neuro fuzzy based heart desease diagnosis

8/10/2019 Neuro fuzzy based heart desease diagnosis

1/42

i

Neuro-fuzzy Based Heart Diseases Diagnosis

By

Patel Harshad S.

(130420704010)

Supervised by,

Prof.(Dr.) Maulin Joshi

(Phd., Professor)

A Thesis Submitted toGujarat Technological University

in Partial Fulfillment of the Requirements for

the Degree of Master of Engineering

in Electronics & Communication

DECEMBER 2014

Department

OfElectronics & Communication Engineering

Sarvajanik College of Engineering & Technology

Dr R.K. Desai Road,

Athwalines, Surat - 395001, India


2/42

ii

CERTIFICATE

This is to certify that research work embodied in this thesis entitled Neuro-fuzzy Based

Heart Diseases Diagnosis was carried out by Mr. Harshadkumar Shnakarbhai Patel

(130420704010) at Sarvajanik College of Engineering and Technology for partial

fulfillment of M.E. degree to be awarded by Gujarat Technological University. This

research work has been carried out under my supervision and is to my satisfaction.

Date:

Place: Sarvajanik College of Engineering and Technology,Surat.

Prof.(Dr.) Maulin M. Joshi

ProfessorElectronics & Communication

Department

Sarvajanik College ofEngineering & Technology

Prof. Niteen B. PatelHead of Department

Electronics & Communication

DepartmentSarvajanik College of

Engineering & Technology

Dr. Vaishali Mungurwadi,

Principal,

Faculty of Engineering,Sarvajanik College of Engineering & Technology

Seal of Institute


3/42

iii

Declaration of originality

I hereby certify that I am the sole author of this thesis and that neither any part of this

thesis nor the whole of the thesis has been submitted for a degree to any other University

or Institution.

I certify that, to the best of my knowledge, my thesis does not infringe upon anyones

copyright nor violate any proprietary rights and that any ideas, techniques, quotations, or

any other material from the work of other people included in my thesis, published or

otherwise, are fully acknowledged in accordance with the standard referencing practices.

Furthermore, to the extent that I have included copyrighted material that surpasses the

bounds of fair dealing within the meaning of the Indian Copyright Act, I certify that I

have obtained a written permission from the copyright owner(s) to include such

material(s) in my thesis and have included copies of such copyright clearances to my

appendix.

I declare that this is a true copy of my thesis, including any final revisions, as approvedby my thesis review committee.

Date:

Pl ace: Sarvajanik College of Engineering and Technology, Surat

Signature of Student :

Name of Student : Patel Hrashadkumar S.

Enrollment No : 130420704010

Signature of Guide :

Name of Guide:Prof. (Dr.) Maulin M. Joshi

Institute Code: 042


4/42

iv

Acknowledgement

I would like to express my deep sense of gratitude to my guide, Prof. (Dr.) Maulin M.

Joshi for imparting me valuable guidance and priceless suggestions during the

dissertation and in creating such an excellent report and also for his full dedication anddevotion of time.

I would further like to thank our Head of Department, Prof. Niteen B. Patel and all the

faculty members for giving me this opportunity. I also wish to communicate my deep

sense of gratitude and thanks to the Almighty God.

I would like to express thanks, gratitude and respect to my parents for giving me valuable

advice and support at all times and in all possible ways. Last but not least,

Acknowledgement will not be over without mentioning a word of thanks to all my friends

& my family members who have provided immeasurable support throughout this journey.

Yours Sincerely

Patel Harshad S.


