Sei sulla pagina 1di 40

Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

ONTOLOGICAL FRAMEWORK FOR MEDICAL


INFORMATION RETRIEVAL AND
INFERENCING MECHANISM

Absheer K.K
Ashwin Thomas
Shafeeque M.K.M
Siju Pavithran
Varghese K Renny
Project Guide : Dr.K.Najeeb

Government Engineering College


Sreekrishnapuram Palakkad

September 6, 2010
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

CONTENTS

1 Introduction

2 Motivation & Objectives

3 Tools Used

4 Architecture

5 Conclusion

6 Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

INTRODUCTION

The basic motivation behind the project is to design a


knowledge based expert system for rural areas.
In the villages, where people may be lacking basic medical
amenities, this system can be used effectively.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

INTRODUCTION Contd.

The ontological framework can be used to efficiently give a


basic diagnosis about the disease
The system is capable of deducing possible diseases from the
symptoms
Also, an idea can be obtained about the treatment related
issues such as medicines and concerned doctors
expert systems for doctors and practitioners.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

BASIC TERMINOLOGY

Ontology
explicit specification of a conceptualization

example given by Genesereth and Nilsson(a, b, c, d, e, on,


above, clear, table)
In Computer Science and Information Science,ontology defines
set of representational premitives with which to model a
domain of knowledge or discourse.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Ontology Contd.

independent of data modelling strategy or implementation.


It is a rigorous and exhaustive organisation of some knowledge
domain that is usually hierarchical and contains all the
relevant entities and their relations
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

OWL
The Web Ontology Language(OWL) is a family of knowledge
representation languages for authoring ontologies, and is
endorsed by the World Wide Web Consortium.
The OWL is intended to provide a language that can be used
to describe the classes and relationship between entities that
are inherent in Web documents and applications.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

OWL contd.

An OWL Ontology contains:


Classes +Class Hierarchy
Relations between the classes(inheritance , disjoints etc)
Restrictions on the properties(types, cardinality etc)
Individuals
types of OWL.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

MOTIVATION FOR THE PROJECT

Ontologies are more general and reusable than traditional data


models
They are easily shareable
They are intended for multiple purposes, goals and users
Take stand on the semantics of the concepts (as opposed to
mere structure and integrity)
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

OBJECTIVES OF THE PROJECT

Design and develop an ontology for a Medical domain.


Propose a system architecture for retrieving information and
enrichment of the ontology.
Retrieve the results in a way that can be used for further
processes
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

LITERATURE REVIEW

Recognizing and filtering web documents using an Ontology


Authors:Abadi, R.M.B, Yektaie, M.H., Abbasi, M.
Azad University Of Oloum va Tahghighat, Ahwaz, Iran
This paper puts to evaluation the extent of relationship
between a semi structured HTML and ontology using some
statistical techniques.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Automatic ontology-based knowledge extraction from Web


documents
Authors:Alani, H., Sanghee Kim, Millard D.E., Hall W, Lewis,
P.H., Shadbolt N.R
Southampton University UK
Specialized knowledge services require tools that can search
and extract specific knowledge directly from unstructured text
on the Web.This paper links a knowledge extraction tool with
an ontology to achieve continuous knowledge support and
guide information extraction
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Active User-Based and Ontology-Based Web Log Data


Preprocessing for Web Usage Mining
Authors:Natheer Khansawneh, Jordan University of Science
and Technology, Jordan
Chien-Chung Chan, University of Akron, US
User and session identification are two major steps in web log
data for web usage mining. This paper introduces a fast active
user-based user identification algorithm with time complexity
O(n)
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Building Semantic Rich Model for Web Documents Using


Domain Ontology
Authors: ShahrulAzmanNoah, LailatulqadriZakaria,
ArifahCheAlhadi,SaidahSaad,
National University of Malaysia
The paper proposes an approach meant to assist in
constructing semantic document models using natural
language analysis technique and a domain specific
ontology,which simplifies the working of search engines and
other such applications
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

TOOLS USED

Protege
Jena API
Pellet API
SPARQL
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Protege

Protege is a free , open source platform that provides a


growing user community with a suite of tools to construct
domain models and knowledge based applications with
ontologies
Protege has an open architecture that allows programmers to
integrate plugins
The plugins can appear as separate tabs, specific user
interface components(widgets), or perform any other specified
operation on the user model
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Protege Contd.

