Transcript ppt

Application of Knowledge
Based Systems in Education
Dr Priti Srinivas Sajja
Department of Computer Science
Sardar Patel University
Vallabh Vidyanagar, Gujarat
Introduction and Contact Information
• Speaker: Dr Priti
• Communication:
Srinivas Sajja
• Email : [email protected]
• Mobile : 9824926020
• URL : priti.sajja.info
• Academic qualifications : Ph. D in Computer Science
• Thesis title: Knowledge-Based Systems for Socio-Economic
Rural Development
• Subject area of specialization : Knowledge Based Systems
•
Publications : 84 in International
•
Academic position : Associate Professor
Department of Computer Science
Sardar Patel University
Vallabh Vidyanagar 388120
6-7 February, 2009
and National Books, Chapters and Papers
Dr. Priti Srinivas Sajja
Lecture Plan
Knowledge Based Systems
• Introduction to Knowledge Based Systems
• Categories and Structures of KBS
• Applications of KBS
KBS in Education
• Symbolic Approach
• Parichay: Adult Literacy System for Leaning Gujarati Language
• Multi Agent KBS fro e-Learning Accessing Distributed Databases on Grid
• Multi-tier KBS Accessing LOR through Fuzzy XML
• Connectionist Approach
•
•
•
•
Symbolic verses Connectionist Approach
Soft Computing
Neuro-fuzzy System for Course Selection
Fuzzy-genetic System for Evolving Rule Bases to Measure Multiple
Intelligence
• Acknowledgement, References and Contact
6-7 February, 2009
Dr. Priti Srinivas Sajja
Artificial Intelligence
• “Artificial Intelligence(AI) is the study
of how to make computers do things at
which, at the moment, people are
better”
• -Elaine Rich, Artificial Intelligence, Mcgraw Hill
Publications, 1986
6-7 February, 2009
Dr. Priti Srinivas Sajja
Knowledge Based Systems
K
Knowledge Based Systems (KBS) are
Productive Artificial Intelligence Tools
working in a narrow domain.
6-7 February, 2009
Dr. Priti Srinivas Sajja
How Knowledge is organized?
Volume
Complexity &
Sophistication
Wisdom(experience)
Knowledge(synthesis)
Information(analysis)
Data
Data Pyramid
Source: Tuthill & Leavy, modified
6-7 February, 2009
Dr. Priti Srinivas Sajja
Data
• Raw Observation
• Stand alone numbers and symbols that do possess little value
• Data are symbols that represent properties of objects, events and
their environments.
• ANYTHING numbers, words, sentences, records, assumptions
• Example BMI, 10, (smith, 50)
6-7 February, 2009
Dr. Priti Srinivas Sajja
Information
• Processed Data
• Smith weight is 50 Kg.
• Information has usually got some meaning and
purpose
6-7 February, 2009
Dr. Priti Srinivas Sajja
Knowledge
• Information can be processed further with
the operations such as
• Synthesis
• Filtering
• Comparing etc.
to get generalized knowledge
6-7 February, 2009
Dr. Priti Srinivas Sajja
Wisdom
• Knowledge of concepts and models lead to higher
level of knowledge called wisdom.
• One needs to apply morals, principles and
expertise to gain and utilize wisdom.
• This takes time and requires a kind of maturity
that comes with the age and experience.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Data Pyramid and Computer Based Systems
IS
Strategy makers apply morals, principles and
experience for generating policies
WBS
Higher management generates knowledge
By Synthesizing information
KBS
Middle management uses reports/info.
generated through analysis and acts
accordingly
Basic transactions by operational staff
using data processing
Volume
6-7 February, 2009
DSS, MIS
TPS
Wisdom (Experience)
Knowledge (Synthesis)
Information (Analysis)
Data (Raw Observations
Processing)
Sophistication and
complexity
Dr. Priti Srinivas Sajja
Computer Based Systems Tree
Intelligent Systems: 21st
Century Challenge
S/W Resources
IS
EES*
ES
Users
Requirement
1990
ESS
EIS
DSS
EES:
Executive Expert System,
which is hybridization of Expert
System , Executive Information
System and Decision Support
System.
OAS
MIS
TPS
1970
1950
Hardware Base/Technology
Figure 1.8: CBIS Tree (Sajja & Patel 1995)
6-7 February, 2009
Dr. Priti Srinivas Sajja
Structure of KBS
Knowledge base is a repository of
domain knowledge and meta
knowledge.
