Sunteți pe pagina 1din 15

Human Disease Prediction Using

Rule Based Expert System


R.Karthikeyan
Assistant professor
SRM COLLEGE CHENNAI

Research Supervisor
Dr P.Geetha,
Assistant Professor
Dr.Umayal Ramanathan College for Women
Karaikudi
 An expert system is a computer system that emulates the
decision-making ability of a human expert and reaches
the performance of an expert in a narrow domain of
intellectual expertise. Often this is some kind of
diagnostic.
 The idea of an expert system is to use the knowledge
from an expert system and to encode it into a set of rules.
A rule-based system consists of a set of IF-THEN rules,
a set of facts and some interpreter controlling the
application of the rules, given the facts.
In artificial intelligence (AI) systems, forward chaining
refers to a scenario where the AI has been provided with a
specific problem must "work forwards" to figure out how
to solve the set problem. To do this, the AI would look
back through the rule-based system to find the "if" rules
and determine which rules to use.
• The main objective of this research work is to
predict human disease by using Rule based
expert system with supervised learning
algorithm classification and decision tree
techniques.
Classification is the problem of assigning new
observations to the class to which they most
likely belong, based on a classification model
built from labeled training data.
 A Decision tree is a flow chart likes tree
structure, where each node denotes a test on an
attribute value, each branch represents an
outcome of the test, and tree leaves represent
classes or class distribution
Existing system
A Belief Rule based Expert System to
Diagnose Dengue Fever under Uncertainty

Disadvantages:
1) The architecture does not have any machine learning
tools to cross check predicted values.
2) It also uses backward chaining process to predict the
disease from the human through various questionnaires.
3) Missing values calculation is not provided
Medical Diagnosis Expert System for Malaria and
Related Diseases for Developing Countries

Disadvantages:
1.This paper does not have any statistical formulas or
metrics to cross verify the given data is correct or not
2.CLIPS – basically works based on questionnaire
3. To improve the accuracy of the result is not available
4. Attribute selection is not provided
Proposed Architecture Diagram
Proposed System
Proposed system is to develop an expert system that could predict various disease in a
person accurately by using rule based classification.
 Rule-based system consists of a few basic and simple elements as follows:
1. A set of facts. These facts are actually the assertions and should be anything
relevant to the beginning state of the system.
2. A set of rules. This contains all actions that should be taken within the scope of
a problem specify how to act on the assertion set. A rule relates the facts in the IF
part to some action in the THEN part. The system should contain only relevant
rules and avoid the irrelevant ones because the number of rules in the system will
affect its performance.
3. A termination criterion. This is a condition that determines that a solution has
been found or that none exists. This is necessary to terminate some rule-based
systems that
The goal of classification is to accurately
predict the target class for each case in the
data. For example, a classification model could
be used to identify whether a person is
affected by the disease or not
 Decision TreeJ48 is an extension of ID3(Iterative
Dichotomiser 3). The additional features of J48
are accounting for missing values, decision trees
pruning, continuous attribute value ranges,
derivation of rules, etc. In the WEKA data mining
tool, J48 is an open source Java implementation
of the C4.5 algorithm.
 The performance are evaluated by the two
evaluation measures: Confusion Matrix &
Entropy and Information Gain
RULE BASED (IF- THEN-ELSE)

An example showing the parts of a rule based systems and the interactions between them
Advantages of the architecture

• Prediction of human disease by rule based expert system


• Rule based IF-THEN –ELSE is used to category the
various diseases based on their symptoms
• Inference engine uses Forward chaining , it refers to a
scenario "work forwards" to figure out how to solve the
problem
• Data’s are collected through various modes like repository,
Disease expert, Patients, Knowledge expert, www.
• Every data`s are commonly applied in training data set for
WEKA and through knowledge base expert system.
• Dataset is tested for accuracy by supervised learning
classification and decision tree, if the accuracy is low then
check for the missing values in the dataset and replace
missing values by mean or standard deviation of the
attribute to get better accuracy
• Once Training model is created it is cross verified with the
test data / unseen data for the efficiency of the model
• Attribute and feature selection is made for the best attribute
as a root node for disease prediction in the WEKA.
• Entropy and Information Gain are used to cross validate the
result of decision tree generated by classifier.
• Results from model and expert system are tested for
originality of disease prediction
THANK YOU

S-ar putea să vă placă și