5/42

v

Table of Contents

1. Introduction ................................................................................................................. 1

1.1 Scope ......................................................................................................................... 1

1.2 Motivation ................................................................................................................. 2

1.3 Organization of thesis ............................................................................................... 2

2. Basic Theory ............................................................................................................... 3

2.1 Introduction of Neural Network................................................................................ 3

2.2.1 Artificial Neuron Model .................................................................................... 4

2.1.2 Feed-Forward Neural Network .......................................................................... 5

2.2 Introduction of Fuzzy Inference System ................................................................... 7

2.3 Introduction of ANFIS .............................................................................................. 9

2.4 Parameter of Heart Diseases Diagnosis .................................................................. 10

2.4.1 Detail Of attributes ........................................................................................... 13

3. Literature Review...................................................................................................... 19

3.1 Prediction of nasopharyngeal carcinoma recurrence by neuro-fuzzy techniques.[3]

....................................................................................................................................... 19

3.1.1 Single input Rule module method (SIRMs)..................................................... 19

3.1.2 Functional-type single input rule modules connected fuzzy inference method

(F-SIRMs) ................................................................................................................. 20

3.1.3 A generalized neural network-type single input rule modules connected fuzzy

inference method (G-NN-SIRMs) ............................................................................ 21

3.2 Effective diagnosis of heart disease through neural networks ensembles.[4]

......... 22

3.3 The reevaluate statistical results of quality of life in patients with cerebrovascular

disease using adaptive network-based fuzzy inference system.[5]

............................... 22

3.3.1 Adaptive Neuro fuzzy inference system .......................................................... 23

4. Implementation ............................................................................................................. 26

REFERENCES ..................................................................Error! Bookmark not defined.


6/42

vi

List of Figure

Figure 2-1 Basic Neural Model[2]

.................................................................................... 4

Figure 2-2 Feed- forward or acyclic network with single layer[1]

................................ 5

Figure 2-3 fully connected feed forward or acyclic network with one hidden layerand one output layer

[1]..................................................................................................... 6

Figure 2-4 Fuzzy System[2]

.............................................................................................. 8

Figure 2-5 Architecture of ANFIS[5]

............................................................................. 10

Figure 3-1 Architecture of F-SIRMs[3]

......................................................................... 20

Figure 3-2 Architecture of G-NN-SIRMs[3]

................................................................. 21

Figure 3-3 Block representation of proposed ANFIS structure for input/output

variables.[5]

....................................................................................................................... 23


7/42

vii

List of Table

Table 2-1 Attributes description.................................................................................... 11

Table 2-2 Age................................................................................................................... 13

Table 2-3 Cholesterol...................................................................................................... 14

Table 2-4 Blood Pressure................................................................................................ 15

Table 2-5 Heart rate........................................................................................................ 15

Table 2-6 Blood Sugar.................................................................................................... 16

Table 2-7 Electrocardiography...................................................................................... 16

Table 2-8 Old Peak.......................................................................................................... 17

Table 2-9 Thallium Scan................................................................................................ 17

Table 2-10 Output........................................................................................................... 18


8/42

viii

Acronyms

NN Neural Network

RBF Radial Basis Function

FF Feed Forward Network

MLP Multilayer Perceptron

MSE Mean Square Error

ANN Artificial Neural Network

BP Back Propagation

SIRMs Single Input Rule Modules

F-SIRMS Function Single Input Rule Modules

ANFIS Adaptive Neuro Fuzzy Inference System


9/42

ix

Abstract

Medical diagnosis where by any application can be incorporated with help of Artificial

Neural Network (ANN), usually called neural network (NN), Adaptive neuro-fuzzy

inference system(ANFIS),the functional type single input rule modules connected fuzzy

inference method(F-SIRMs Method) and the functional and neural network type SIRMs

method(F-NN-SIRMs method).

Automation of classification through the use of computers is common practice today,

reaping tremendous benefits. The example in medical diagnosis, involves the

classification of various diseases considering the number of attributes .In this I can

classify pattern using different technique. In this project it is planned to apply Neuro-

fuzzy based network for specific application using simulation platform. Results could be

analyzed further and compared with other existing methods. In this work, different

attributes are given to the Neuro-fuzzy based network to generate single output classify

person into normal or person with possibility of number of heart attack already occurred.