The Protege platform supports two main ways of modelling


ontologies:
The Protege-Frames editor enables users to build and populate
ontologies that are frame-based, in accordance with the Open
Knowledge Base Connectivity protocol (OKBC). In this model,
an ontology consists of a set of classes organized in a
subsumption hierarchy to represent a domain’s salient
concepts.
The Protege-OWL editor enables users to build ontologies for
the Semantic Web, in particular in the W3C’s Web Ontology
Language.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Protege Features

Extension to handle OWL ontologies


Loading and saving OWL files and databases
Graphical editors for class expressions
Integrated reasoner to ensure consistency
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

JENA

It is an open source semantic web framework written in Java


Jena is composed of:
RDF processing API
OWL processing API
A rule- based inference engine
SPARQL query engine
In-memory and persistent storage.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

JENA Contd.

Can parse,create and search RDF models


ModelFactory for creating models. So that application code
remains independent of the implementation, it is best if it
uses interfaces wherever possible, not specific class
implementations.
JENA has a special model class called OntModel
This can be used to derive meaningful relationship that the
model does not express directly
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Pellet API

Pellet is an open source Java based OWL DL reasoner


It can be used in conjunction with both Jena and OWL API
libraries and also provides a DIG interface
provides functionalities to see the species validation, check
consistency of ontologies, classify the taxonomy
Special features
Ontology analysis and repair
Data type reasoning
Rule integration
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

SPARQL

Simple Protocol And RDF Query Language


SPARQL query consist of triple
patterns,disjunctions,conjunctions and optional patterns
SPARQL queries are created and executed with Jena via
classes in the com.hp.hpl.jena.query package
SPARQL is data oriented in that it only queries information
held in the models,there is no inference in the query language
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

PLATFORM USED

Linux
Java runtime environment
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

ARCHITECTURE
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

The architecture consists of 4 main modules. They


are:-
Hierarchy viewing module
Consistency checking module
Query processing module
Enrichment module
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

HIERARCHY VIEWING MODULE

This module shows the user the hierarchical structure of the


ontology
Different axioms like the classes, objects and data properties
are also displayed
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

CONSISTENCY CHECKING MODULE

This module makes use of a reasoner like pellet,racer etc to


check the consistency status of the domain ontology
Consistency checking module has to be activated while the
user enriches the ontology, to ensure validity of the ontology
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

Query processing module

Query processing can be handled in two ways


User can enter the SPARQL query directly
SPARQL query generation
Information retrieval can also be done by node searching
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

ENRICHMENT MODULE

This module allows user to add new information to the


domain ontology
We have provided two options to enrich the ontology:
User may delete an existing class
User may add a valid class
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

CONCLUSION

The project puts emphasis on some valuable points in the field


of patient oriented medical information system
Since the application is aimed at the general public, the
interface has a simple and easy-to-understand design
It is also possible to add newer ontologies to the
application(from websites such as swoogle.com) directly to
our application
System runs through java run time environment that is
platform independent.
System implements disambiguation feature.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

FUTURE ENHANCEMENTS

Developing a Semantic search engine utilizing several


heterogeneous open source technologies
Designing an Auto enriching Ontology, which is capable of
making transitive deductions, based on user input
Designing an online ontology knowledge based system,
capable of sharing and enriching information by using suitable
networking among them.
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

FUTURE ENHANCEMENTS Contd.

User can enter queries in XML format and also add


information as XML file.
It is possible to generate XML file so that it can be used as
input for further processing.
Caching of query is yet another feature that can be
implemented
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

BIBLIOGRAPHY

Natalya F. Noy, Deborah L McGuinness, Ontology


Development 101: A Guide to Creating your own Ontology
Matthew Horridge, Holger Knublauch, Alan Rector, Robert
Stevens and Chris Roe: A Practical guide to building OWL
Ontologies Using the Protg OWL Plugin
Herbert Schildt : Java 2- The Complete Reference, Tata
McGraw Hill
Amandeep Sidhu, Tharam S. Dillon, Elizabeth Chang,
Baldeep Sidhu:Medical Ontology Development using OWL,
OWLED, Volume 188 of CEUR Workshop proceedings,
CEUR-WS.org, 2005
Introduction Motivation & Objectives Tools Used Architecture Conclusion Bibliography

http://protege.stanford.edu/
http://jena.sourceforge.net/ARQ/Tutorial
http://www.w3.org/TR/rdf-sparql-query/
http://www.swoogle.com/

Potrebbero piacerti anche