Inference Engine is a software
program, which infers the
knowledge available in the
knowledge base
Explanation
/ Reasoning
Provides
explanation and
reasoning
facilitates
6-7 February, 2009
Knowledge Base
Inference Engine
User Interface
Enriches the
system with
self learning
capabilities
Self
Learning
Friendly
interface to
users working
in their native
language
Dr. Priti Srinivas Sajja
Categories of the KBS
According to Tuthill & Levy (1991), KBS can be mainly classified into 5
types:
Expert Systems
The Expert Systems (ES) are the most popular and historically pioneer
knowledge based systems, which replace one/more experts for problem
solving.
Linked Systems
The Hypermedia systems like hyper-text, hyper-audio, hyper-video are
considered as linked knowledge based systems.
CASE Based Systems
These systems guide in information/intelligent systems’ development for
better quality and effectiveness.
Database in conjunction with an Intelligent User Interface
An intelligent user interface can enhance the use of the content available in
the traditional format.
Intelligent Tutoring Systems
The knowledge based systems are also used to train and guide the different
level of students, trainers and practitioners in specific area. These systems are
also useful to evaluate students’ skills, prepare documentation of subject
material and manage the question bank for the subject.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Major Advantages of KBS
• Increased effectiveness with efficiency
• Documentation of knowledge for future use
• Add powers of self learning
• Provides justifications for the decisions made
• Deals with partial and uncertain information
• Friendly interface
6-7 February, 2009
Dr. Priti Srinivas Sajja
Difficulties with the KBS
•
•
•
•
Nature of knowledge
Large Size of knowledge base
Slow Learning and Execution
Little methodological support from typical life cycle
models
• Acquisition of knowledge
• Representation of knowledge
6-7 February, 2009
Dr. Priti Srinivas Sajja
KBS Applications
Economical
Small Scale Industry
Agri-Business & Cooperative
etc.
Physical
Communication
Physical
Planning &
Administration Development
Forestry, Energy,
Agriculture etc.
Health
Nutrition, Sanitation
Community Health etc.
6-7 February, 2009
Economical
Development
Social
Education & Training
Social Awareness
Programme etc.
NR
Social
Development
LA
Health
Development
HR
NR: Natural Resources
HR: Human Resources
LA: Live stock and
Agricultural Resources
Dr. Priti Srinivas Sajja
Technology and Education
Technology helps in learning
Technology
Education
Education helps in development of
technology
6-7 February, 2009
Dr. Priti Srinivas Sajja
Objectives of Educational Solution
Different Model like Class room education, Distance learning
and Virtual learning / E-Learning etc. have some common
objectives as follows:
• Support learning objectives and goals
• Facility to publish, update and access learning material and
announcements
• Friendly interface for non-computer professionals and
students for communication
• Evaluation of learners and feedback mechanism
• Administrative and documentation support
• Meets standards and security aspects
6-7 February, 2009
Dr. Priti Srinivas Sajja

Web Designers,
Technical Experts




Accessibility
(Internet)
User friendliness
Security
Communication
Inference and self
learning etc.
Technology


Domain
knowledge
Supporting
databases and
documents etc.
Subject Experts
6-7 February, 2009
Content
Service
Media
developers,
Editors,
Instructors





Information Retrieval
Assistance
Learning System
Management
Evaluation
Documentation etc.
Dr. Priti Srinivas Sajja
Symbolic KBS: Some Examples
Parichay: Adult Literacy System for Leaning
Gujarati Language
This is a Single PC based system where knowledge
based contains set of rules in if…then…else form.
This system has been developed as an agent to help
adults to learn regional language, Gujarati.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Some results from ‘Parichay’
The system gives training to adult
users in multi media to speak and
write Gujarati alphabets, words,
sentences and numbers.
The package of ‘parichay’ is
accommodated in CD with autorun facility.
The touch screen facility helps
even an illiterate person to
identify icons and choose
appropriate actions.
6-7 February, 2009
Dr. Priti Srinivas Sajja
The frequent continuous
development of a letter
helps users to see the
exact motion to write the
letter.
At the end of the full letter
generation, the picture
representing use of the
letter and pronunciation is
represented to the user.
6-7 February, 2009
Dr. Priti Srinivas Sajja
With a notepad facility given,
user may practice any
letter.
That letter written by the user
is matched with the
correct letter by measuring
shapes and angles in terms
of percentages.
If the degree of matching is
low then user may ask to
redraw/rewrite the letter.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Limitations of the System
• ‘Parichay’ is limited to single user system
only.