After training the network with sufficient number of training pair derived from standard

data set, testing is done on the various cases that shows the effectiveness of proposed

approach.


10/42

1

1.Introduction

A major challenge, facing healthcare organizations (hospitals, medical centers) is the

provision of quality services at affordable costs. Quality service implies diagnosing

patients correctly and administering treatments that are effective. Integration of clinical

decision support with computer-based patient records could reduce medical errors,

enhance patient safety, decrease unwanted practice variation, and improve patient

outcome. In spite of the rapid development of pathological research and clinical

technologies, people die suddenly due to arrhythmias and heart diseases. The aim of the

present study is to identify the combination of clinical and a laboratory noninvasive

variable, easy to obtain in most patients, that best predicts the occurrence of heart

diseases. Taking cardiologists as gold standard it is aimed to minimize the difference by

means of machine learning tools. From exhaustive and careful experimentations, it is

observed that proposed Neural Network (NN) classifiers ensures true estimation of the

complex decision boundaries, remarkable discriminating ability and does outperform the

statistical discriminate analysis and classification tree rule based predictions.

Clinical decisions are often made based on doctors intuitions and heuristics experience

rather than on the knowledge rich data hidden in the database. This practice leads to

unwanted biases, errors and excessive medical costs which affects the quality of service

provided to patients. A number of techniques have been used for identification of heart

diseases including waveform analysis, time frequency analysis, complexity measures,

Neuro, Fuzzy, Neuro-fuzzy, Radial Basis Function (RBF) NN and a total least square

based Prony modeling algorithm.

1.1 Scope

Artificial neural network are finding many uses in medical diagnosis. They are actively

being used for such applications as locating previously undetected patterns in mountains

of research data, controlling medical devices based on biofeedback, and Detecting

characteristics in medical imagery. The system uses neural network for model estimation

and classification of Normal and several heart diseases based on the attributes.


11/42

2

1.2 Motivation

In face of uncertainty of heart disease symptoms even experienced cardiologists need

complimentary assistance from intelligent decision system to arrive at precise diagnosis

of cardiac disease.

1.3 Organization of thesis

Rest of the thesis is organized as follows: Basic theory of neural network, Fuzzy

Inference System, Adaptive Neuro-Fuzzy Inference System (ANFIS) and Parameter of

Heart Diseases Diagnosis is predicted in chapter 2. Brief review of literature survey is

discussed in chapter 3.The implementation of method and analysis are presented in

chapter 4 which is followed by simulation result and comparison in chapter 5 and finally

conclusion.


12/42

3

2.Basic Theory

2.1 Introduction of Neural Network

A neural network is artificial representation of human brain that tries to stimulate its

learning process. Traditionally the neural word referred to biological neurons in the

nervous system that transmit information. Artificial neural network is interconnected

groups of artificial neurons that use mathematical model that uses mathematical model or

computational model for information processing based or connectionist approach to

computation. The artificial neural network is made up of interconnecting artificial

neurons that usesproperties of biological neural network.

Artificial neural network is an adaptive system that changes its structure based on external

and internal information that flows to network. In information technology, a neural network

is a system of programs and data structures that approximates the operation of the human

brain. A neural network usually involves a large number of processors operating in parallel,

each with its own small sphere of knowledge and access to data in its local memory.

Typically, a neural network is initially "trained" or fed large amounts of data and rules about

data relationships .A program can then tell the network how to behave in response to an

external stimulus (for example, to input from a computer user who is interacting with the

network) or can initiate activity on its own (within the limits of its access to the external

world).

Machine learning is the field of research devoted to the formal study of learning systems.

This is a highly interdisciplinary field which borrows and builds upon ideas from statistics,

computer science, engineering, cognitive science, optimization theory and many other

disciplines of science and mathematics. One of the most significant attributes of a neural

network is its ability to learn by interacting with its environment or with an information

source. Learning in a neural network is normally accomplished through an adaptive

procedure, known as a learning rule or algorithm, whereby the weights of the network are

incrementally adjusted so as to improve a predefined performance measure over time.

