Transcript No Slide Title

Client-server based adaptive and
intelligent tutoring
Dr Kinshuk
Information Systems Department
Massey University, Private Bag 11-222
Palmerston North, New Zealand
Tel: +64 6 350 5799 Ext 2090
Fax: +64 6 350 5725
Email: [email protected]
URL: http://fims-www.massey.ac.nz/~kinshuk/
Online content and delivery
• Increasing demand on educational material
delivery
to
dispersed
geographical
locations by extramural students
• Content with different granularity is
required to cater the students with
different level of domain competence
(remedial material, main line material, and
advanced material)
• Low bandwidth requirements!
Collaboration & design goals
• to deliver multimedia courseware via the
WWW
• to provide simple-to-use tools capable of
producing multimedia presentations with
little or no experience
• to significantly reduce the preparation time
for every hour of multimedia presentation
Collaboration & design goals
• to ensure a compact media archive to
provide a large corpus of multimedia
tuition on a modestly sized server
• to ensure access over
connection speeds
modest modem
• to provide cross platform delivery of the
multi-media content using a simple
browser plug-in technology
AudioGraph player demo
AudioGraph authoring demo
Technology Integrated Learning
Environments (TILE)
to develop a complete client-server
architecture for all aspects of on-line
education authoring and delivery including:
• management of students and syllabus
• media authoring
• media indexing and natural-language
querying
• authoring
problem
solving
and
simulation environments
• student modelling and a assessment
Technical details
• TILE is based on client server model.
• Server is built around a relational database
for flexibility and for standardised
interface.
• Development is done incrementally on a
module-by-module basis.
• Mostly public-domain tools are used.
Server system
• Server will provide a base where all other
tools will be integrated.
• Meta-schemas will be used so that any
change can be adapted by all tools without
actually changing the code.
• A management interface for authoring tool
is already developed based on mySQL and
JDBC.
Multimedia editing clients
• We aim to
multimedia
develop
low-bandwidth
• Voice activated recording for optimised
multimedia
storage
and
delivery
(compressed small packets of speech with
time pauses rather than continuous media)
• indexing and linking strategies for
multimedia annotation and query facility
Knowledge representation and
free-form querying
• to facilitate improved guidance and greater
interactivity
• based on Flexible Structured Coding
Language (FSCL), a restricted grammar
natural language and accompanying query
language FSQL.
• also working
interface
on
speech
recognition
What exactly we mean by
Adaptivity
in
Adaptive Educational Systems?
“Intelligence”/adaptivity
Increased user efficiency, effectiveness
and satisfaction
by
Improved correspondence between
learner, goal and system characteristics
Need of Intelligence/adaptivity
 Users generally work on their own
without external support.
 System is used by variety of users from
all over the world.
 Customised system behaviour reduces
meta-learning overhead for the user
and allows focus on completion of
actual task.
Adaptable Systems
Systems that allow the user to
change certain system
parameters and adapt the
system behaviour accordingly.
Adaptive Systems
Systems that adapt to the users
automatically based on system’s
assumptions about user needs.
How does adaptivity work?
 System monitors user’s action patterns
with various components of system’s
interface.
 Some systems support the user in the
learning phase by introducing them to
system operation.
 Some systems draw user’s attention to
unfamiliar tools.
 User errors are primary candidate for
automatic adaptation.
Levels of adaptation
 Simple: “hard-wired”
 Self-regulating: monitors the effects of
adaptation and changes behaviour
accordingly
 Self-mediating: Monitors the effects of
adaptation on model before putting into
practice
 Self-modifying: Capable of chaging
representations by reasoning about the
interactions
Problems in adaptation
 User is observed by the system, actions
are recorded, giving rise to data and
privacy protection issues.
 Social monitoring becomes possibility.
 User feels being controlled by the system.
 User is exposed to adaptation concept
favoured by the designer of the system.
 User may be distracted from the task by
sudden automatic modifications.