• It can be used only for elementary Gujarati
learning (reading and writing) such as
simple alphabets, numbers and sentences.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Multi Agent KBS for e-Learning Accessing
Distributed Databases on Grid
• e-Learning is supported by a knowledge based
systems to improve quality.
• e-Learning emphasis on on-line delivery,
management and learning of educational material.
• The following aspects are given importance for
such learning:
•
•
•
•
Easy access of material in user friendly way
Anytime and anywhere learning
Better control and administration of material and users
Quick results and reporting
6-7 February, 2009
Dr. Priti Srinivas Sajja
• System considers different databases which may
be available in distributed fashion.
• At many places the learning material and supporting
information like students, courses and infrastructure are
available in electronic form.
• The idea is to access the available data sources in
knowledge based way.
• e-Learning is a big job encompasses different activities
hence multiple independent agents have been
considered.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Architecture of the system
Knowledge Utilization
Knowledge Management
Knowledge Discovery
Agents
Learning Mgt.
Resources
Drills and Quizzes
Knowledge Mgt.
Conceptual system
Distributed
Databases
Tutorial Path
Content knowledge
Explanation
Learner’s ontology
Documentation
Local DataBases
Semantic Search
Mail
Documents
User Interface Agent
Question/Answer
Meta knowledge
Users
Experts
E-mail & Chat
Resource Management
6-7 February, 2009
Dr. Priti Srinivas Sajja
Communication between Agents
• Agents developed here are communicating with a tool
named KQML.
• Knowledge based Query Management Language.
(register
Action intended for the message
: sender agent_Lerning_Mgt
Agents name sharing message
: receiver agent_Tutorail-Path
: reply-with message
: language
common_language
: ontology
common_ontology
: content
)
6-7 February, 2009
“content.data”
Action intended for the message
Language of both agents
Ontology of both the agents
Context-specific information describing the
specifics of this message
Dr. Priti Srinivas Sajja
Some results form the System
6-7 February, 2009
Dr. Priti Srinivas Sajja
Some results from the System
6-7 February, 2009
Dr. Priti Srinivas Sajja
Some results from the System
6-7 February, 2009
Dr. Priti Srinivas Sajja
Some results from the System
6-7 February, 2009
Dr. Priti Srinivas Sajja
New architecture on Grid Environment
Future extension
Knowledge Utilization
Knowledge Management
Knowledge Discovery
Agents
Learning Mgt.
Resources
Drills and Quizzes
Knowledge Mgt.
and
Grid FTP ReplicaLocation
Services
Question/Answer
Meta knowledge
Conceptual system
Tutorial Path
Content knowledge
Explanation
Learner’s ontology
Information
Discovery
Services
Documentation
Local DataBases
Semantic Search
Mail
Security Services
Documents
User Interface Agent
Internet
Grid Middleware Services
Resource
Management
(Grid Resource
Allocation
Protocol-GRAM)
Users
Experts
E-mail & Chat
Resource Management
Distributed
databases
6-7 February, 2009
Middleware
Services and
Protocols
Dr. Priti Srinivas Sajja
Towards reusable component library logic
• Learning Object Repository (LOR)
6-7 February, 2009
Dr. Priti Srinivas Sajja
Multi-tier KBS Accessing LOR through Fuzzy XML
6-7 February, 2009
Dr. Priti Srinivas Sajja
Combining Neural and Fuzzy
Neural Nets
Knowledge
Representation
Trainability
Fuzzy Logic
Implicit, the system cannot
be easily interpreted or
modified (-)
Explicit, verification and
optimization easy and
efficient (+++)
Trains itself by learning from
data sets (+++)
None, you have to define
everything explicitly (-)
Get “best of both worlds”:
Explicit Knowledge Representation from
Fuzzy Logic with Training Algorithms
from Neural Nets
6-7 February, 2009
Dr. Priti Srinivas Sajja
Neuro-fuzzy System for Course Selection
• Critical decision + limited time period
• Parents and students are not exposed to the
opportunities though educated
• All alternatives are not available at one place
• Continuously changing data
• Changing job opportunities
• Too many choices Vs. shortfall in specific stream 
industry gap  imbalance in trained personnel
6-7 February, 2009
Dr. Priti Srinivas Sajja
Current scenario
• Available systems:
‘Course
Selector’,
University of
Edinburg, UK
• Local with limited scope,
• biased and
• manual systems are available
‘Course Advisor
Expert System’ is
developed at the
Griffith University
• Static information system
• Work on Database and explicit documentation required
• Lacks knowledge orientation
• No justification of the decisions
• No self learning about new opportunities and courses
6-7 February, 2009
Dr. Priti Srinivas Sajja
Requirements
• Timely decision
• Uniform Information availability at one place
• Management of large amount of data
• Effective and knowledge oriented personalized
decision support
• Justification (explanation and reasoning)
• Adaptive to new courses
• Friendly user interface working in natural fashion
6-7 February, 2009
Dr. Priti Srinivas Sajja
Users
•
•
•
•
•
Students
Parents
Institutes and Universities
Professional consultants, if allowed
Researchers and policy makers
6-7 February, 2009
Dr. Priti Srinivas Sajja
Critical Parameter categories
• Institute and course information:
• Institute name, registration number, preliminary
information, courses, seats, reservation, placement,
history etc.
