Context Aware Technology

1
Context Aware Technology

• Jae Doo Huh
• 2008. 3. 11

2
Contents

• I. Introduction
• II. Context?
• Future Computing
• Ubiquitous Computing
• Motivation
• Smart Device
• III. Context-aware Computing
• Context-aware Computing
• Context who, where etc..
• Context Modeling
• Service Application
• IV. Context-aware Services

3
I. Introduction

• Paradigm Shift
• Ubiquitous Computing
• Future Computing Roadmap

4
Paradigm Shift

• Computing

Mainframe computer
Personal Computer
Networked Computers
1980s
1960s
1990s
Ubiquitous Computing
2000s
Sharing a computer
Individual usage
Sharing over Internet
information everywhere
Small, Intelligent, 3D
46 ENIAC 71 4004 72 8008 73 8080/85 78
8086/88 82 80286 85 80386 89 80486
93 Pentium 95 P-pro 97 P-II 99 P-III 00
P-IV 08 P-QuadCore
5
The Vision
In the 21st century the technology revolution
will move into the everyday, the small and the
invisible Mark Weiser, 1988
The most profound technologies are those that
disappear. They weave themselves into the fabric
of everyday life until they are indistinguishable
from itMark Weiser, 1991
Mark Weiser (1952 1999), XEROX PARC
6
II. Context-aware

• Definition
• Examples of context
• Context Information

7
Context
The specific conditions, external to the
application itself, such as audience, speaker
(user), situation (place and its surroundings),
time, environmental and network conditions, etc.,
which determine the application behavior, will be
called the context of the application.
Sensed Context Predefined Context Inferred/Dedu
ced Context
8
Context Defines

• Everybody has a different notion.
• Context in the literature
• location, identities of nearby people and
  objects.
• time of day, season, temperature.
• users emotional state, focus of attention
• environment the user and computer know about
• state of the computer surroundings

9
Context-aware?

• Pascoe(1997) taxonomy of context-aware features
• contextual sensing
• context adaptation
• contextual resource discovery
• contextual augmentation (associating digital data
  with users context)
• Abowd Dey(2000) context-aware features
• presentation of information/services to a user
  according to current context
• automatic execution of a service when in a
  certain context
• tagging context to information for later
  retrieval
• Kotz
• Active context awareness - An application
  automatically adapts to discovered context, by
  changing the applications behavior
• Passive context awareness - An application
  presents the new or updated context to an
  interested user or makes the context persistent
  for the user to retrieve later.

10
Shortcomings of the former systems

• Context acquisition and use was often tightly
  integrated into a single application, and could
  not easily be incorporated into other
  applications.
• Individual agents are responsible for managing
  their own context knowledge
• Thus application developers often find it very
  difficult to build their applications
• Lacking an adequate representation for context
  modeling and reasoning
• Existing solutions for Context information are
• Name-value pairs (in the Context Toolkit) or
  entity relation model
• Objects to represent context with methods and
  fields for retrieval of information
• Simple matching mechanisms for context access,
  and developers must perform low-level programming
  for reasoning
• Users often have no control over the information
  that is acquired by the sensors
• Privacy Concerns

11
And the Role of Middleware

• Designating those steps to Middleware will
• Free the application developer from underlying
  tasks sensing technologies, gathering sensed
  context data, modeling context data, reasoning
  and delivering/disseminating the inferred
  contexts to applications
• Let him focus on implementing application logic
• Reusability built once used by everyone
• Separation of concerns Context-aware Middleware
  decouples application layer with lower layers gt
  more efficient to develop

12
Context-aware Middleware

• Desired Characteristics
• Support for heterogeneous and distributed sensing
  agents
• Make it easy to incrementally deploy new sensors
  and context-aware services in the env.
• Provide different kinds of context classification
  mechanisms -gt Flexibility
• Different mechanisms have different power,
  expressiveness properties
• Rules written in different types of logic (first
  order logic, description logic, temporal/spatial
  logic, fuzzy logic, etc.)
• Machine-learning mechanisms (supervised/unsupervis
  ed classifiers)
• Follow a formal context model using ontology
• To enable syntactic and semantic
  interoperability, and knowledge sharing between
  different domains
• Facilitate for applications to specify different
  behaviors in different contexts easily, as
  well as privacy policy and security mechanism
• Graphical development tool to ease developers in
  writing code.
• Dealing with uncertainty to enhance the quality
  of context

13
III. Context Aware Computing

• Context Aware Computing
• Context Define
• Context Modeling
• Application Service
• Related Work

14
Context Aware Computing

• Context-aware
• To recognize users state and surroundings, and
  modify its behavior based on this information
• Is
• Breaking computers out of the box
• Making computers more aware of the physical and
  social situations they are embedded in
• One line of ubiquitous computing research
• A Context-aware Systems should make my life
  easier but if it makes mistakes Im angry with it
  and the second time it does something wrong I
  turn it off (forgetting the many times it was
  working correctly)
• They want cellular phones but we dont want the
  antennas

15
Context Information - Location

• The Active Badge (92)
• User based indoor location sensing
• Identity using an IR data link
• Active maps scalability
• _at_ Olivetti Research Lab (Cambridge, UK)
• ParcTabs (Schilit 95)
• Active badgewireless Rough location ID
• Active Bat (Ward 97)
• Active Badge only identify 2D location
• Ultrasonic fine-grained 3D location system

16
Context Information - Location

• Cricket (MIT Oxygen)
• An indoor location system for pervasive computing
  env.
• RADAR (Microsoft)
• A set of static receivers track positions of
  transmitters
• Barcode
• 1D vs. 2D BW vs. color
• Load cell (GATECH) vs. ON/OFF cell

GATECH
GIST
17
Context Information User Identify

• Who
• Biometric sensors
• Face recognition)
• Speech identification/recognition

18
Context Information - Behavior

• What Users behavior
• Body tracking
• Gesture recognition
• Activity recognition
• Object recognition

Body tracking
Environment
Face
Guesture
19
Context Information - Intention

• How Why Users emotion
• Sensing affect signals
• Recognizing patterns of affective expression
• lightness, Angry, Fear,,,

20
IV. Context Aware Services
21
Context aware Intelligent Service
Context-aware Agent
Smart Home
22
Context aware Intelligent Service
Context-aware Agent
Smart Home
23
Q and A

• Discussion and More Information
• Open to Collaborative Research with ETRI
• to jdhuh_at_etri.re.kr