Recommendation for adaptive systems
 Means for user to (de)activate or limit
adaptation procedure
 Offering adaptation in the form of
proposal
 User may define specific parameters used
in adaptation
 Giving user information about effects of
adaptation hence preventing surprises
 Editable user model
Adaptation in web-based
modules
• Facilitation of dynamic interaction
• adaptation with respect to current domain
comepetence level of the learner
• suitability with respect to domain content
• adaptation with respect to the context in
which the information is being presented
Adaptation - targets
• Developing suitable way
interactions over the Internet
to
capture
• Provide continuous interaction pattern for a
given student
• Construct server and client side student
models
• Facilitate off-line adaptation
• Intermittent update of server-side student
model for further domain material adaptation
Use of student model in adaptation
• to provide adaptive navigation guidance
• to select coarser/finer granularity of domain
content
• to provide context based excursions to other
learning units
• in making analogies with previously learnt
material
• in making direct references to previously
learnt material
• to provide dynamic messaging and feedback
Student model
• Client server based
• Individual and group student model
• Agent based communication
Two major components:
• Domain competence at various granularity
• Student preferences
Individual Student model
• Global preferences of the learner (behavioral
component)
• Specific content presentation related
preferences of the learner (behavioral
component)
• Domain competence related information
about
the
learner
(domain
based
component)
• Student’s working history with annotated
system feedback
Individual Student model
Contains four levels of student competence:
1. No competence (initial stage)
2. Ready for problem solving, which assures that
the student has fulfilled the learning criteria for
a unit and requires assessment.
3. Partially learnt, which means the student has
successfully completed assessment for unit but
still has not achieved full competence, which
requires repetitive training.
4. Full competence, which means that the student
has really grasped particular domain content.
Group Student model
• Contains summary of the students’ common
behaviour and preferences.
• Students are categorizes into different groups by
matching their behaviour and domain
competence.
• The structure of the groups is multi-dimensional;
one student can belong to one or more such
groups (say in a serialistic learning style group
and in an active learning group).
• It also offers more reasonable default setup and
help for newcomer individual students.
Group Student model
The group student model contains attributes such
as (based on the data collected over a certain
number of students):
• Common mistakes/errors made by
number of students in problem solving
certain
• Certain common behavior of a number of
students
• Common preferences of a number of students
during study and interaction with the system
Student model
Group
student
model
Partial
individual
student model
Partial
individual
student model
Inference
engine
Inference
engine
Client
Host
In ternet
Agent picks up data from client side and moves
to other side to perform all the processes, then
returns back with information needed.
Student model
Client could either be student’s home
machine, university server, or any other
machine,
as
configured
by
the
organisation in question.
Mobile agents in web-based
learning environment
Pre-fetching the content
• Domain content, that might be requested
shortly by the student, can be pre-fetched
from the server on the basis of real-time
analysis of the student’s behavior, and
calculation of the probability of a request.
• Depending on the state of the network, an
immediate request or a reservation can be
fulfilled by the mobile agent.
Mobile agents in web-based
learning environment
Pre-fetching the content
Intelligent Interface Agent
Pre-fetch content
based on student’s
behaviour
Agent
Client
Server
Mobile agents in web-based
learning environment
Good support for mobile users
• More and more mobile users will access
web-based learning environments under
just-in-time learning situations, using
portable-computing devices such as
laptops, palmtops, and electronic books.
• Mobile agents are ideal to support these
devices
compared to unreliable, lowbandwidth, high-latency telephone or
wireless network connections.
Mobile agents in web-based
learning environment
New programming paradigm: scalability of
system and easy authoring
• Mobile agents offer a new programming
paradigm with higher-level abstraction and
unified “process” and “object”.
• This in turn provides a flexible and
effective
philosophy
on
learning
environment development, design, and
scalability.
Mobile agents in web-based
learning environment
Facilitate sharing of distributed resources
• Web-based learning environments can
share resources through different systems,
even in heterogeneous computers and
network environments.
Intelligent Interface Agent
Agent
Client
Server
Server
Mobile agents in web-based
learning environment
Web-based learning ideal test bed
• Mobile agent is a new technology.
• Electronic commerce has been first client.
• Educational environments are lesser
security risk-prone than e-commerce, hence
ideal for mobile agents test-bed.
Mobile agents in web-based
learning environment
Web-based learning ideal test beds
• Types of security:
• agent-agent security (negotiations)
• host-agent security (search/retrieval)
• agent-host security (most problematic,
but easily manageable in educational
sector)
Summary
• Future of education will largely
influenced by web-based education
be
• We aim to provide an integrated system for
the management, delivery and monitoring
of such material