It is basically defined as, Learning is a process by which the free parameters of a neural

network are adapted through a process of stimulation by the environment in which the

network is embedded. The type of learning is determined by the manner in which the


13/42


14/42

5

i (1)

Where is a neuron activation threshold.

2.1.2 Feed-Forward Neural Network

The manner in which the neurons of neural network are structured is intimately linked

with learning algorithm used to train network. We therefore speak of learning algorithm

used in design of neural network as begin structured.

a) Single layer feed forward network:

In a layered neural network the neural are organized in a form of layers. In this we have

input layer of source node that project onto an output layer of a neurons but not vice

versa. So this type is feed forward or acyclic type as shown in Figure 2.2.

Figure 2-2 Feed- forward or acyclic network with single layer[1]

b) Multi-layer feed forward network:


15/42

6

The second class of a feed-forward neural network distinguishes itself by presence of one

or more hidden layer, whose computation nodes are correspondingly called hidden units

or hidden neuron. The function of hidden neuron is to intervene between external input

and network output in some useful manner. By adding one or more hidden layer, the

network is enabling to extract higher order statistics. The source nodes in the input layer

of the network supply respective elements of the activation pattern which constitute the

input signal apply to the neurons in second layer. The output signals of the second layer

are used as an input to the third layer and so on for the rest of the network. The neural

network in the Figure 2.3 is fully connected in the sense that every node in the each layer

of the network is connected to the every other node in adjacent forward layer.

Figure 2-3 fully connected feed forward or acyclic network with one hidden layer and one output

layer[1]

.


16/42

7

2.2 Introduction of Fuzzy Inference System

What is Fuzzy System?

Fuzzy Systems include Fuzzy Logic and Fuzzy Set Theory.

Knowledge exists in two distinct forms:

The Objective knowledge that exists in mathematical form is used in engineering

problems.

The Subjective knowledge that exists in linguistic form, usually impossible to

quantify.

Fuzzy Logic can coordinate these two forms of knowledge in a logical way. Fuzzy

Systems can handle simultaneously the numerical data and linguistic knowledge. Fuzzy

Systems provide opportunities for modeling of conditions which are inherently

imprecisely defined. Many real world problems have been modeled, simulated, and

replicated with the help of fuzzy systems.

The applications of Fuzzy Systems are many like:

Information retrieval systems,

Navigation system

Robot vision.

Expert Systems design have become easy because their domains are inherently fuzzy and

can now be handled better.

Examples: Decision-support systems, financial planners, Diagnostic system, and

Meteorological system.


17/42

8

Fuzzy System

A Block Diagram of Fuzzy System Is shown in figure 2-4.

Figure 2-4 Fuzzy System[2]

Fuzzy System Elements:

Input Vector: X = [x1, x2xn] T are crisp values, which are transformed into fuzzy sets

in the fuzzification block.

Output Vector: Y = [y1, y2ym] T comes out from the defuzzification block, which

transforms an output fuzzy set back to a crisp value.

Fuzzification: a process of transforming crisp values into grades of membership for

linguistic terms, "far", "near", "small" of fuzzy sets.

Fuzzy Rule base: a collection of propositions containing linguistic variables; the rules

are expressed in the form: If (x is A) AND (y is B) . . . . . . THEN (z is C)

Where x, y and z represent variables (e.g. distance, size) and A, B and C are linguistic

variables (e.g. `far', `near', `small').

Membership function:provides a measure of the degree of similarity of elements in the

universe of discourse U to fuzzy set.


18/42

9

Fuzzy Inference:combines the facts obtained from the Fuzzification with the rule base

and conducts the Fuzzy reasoning process.

Defuzzification:Translate results back to the real world values.