• Users academic qualification/marks:
• Name, location, degree/exam, marks, year, board etc.
• Users personal preferences:
• Institute & course preference, hostel accommodation,
foreign chances etc.
• Family background:
• Parents business, economical conditions etc.
6-7 February, 2009
Dr. Priti Srinivas Sajja
Methodology
Fuzzy Interface
Implicit
learning
& self
learning
by ANN
Friendly
interface and
Explicit
justification,
documentatio
n
Users
choice
and
needs
Fuzzy interface
Linguistic
fuzzy
interface
Fuzzy
rule base and
membership
functions
Underlaying ANN
Crisp
Normalized
values
P
1
P
2
P
3
P
4
Decision
support
Workspace
Decision support
Structure of the Neuro-fuzzy System
6-7 February, 2009
Dr. Priti Srinivas Sajja
User
Available in
Knowledge Base
Institute list with
Courses, seats,
accredition, faculty,
resources, history,
placement, cut-off marks
etc.
PI & PF
Collected from User(s)
through Input Screens
Students Information Collection:
Name, Location, Score, Subject wise marks, Board Name,
State information, etc.
Family Background Information:
Economical conditions, parents profession etc.
Aptitude and Preference Seeking Questions:
Choice of institute, course, homesickness, etc.
Conversion into crisp normalized values by Fuzzy Interface
ANN
Normalized Student Info
*
+
Reference Ids *
generated from Institute
+Courses + Scheme etc.
Input Layer
Hidden Layers
Fully Connected
Feed Forward
Multi-Layer
Back-Propagation
ANN
Output Layer
Fuzzy Interface
6-7 February, 2009
Can be changed
according to
users demand
Array of alternatives in Sorted order with default three best suitable alternatives
Dr. Priti Srinivas Sajja
Users
An Example Prototype
Elective Course Selection system:
• Objective: To test feasibility of the proposed project
• Place: Department of Computer Science, S P University
• Tools: .Net 2005 + ANN simulator (JavaNNS)
• Training set: 100 records
• Users :Final Year MCA Students at the S P University
(220 app.)
6-7 February, 2009
Dr. Priti Srinivas Sajja
Interface Screen to collect training data
6-7 February, 2009
Dr. Priti Srinivas Sajja
Fuzzification of the parameters resulting in normalized values…
Linguistic Distance :[very far way, far away, away, near, very near etc.]
Distance :[ 50, 100, 150 km]
Membership
degree
Very Near
Near
1.0
Away
0.5
Far Away
0
0.1
0.4
0.6
0.8
1.0
thousand KM
Too Far
Linguistic variable ‘Distance’
6-7 February, 2009
Dr. Priti Srinivas Sajja
Network Structure
Availability of expertise
BioInformatics
Availability of hardware/based
technology
Content /length of the course
Degree of assistance required
suggeste
d
decision
for
Current
Trends
[[[
Knowledge level required for the
course/ depth of the course
Market trend towards
technology/course
Personal interest
Hidden
Layers
Success history if any (last few
years result in%)
Output
Layer
Wireless
Tech.
Time taken to complete
(revision)
Input
Layer
6-7 February, 2009
Dr. Priti Srinivas Sajja
Advantages
• Quick and effective decision support
• Ease of cloning and documentation
• Knowledge Based
• Dual advantages through explicit and implicit
representation
• Self learning
• Manages vague parameters in fuzzy way
• Explanation and reasoning
• Management of large amount of data & dynamic
• Object oriented
• Platform independent
• Easy to use with fuzzy interface
6-7 February, 2009
Dr. Priti Srinivas Sajja
Fuzzy-genetic System for Evolving Rule Bases to
Measure Multiple Intelligence
• Fuzzy genetic hybridization
• The paper will be presented by Ms. Kunjal Mankad, ISTAR
6-7 February, 2009
Dr. Priti Srinivas Sajja
6-7 February, 2009
Dr. Priti Srinivas Sajja