation 2

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 3

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 4

Introduction Wearable computers as intelligent agents assist the user in a variety of tasks Location is the most common context to determine the users’ tasks We present a system that automatically find the significant locations Create user models to predict movement 5

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 6

Previous Work Sparacino used infrared beacons to create individual models of museum visitors Liu and Maguire describe a generalized network architecture that incorporated prediction with the goal of supporting mobile computing Above using fixed sensors, but systems using GPS must determine which locations are significant 7

Previous Work Researches using GPS Wolf used stopping time to mark the starting and ending points of trip Marmasse and Schmandt used the loss of GPS signal to detect buildings 8

In This Research The goal: Construct a system to record and model an individual’s travel and predict on different scale – Answer the query like “Where is Daniel most likely to go after work?” Conducted two studies. – In 2001, a pilot study with single user in four months – In 2002, six users in seven months 9

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 10

The Pilot Study - data One user for a period of four months GPS receive rate is once per second – Valid signal and moving at one mile per hour at least The user traveled in and around Atlanta 11

The Pilot Study - methodology Find significant places Clustering places into locations Learning sublocations Prediction Definition: place = gps points which are significant location = clustered places 12

Finding significant places Latitude and longitude are useless “Home” and “Work” are meaningful The logical way to finds significant points is to look at – Where the user spends her/his time – Significant locations will be inside buildings(no GPS signal) We define a “place” with an interval of time t between it and the previous point 13

Finding significant places We need to decide what value of time t There is no clear point on the graph to choose Use 10 minutes as stopping time 14

Clustering places into locations Because of the erroneous GPS measurements, the logger won’t record exactly the same point even the user stops Use K-means to cluster the places – place list and a radius until no place remained Every cluster denotes a “location”, and is assigned a unique ID 15

16

Clustering places into locations So we need to decide the radius Too small or too large may cause problem We run our clustering algorithm several times with varying radius And find the “knee” point – Decide next n and threshold? Knee point: For each point on the graph, we find the average of it and the next n points on the right. If the current point exceeds the average by some threshold, we use it as the knee point. 17

18

Learning sublocations We subsume smaller-scale paths From city-wide scale to campus-wide scale Taking the points within each “location” and running the same clustering algorithm If a knee exists, it forms a sublocation 19

Prediction We substitute for each place the ID of the location it belongs to Markov model is created for each location with transition probability – Node is location, edge is transition probability First order and second order… nth order – Quantity of second order is small… 20

A BC Edge - transition It’s first order Markov model Compare the path’s relative frequency to the probability that the path was taken by chance (Monte Carlo simulation) 21

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 22

The Zürich study – data Conducted a second study in Zürich, Switzerland with multiple users Six users during seven months Unfortunately, one user broke the cabling for his unit and was unable to collect any data at the beginning Total 800,000 data points 23

The Zürich study – methodology Find places using time t – But now we register a place when signal is lost Cluster places to locations Markov model Place 1Place 2 Time spend between current point and previous point When signal is lost May contain park, gym, and building Only building Time t is hard to decideWe think people will tend to visit a few places often 24

Place 1 Place 2 Fewer places Place 2 Fewer places 25

The Zürich study – evaluation We present two results – The correlation between the names assigned to locations by users – Even in a different environment, the prediction generates consistent results 26

Naming across users Asked each user to give names to each location we found To see if the locations we found are common places to the users – Ex. If all user give location A the same name Of the five users, three had 11 locations within Zürich, one had 9 and one had 6 (it just express the time period they stay effect the number of locations) 27

Prediction User 1 User 2 Monte Carlo simulation result 28

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 29

Application Single-user application : – To-do list with location reminder – Detect situation Multi-user application (share user’s model) 1.Answer social query like “Will I see Daniel today?” 2.Schedule a meeting (time & location) for several people 3.Make a serendipitous meeting with friends 4.Do me a favor 30

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 31

Future Work Support time prediction Our model takes long time to update – Weighting update Online learning Suggest names for a location To-do application Combine two similar users’ location 32

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 33

Conclusion We develop an algorithm to extract significant places and locations Predictive model demonstrated patterns of movement that occurred much more frequently than chance 34

Outline Introduction Previous work The pilot study The Zürich study Application Future work Conclusion Comments 35

Comments Concept is simple Few experiment with poor evaluation The method they proposed becomes a standard scenario for location-based activity recognition The early bird catches the worm Give many application I can’t see any color 36

Recently research Most of them are devoted to extract significant locations using either GPS or other sensor then predict the movement or the activity Once we have the place and activity information, we can answer social query like “Who will I meet in lab on Friday morning?” But no more detail about users’ character Maybe we can classify the user into category and guess who have the same interest or in the same college or … It seems like an application rather than research… 37