2.3 Introduction of ANFIS

Current systems have a lacking in handling imprecise and vague information but still

achieving precise and useful results, which is a natural process for a human brain to

perform. Due to this, Soft Computing emerged as a sub-area of Computational

Intelligence, offering techniques and solutions for computationally deal with imprecise

data (Zadeh 1994).

The Soft Computing techniques tend to be suitable for combining with other established

methods, making it possible to create hybrid systems which are more suitable for problem

solving and data analysis. Fuzzy set theory (Zadeh, 1965), has recently attracted more

interest, as computers are today more suitable for handling the somewhat computationally

intensive calculations imminent in the Soft Computing field.

Another technique affiliated with soft computing is neural networks, inspired from the

actual principles of the human brain, creating an artificial network of interconnected

neurons (Jang et al., 1997). Due to its complex implementation, a neural network is

sometimes regarded as a black-box model. This means that one is only able to see themodels inputs and outputs, not what is going on inside the process.

The advantage is the Learning abilities, which is why it is often used together with other

methods. By including fuzzy sets into the mixture it creates a hybrid approach, called

neuro-fuzzy models, which integrates the strengths of both methods. Jang (1993) and

Jang et al. (1997) introduced a class of adaptive networks that perform in the same

manners as fuzzy inference systems, called ANFIS. The architecture combines the

properties of neural networks and fuzzy logic, creating a dynamic fuzzy inference system

similar to the Sugeno fuzzy model (Sugeno and Kang, 1988), built as a network based on

the same manner as in neural networks.

Adaptive-Network-based Fuzzy Inference System (ANFIS) were firstly introduced by

Jang. It is composed of five layers as shown in Figure 2-5. Layer 1 is called the

fuzzification layer. Crisp inputs are transformed into the membership degrees of the


19/42

10

fuzzy sets in the antecedent part. Here, the bell-shaped membership function is used.

Layer 2 is the rule layer. It calculates the rule firing strength from the product of all

incoming signals. These rule firing strengths are normalized in layer 3. This layer is thus

called the normalization layer. Layer 4 is the defuzzification layer. The product of

normalized rule firing strength from layer 3 and a first-order polynomial function of its

inputs is calculated. The last layer is the output layer. It produces the crisp output as the

summation of all incoming signals.

Figure 2-5 Architecture of ANFIS[5]

ANFIS is a hybrid learning algorithm in which it combines the least-square estimator and

the gradient descent method. In the forward pass, premise parameters are fixed. The least-

square estimator is used for determining parameters in the consequent part. In the

backward pass, the consequent parameters are instead fixed. The gradient descent method

is then applied in order to adjust parameters of the antecedent parts.

2.4 Parameter of Heart Diseases Diagnosis

The datasets chosen for project are taken Heart diseases database. It concern

classification of person into normal and abnormal person. All attributes and the values are

given.

Number of attributes: 13 + class attributes


20/42

11

Classes:

Class0: Normal person

Class1: First stroke

Class2: Second stroke

Class3: End of life

Table 2-1 Attributes description

Sr.no Attribute Description Range

1 Age Age in year Continuous

2 Gender (1=male, 0=female) 0,1

3 cp Value 1:typical angina

Value 2:atypical angina

Value 3: non-angina pain

Value 4 : asymptomatic

1,2,3,4

4 Trestbps Resting blood pressure(in mm

Hg)

Continuous

5 Chol Serum cholesterol in mg/dl Continuous

6 Fbs (Fasting blood sugar > 120

mg/dl)

(1=true , 0= false)

0,1

7 Restecg Resting electrocardiographic

result

0, 1, 2
http://g/What%20Is%20Angina_%20-%20NHLBI,%20NIH.pdfhttp://g/What%20Is%20Angina_%20-%20NHLBI,%20NIH.pdfhttp://g/What%20Is%20Angina_%20-%20NHLBI,%20NIH.pdf


21/42

12

-value 0: normal

-value1: having ST-T wave

abnormality (T wave inversions

and/or ST

Elevation or depression of >

0.05mV)

