Laura Zavala, Radhika Dharurkar, Pramod Jagtap, Tim Finin, Anupam Joshi and Amey Sane University of Maryland, Baltimore County AAAI Workshop on Activity.

Slides:



Advertisements
Similar presentations
ROWLBAC – Representing Role Based Access Control in OWL
Advertisements

Building and Analyzing Social Networks Web Data and Semantics in Social Network Applications Dr. Bhavani Thuraisingham February 15, 2013.
CSCI 572 Project Presentation Mohsen Taheriyan Semantic Search on FOAF profiles.
Planning Value of Planning What to consider when planning a lesson Learning Performance Structure of a Lesson Plan.
Audumbar Chormale Advisor: Dr. Anupam Joshi M.S. Thesis Defense
ACOS 2010 Standards of Mathematical Practice
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
SoundSense: Scalable Sound Sensing for People-Centric Application on Mobile Phones Hon Lu, Wei Pan, Nocholas D. lane, Tanzeem Choudhury and Andrew T. Campbell.
An Intelligent Broker Architecture for Context-Aware Systems A PhD. Dissertation Proposal in Computer Science at the University of Maryland Baltimore County.
ONTOLOGY SUPPORT For the Semantic Web. THE BIG PICTURE  Diagram, page 9  html5  xml can be used as a syntactic model for RDF and DAML/OIL  RDF, RDF.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Semantics for Privacy and Context Tim Finin University of Maryland, Baltimore County Joint work with Anupam Joshi, Prajit Das, Primal Pappachan, Eduado.
SPARQL All slides are adapted from the W3C Recommendation SPARQL Query Language for RDF Web link:
Anupam Joshi and Tim Finin Ebiquity UMBC
Tim Finin University of Maryland, Baltimore County Joint work with Anupam Joshi, Laura Zavala, Radhika Dharurkar, Pramod Jagtap, Dibyajyoti Ghosh and Amey.
Intelligent Agents Meet the Semantic Web in Smart Spaces Harry Chen,Tim Finin, Anupam Joshi, and Lalana Kagal University of Maryland, Baltimore County.
TEMPLATE DESIGN © Detecting User Activities Using the Accelerometer on Android Smartphones Sauvik Das, Supervisor: Adrian.
Knowledge based Learning Experience Management on the Semantic Web Feng (Barry) TAO, Hugh Davis Learning Society Lab University of Southampton.
Deploying Trust Policies on the Semantic Web Brian Matthews and Theo Dimitrakos.
SOUPA: Standard Ontology for Ubiquitous and Pervasive Applications Harry Chen, Filip Perich, Tim Finin, Anupam Joshi Department of Computer Science & Electrical.
Tim Finin University of Maryland, Baltimore County 29 January 2013 Joint work with Anupam Joshi, Laura Zavala and our students SRI Social Media Workshop.
UMBC iConnect Audumbar Chormale, Dr. A. Joshi, Dr. T. Finin, Dr. Z. Segall.
The Ubiquitous Web as a model to lead our environment to its full potential Juan Ignacio Vazquez, Joseba Abaitua, Diego López de Ipiña W3C Workshop on.
Recognizing Activities of Daily Living from Sensor Data Henry Kautz Department of Computer Science University of Rochester.
Ontology Summit 2015 Track C Report-back Summit Synthesis Session 1, 19 Feb 2015.
Semantics for Cybersecurity and Privacy Tim Finin, UMBC Joint work with Anupam Joshi, Karuna Joshi, Zareen Syed andmany UMBC graduate students
Streaming Knowledge Bases Onkar Walavalkar, Anupam Joshi Tim Finin and Yelena Yesha University of Maryland, Baltimore County 27 October 2008.
An Ontological Framework for Web Service Processes By Claus Pahl and Ronan Barrett.
SPARQL Query Graph Model (How to improve query evaluation?) Ralf Heese and Olaf Hartig Humboldt-Universität zu Berlin.
Page 1 Alliver™ Page 2 Scenario Users Contents Properties Contexts Tags Users Context Listener Set of contents Service Reasoner GPS Navigator.
CPET 565 Mobile Computing Systems Context-Aware Computing Lecture 10 Hongli Luo Indiana University-Purdue University Fort Wayne.
Cerberus: A Context-Aware Security Scheme for Smart Spaces presented by L.X.Hung u-Security Research Group The First IEEE International Conference.