-value 2: Showing probable or

definite left ventricular

Hypertrophy by Estes 'criteria

8 Thalach Maximum heart rate achieved Continuous

9 Exang Exercise induced angina (1=yes,

0=no)

0, 1

10 Old peak ST depression induced by

exercise relative to rest

Continuous

11 Slope The slope of the peak exerciseST

segment

-value 1: up sloping

-value 2: flat

-value 3: down sloping

1, 2, 3

12 Ca Number of major vessels (0-3)

coloured by fluoroscopy

Continuous

13 Thal Normal, fixed defect, reversible

defect

3, 6, 7
http://g/The%20ST%20segment%20-%20Life%20in%20the%20Fast%20Lane%20ECG%20Library.pdfhttp://g/The%20ST%20segment%20-%20Life%20in%20the%20Fast%20Lane%20ECG%20Library.pdfhttp://g/The%20ST%20segment%20-%20Life%20in%20the%20Fast%20Lane%20ECG%20Library.pdfhttp://g/The%20ST%20segment%20-%20Life%20in%20the%20Fast%20Lane%20ECG%20Library.pdf


22/42

13

2.4.1 Detail Of attributes

For the input variable Cholesterol, we use Low Density Lipoprotein (LDL). However, it

is also possible to use High density Lipoprotein (HDL). In case of Blood Pressure,

Systolic Blood Pressure is used.

Membership function is important for each fuzzy variable. Also rules strength is

calculated based on the membership function.

Age: This input consists of four fuzzy sets i.e. Linguistic variable (Young, Mid, Old,

Very old). Each Linguistic variable has membership functions associated with them. The

range of the fuzzy sets for age is shown in Table 1.

Table 2-2 Age

Chest Pain:This input field has four Chest Pain types: Typical Angina, Atypical Angina,

Non Angina, and Asymptomatic. One Patient can have only one type of Chest Pain at a

time.

To represent Chest Pain,

1= Typical Angina,

2 = Atypical Angina,

3= Non Angina

4 = Asymptomatic.

Input Field Range Linguistic

Representation

Age

Young

Mid

Old

Very Old


23/42

14

Cholesterol: This input field influences the result much more comparing to other input

fields. Cholesterol can be Low Density Lipoprotein (LDL) and High density Lipoprotein

(HDL). In our system, we only consider LDL. However, it is possible to consider HDL

instead of LDL. We use only one type at a time. This field has four fuzzy sets. Each

fuzzy variable is associated with membership function. The range of the fuzzy sets for

Cholesterol is given in Table 2.

Table 2-3 Cholesterol

Input field Range Linguistic

Representation

Cholesterol < 197

188-250

217-307

281>

Low

Medium

High

Very High

Gender:This input Field has two representations (Male and Female).

1 represents male

0 indicates female.

Blood Pressure: Another important risk factor is Blood Pressure. It can be Systolic,

Diastolic and Mean types. In our system, we consider Systolic Blood Pressure. It is

possible to choose any type of Blood Pressure. This field has four fuzzy sets. The ranges

for the Linguistic variable representation are given in Table 2-4. The membership

function is calculated based on the range.


24/42

15

Table 2-4 Blood Pressure

Input field Range Linguistic

Representation

Blood

Pressure

< 134

127- 153

142-172

154>

Low

Medium

High

Very High

Heart rate: This field has three fuzzy sets. Each Linguistic representation is associated

with membership function. The ranges for each linguistic representation are given in

Table 2-5.

Table 2-5 Heart rate

Input Field Range Fuzzy sets

Heart rate < 141

111-164

162>

Low

Medium

High

Blood Sugar: This field plays an important role in changing the results. It has two

linguistic representations. Each fuzz variable is associated with membership function

based on the range. The ranges of fuzzy sets are given in Table 2-6.


25/42

16

Table 2-6 Blood Sugar

Input Field Range Linguistic

Representation

Blood

Sugar

>=120


26/42

17

Old Peak: This field means ST depression induced by exercise relative to rest. The

meaning of ST depression is related to the ECG field. It means previously the patient's T

wave and S wave in the ECG graph paper were down. Old Peak is necessary to assure the

present condition of T wave and S wave of the ECG. It has three fuzzy sets

representation. Each fuzzy variable is associated with membership function. The range

for the fuzzy sets is given in Table 2-8.

Table 2-8 Old Peak


Old Peak

Low

Risk

Terrible

Thallium Scan:Thallium scan is the redistribution of heart image. This input field has

three linguistic representations: Normal, Reversible Defect and Fixed Defect. It depends

on the hours that a heart image appears on the screen of the Gamma camera. This Gamma

camera is able to detect radioactive dye in the body. To develop our system we assume

that the linguistic representation of thallium scan in the Normal, the heart image appears

within 3 hours, in fixed Defect heart image appears within 6 hours and in the Reversible

Defect the heart image appears within 7 hours. The linguistic representation for Thallium

scan is given in Table 8.

Table 2-9 Thallium Scan


3

6

7

Normal

Fixed Defect

Reversible

Defect


27/42

18

Output: The output is the presence of Heart disease valued from 0(no presence i.e.

Healthy condition) to 3. If the integer value increases then the heart disease risk

increases. We divide the Output fuzzy sets {normal, First stroke, Second Stroke, End of

life}.The ranges and membership function for output variable are given below:

Table 2-10 Output

Output Field Range Fuzzy sets

Result

Normal

First Stroke

Second Stroke

End of life


28/42

19

3.Literature Review

3.1 Prediction of nasopharyngeal carcinoma recurrence by neuro-fuzzy

techniques.[3]

Neuro-fuzzy techniques for prediction of nasopharyngeal carcinoma recurrence are

mainly focused in this paper. In the study, clinical data of patients with nasopharyngeal

carcinoma were collected from Ramathibodi hospital, Thailand. In total, 495 records

were taken into account. Relevant factors were extracted and employed in developing

predictive models. The results showed that the proposed technique was superior to the

other neuro-fuzzy techniques, stand-alone neural network, and logistic regression and

Cox proportional hazard model. Accuracy and AUC above 80% and 0.8 could be

achieved. To show validity of the proposed technique, two nonlinear problems, i.e.,

function approximation and the XOR classification problems, are studied.

Neuro-fuzzy techniques

Neuro-fuzzy technique unites fuzzy inference system and artificial neural network in

order to achieve an adaptive reasoning capability. The technique can manage imprecise

information and efficiently handle highly nonlinear problems. In general, parameters of

the fuzzy model are learned to provide mapping between training inputoutput pairs.

Three neuro-fuzzy techniques are mainly investigated in this paper.

3.1.1 Single input Rule module method (SIRMs)

The single input rule modules connected type fuzzy inference method (SIRMs method)

has been presented by Yubazaki. It provides the same number of rule modules as input

variables. Therefore, it can decrease the number of fuzzy rules in conventional fuzzy

inference method. Thus it has been effectively applied to many problems however, it can

be handled with only simple application.


29/42

20

3.1.2 Functional-type single input rule modules connected fuzzy

inference method (F-SIRMs)

F-SIRMs was proposed by Sekietal to enhance reasoning capabilities of SIRMs method.

It was successfully applied to nonlinear function approximation and classification

problems. In addition, it has been proven to be a subset of TakagiSugeno inference

system. Simple architecture of F-SIRMs composed of two inputs and one output is shown

in Fig.3-1.

Figure 3-1 Architecture of F-SIRMs[3]

In the figure, each input, xi(i=1, 2), has three corresponding membership functions, Ai1,

Ai2,Ai

3, represented by the Gaussian function form. Degrees of the membership function,

hi1, hi

2, hi

3, are evaluated in layer1.Therefore, this layer is called the fuzzification layer as

in ANFIS model. Layer2 is called the rule module layer. It consists of rule modules. The

number of rule modules is equal to the number of input variables .Each module contains

m associated fuzzy rules as

Rule modules-i: {xi=Ajiyi= fj

i(xi)}j=1

mi (2)

Where fji(xi) is a function of input xi.