MyActivity: A Cloud-Hosted Ontology-Based Framework for Human Activity Querying Amin BakhshandehAbkear Supervisor:
Nicholas D. Lane, Hong Lu, Shane B. Eisenman, and Andrew T. Campbell Presenter: Pete Clements Cooperative Techniques Supporting Sensor- based People-centric.
The Second Life of a Sensor: Integrating Real-World Experience in Virtual Worlds using Mobile Phones Mirco Musolesi, Emiliano Miluzzo, Nicholas D. Lane,
Using Several Ontologies for Describing Audio-Visual Documents: A Case Study in the Medical Domain Sunday 29 th of May, 2005 Antoine Isaac 1 & Raphaël.
Report from the Abstract Process Clarification Sub- Committee Monday June 21, 2004.
Introduction to Dialogue Systems. User Input System Output ?
CMPS 435 F08 These slides are designed to accompany Web Engineering: A Practitioner’s Approach (McGraw-Hill 2008) by Roger Pressman and David Lowe, copyright.
SKOS. Ontologies Metadata –Resources marked-up with descriptions of their content. No good unless everyone speaks the same language; Terminologies –Provide.
Tim Finin University of Maryland, Baltimore County UMBC HON 300 / CMSC491, Spring 2012 Joint work with Anupam Joshi, Laura Zavala, Radhika Dharurkar, Pramod.
Temporal Ontology Shervin Daneshpajouh ce.sharif.edu/~daneshpajouh.
Computational Policies in a Need to Share Environment Tim Finin University of Maryland, Baltimore County SemGrail workshop, Redmond WA, 21 June 2007.
Of 38 lecture 6: rdf – axiomatic semantics and query.
THE SEMANTIC WEB By Conrad Williams. Contents  What is the Semantic Web?  Technologies  XML  RDF  OWL  Implementations  Social Networking  Scholarly.
1/14/ :59 PM1/14/ :59 PM1/14/ :59 PM Research overview Koen Victor, 12/2007.
An Ontology-based Approach to Context Modeling and Reasoning in Pervasive Computing Dejene Ejigu, Marian Scuturici, Lionel Brunie Laboratoire INSA de Lyon,
Achieving Semantic Interoperability at the World Bank Designing the Information Architecture and Programmatically Processing Information Denise Bedford.
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
1 An infrastructure for context-awareness based on first order logic 송지수 ISI LAB.
Semantic Web in Context Broker Architecture Presented by Harry Chen, Tim Finin, Anupan Joshi At PerCom ‘04 Summarized by Sungchan Park
NSF Cyber Trust Annual Principal Investigator Meeting September 2005 Newport Beach, California UMBC an Honors University in Maryland Trust and Security.
Dude, Where's My Car? And Other Questions in Context-Awareness Jason I. Hong James A. Landay Group for User Interface Research University of California.
1 Web Services for Semantic Interoperability and Integration Tim Finin University of Maryland, Baltimore County Dagstuhl, 20 September 2004
GoRelations: an Intuitive Query System for DBPedia Lushan Han and Tim Finin 15 November 2011
NEDA ALIPANAH, MARIA ADELA GRANDO DBMI 11/19/2012.
Anupam Joshi University of Maryland, Baltimore County Joint work with Tim Finin and several students Computational/Declarative Policies.
Panel: OWL Leaves the Nest Knowledge Integration for Ubiquitous Agents Harry Chen Image Matters LLC First International.
SPARQL Query Andy Seaborne. Apache Jena he.org/jena ● Open source - Apache License ● Apache Incubator (accepted November 2010) ●
OWL (Ontology Web Language and Applications) Maw-Sheng Horng Department of Mathematics and Information Education National Taipei University of Education.
FaceBlock: Semantic Context-Aware Privacy for Mobile Devices
Context Sensing.
Privacy Preservation in Context-Aware Systems
Vijay Srinivasan Thomas Phan
Mobile, Collaborative and Context-Aware Systems
Analyzing and Securing Social Networks
University of Maryland, Baltimore County
Scalable and Efficient Reasoning for Enforcing Role-Based Access Control
Deniz Beser A Fundamental Tradeoff in Knowledge Representation and Reasoning Hector J. Levesque and Ronald J. Brachman.
Presentation transcript:

Laura Zavala, Radhika Dharurkar, Pramod Jagtap, Tim Finin, Anupam Joshi and Amey Sane University of Maryland, Baltimore County AAAI Workshop on Activity Context Representation 07 August 2011 Mobile, Collaborative and Context-Aware Systems

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 2

Part of an NSF collaborative project with NC state (M. Singh & I. Rhee) and Duke (R. Choudhury) Overall theme: enable smartphones to learn and exploit a richer notion of place  Place is more than GPS coordinates  Conceptual places include people, devices, activ- ities, purpose, roles, background knowledge, etc.  Use this to provide better services and user experience Platys Project

I am … 8/6/11 4 at ( , ) vs. in a hotel, the Hyatt Regency SF, San Francisco, … participating in a meeting, a workshop, the AAAI Activity Context Representation Workshop, … with other >10 people including L. Shastri … filling a speaker role remembering I was here yesterday from 08:52 to 10:24 … seeing many WIFI access point here: … …

Sharing place information 8/6/11 5  Peer to peer communication  Opportunistic Gossiping  User privacy policies control sharing  Fixed devices acquire, store, share, and summarize

Goals Prototype and evaluate mobile context-aware applications for better services and user experiences Use smartphones to capture and reason about context Share context among devices  Develop a semantic model of context  Address privacy issues 8/6/11 6

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 7

General Interaction Architecture  Device sensors used for contextual clues  Context RDF KB on each device  Context shared with neighboring devices  Devices interact directly or via Inter- net services  Privacy policies specify user’s infor- mation sharing constraints 8/6/11 8

Current Work Semantic model of context  Grounded in explicit OWL ontologies  Linked data integration: FOAF and GeoNames  Local RDF KB +Jena on devices Context / situation recognition  Use sensors, status, settings, user data (e.g., calendar) and linked data (e.g., geonames) to recognize context  Individual activity and conceptual place recognition User privacy  Privacy policies for sharing contextual information  Prototype ad hoc sharing of context info 8/6/11 9

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 10

The Place ontology: semantic model of a person’s context  Light-weight, upper level context ontology  Centered around the concepts for  Users  Conceptual places  Activities  Roles  Time  Conceptual places such as at work and at home  Activities occur at places and involve users filling particular roles 8/6/11 11

Context KB on the devices  A KB on the device which conforms to the ontology  Links to FOAF and GeoNames  Use of Geonames to assert further spatial knwledge in the KB UMBC  Baltimore County  United States  Maryland  Baltimore County 8/6/11 12

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 13

Privacy Preservation Privacy controls in existing location sharing applications  “Friends Only” and “Invisible” restrictions are common Need for high-level, flexible, expressive, declarative policies  Temporal restriction, freshness, granularity, access model (e.g. optimistic or pessimistic)  Context dependent release of information  Obfuscation of shared information 8/6/11 14

Privacy Policies Requests come from other devices asking to share contextual information  A specified protocol  SPARQL queries Flexible privacy policies Role and group based context/location sharing Obfuscation of location nand activity information Summarization Share building-wide location with teachers on weekdays only between 9 am and 6 pm Share detailed context information with family members Do not share my context if I am in a date with girlfriend Share my room-wide location with everyone in the same building as me Rules using context model and KB on foaf:. [AllowFamilyRule: (?requester kb:contextAccess kb:userPermitted) <- (?requester rdf:type kb:requester) (?groupFamily foaf:member ?requester) (?groupFamily foaf:name "Family") ] Jena prototype on Android 8/6/11 15

Location Generalization  Share my location with teachers on weekdays from 9am-5pm  User’s exact location in terms of GPS co-ordinates is shared  The user may not be interested to share GPS co- ordinates but fine with sharing city-level location  Share my building-wide location with teachers on weekdays from 9am-5pm 8/6/11 16

Location Generalization  Hierarchical model of location to support location generalization  The transitive Part_Of property creates the location hierarchy  GeoNames spatial containment knowledge is also used when populating the KB 8/6/11 17

Activity Generalization  Share my activity with friends on weekends  User’s current activity shared w. friends on weekends  Share more generalized activity rather that precise  confidential project meeting => Working, Date => Meeting  User clearly needs to obfuscate certain pieces of activity information to protect her context info  Share my public activity with friends on weekends  Public is a visibility option 8/6/11 18

Activity Generalization 19 8/6/11

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 20

Context / situation recognition Focus on individual activity and place recognition Using smartphones as sensors we use probabilistic models for context recognition  noise, ambience light, accelerometer, Wifi, Bluetooth, call stats, phone settings, user calendar Data collection program used to collect training data to learn to recognize context  5 users, 1 month, logging TRUE activity and place attached to phone readings (noise, light, etc.)  Naive Bayes, decision tree, SVM, and bagging+decisiontrees 8/6/11 21

Context / situation recognition (process overview) Train Classifiers Decision Trees Naïve Bayes SVM Feature Vector Time, Noise level in db (avg, min, max), accel 3 axis (avg, min, max, magnitude, wifis, … 8/6/11 22

Evaluation Experiments Varying granularity level on activities  Motion, Stationary  Work, Home, Outdoors, Other  In meeting, in class, watching TV, reading, sleeping, etc. Two different schemes  Individual: training and testing on one person’s data  Across users: training with one person’s data and testing it with other’s 8/6/11 23

Results – Comparing classifiers Accuracy higher for decision tree classifiers  Improved with bagging SVMs slightly below decision trees Weak performance of Naive Bayes 8/6/11 24

Results – Generalizing activities 8/6/11 25 Some states hard to distinguish Fewer states => greater accuracy

Results – Testing across users 8/6/11 26 Accuracy drops when using a general model or one not trained on a different user

Results – Time and Location 8/6/11 27 Time and location attributes important, but adding more significantly improves accuracy

Results – Decision tree output model 8/6/11 28

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 29

Ongoing Work Collecting more data Running the model on the device Use HMMs for state recognition Incorporating common sense knowledge as priors  A person has only one home  A person has only one workplace  A meal is usually not repeated during the day  Sleeping usually occurs at night  Students study frequently 8/6/11 30

HMM data for a user 8/6/ %1%0%7%0% 1%0%1%0% 1%91%0%4%0% 3%0% 17%0%67%17%0% 10%5%0%64%11%2%1%0%1%0%1% 0% 1%0% 1%0% 3%0% 41%49%1%0% 3%1%0%1%0% 15%1%0%3%0%81%0% 1%0% 25%0% 50%0% 25%0% 50%0% 50%0% 4%0% 16%4%0% 72%0% 4%0% 7%0% 13%0% 73%0% 7%0% 1%0% 5%0% 94%0% 13%0% 5%0% 82%0% 2%0% 3%0% 6%0%89%0% 5%0% 2%0% 2%90%0% 15%0% 5%80%0% 17%0% 83%0% 100%0% 25%0% 75%0% 3%0%8%0% 89%0% 14%0% 86%0% 33%0% 67% Noise level Working Chatting Playing Walking Driving Coffee Other Meeting Shopping Dinner Sleeping Lunch Watching TV Cooking On Call Movie Class Conversation Exercising Reading Cleaning State transition probability data Emission probabilities

HMM representation Activities are the states and sensor readings such as noise and accelerometer data are the observations 8/6/11 32 A partial state transition graph with the most likely non-loop transition for each state

Future Work Policy language for policy declaration and enforcement integration  Richer policies at the triple level  Protect the inferences that can be drawn from the information that is shared  A mix of rich pattern matching such as SPARQL and rules, with First Order semantics 8/6/11 33

Depending on the kindness of strangers 8/6/11 34 People are cooperative and ask one another for information  Stanger on the street: Does this bus go to the aquarium?  Random classmate: When is HW6 due? Devices can use ad hoc networks (e.g., Bluetooth) to query nearby devices for desired information Each device has an info. sharing policy for what triples can be used to answer the query based on context and requester’s information  Mobile Ad Hoc Knowledge Network

Agenda Background, motivation and goals General interaction architecture Semantic context modeling Privacy preservation Context / situation recognition Ongoing and future work Conclusion 8/6/11 35

Conclusion 8/6/11 36 We established our baseline system for simple activity recognition in a university environment Our description logic representation enables  Inferences and rules  An expressive query language (SPARQL)  More expressive policy languages for information sharing and privacy  A natural way to give less general responses to queries