30/42

21

Unifying outputs of the associated fuzzy rules, inference result, yiof the ithmodule can be

determined by

(3)

And the final output of F-SIRMs is given by

(4)

Where wiis the weight of the ith

rule module. N is the number of input nodes.

3.1.3 A generalized neural network-type single input rule modules

connected fuzzy inference method (G-NN-SIRMs)

Though F-SIRMs provided better inference results than the traditional SIRMs method,

with linear functions in the consequent part, generated fuzzy rules are still limited and

unable to efficiently handle highly nonlinear data. In this paper, we propose a generalized

neural network-type single input rule modules connected fuzzy inference method (G-NN-

SIRMs). It combines F-SIRMs technique with artificial neural network. Layer 4 of F-

SIRMs is replaced by multilayer perceptron neural network as shown in Figure 3-2.

Inference results from the rule module layer are thus the inputs to the neural network.

Figure 3-2 Architecture of G-NN-SIRMs[3]


31/42

22

In G-NN-SIRMs model layer 4 represents hidden layer of the multilayer perceptron

neural network. Output, Hk , of the kth

hidden node is obtained by

(5)

Where,

(6)

Layer 5 is the output layer.it provides the final inference result as,

(7)

Where,

(8)

Is the induced local field of the pth

neuron in the output layer. Worepresents weight of the

output. The gradient descent method is employed for adapting parameters in order to

reduce the error function formed by the difference between the target zt and the final

inference result.

The Error Function is given by

(9)

3.2 Effective diagnosis of heart disease through neural networks

ensembles.[4]

Parameters from this paper are taken and are described in the previous section 2.4.

3.3 The reevaluate statistical results of quality of life in patients with

cerebrovascular disease using adaptive network-based fuzzy inference

system.[5]

In this paper, the research data about quality of life in persons with cerebrovascular

disease (CVD) is examined by Adaptive-Network- based Fuzzy Inference system


32/42

23

(ANFIS) and these results are compared with statistical results obtained from the same

data.

3.3.1 Adaptive Neuro fuzzy inference system

The ANFIS is a fuzzy Sugeno model put in the framework of adaptive systems to

facilitate learning and adaptation (Jang, 1993; Jang, 1992). For a first-order Sugeno fuzzy

model Sugeno and Kang, 1988; Takagi and Sugeno, 1985, a typical rule set with two

fuzzy if-then rules can be expressed as

Rule 1: if (x is A1) and (y is B1) then (f1= p1x +q1y + r1).

Rule 2: if (x is A2) and (y is B2) then (f2= p2x +q2y + r2).

Where x and yare the inputs, Aiand Biare the fuzzy sets, fi are the outputs within the

fuzzy region specified by the fuzzy rule, pi, qiand r1are the design parameters that are

determined during the training process. Figure 3-3 illustrates the reasoning mechanism

for this Sugeno model. The corresponding equivalent ANFIS architecture is as shown in

Figure 3-3, where nodes of the same layer have similar functions, as described below.

(Here we denote the output node i in layer 1 as O1, i.)

Figure 3-3 Block representation of proposed ANFIS structure for input/output variables.[5]

Layer 1:

Every node i in this layer is an adaptive node with a node output define by

(10)

(11)

Ai(x) and Bi2(x) can adopt any fuzzy membership function. X (or y) is the input node i

and Ai (or Bi2) is a linguistic label (small, large, etc.)Associated with this node. If thebell shaped membership function is employed Ai(x) is given by:


33/42

24

bacx

i

i

i

Ax

21

1)(

(12)

Ai, bi, ciare the parameter set. Parameters are referred to as premise parameters.

Layer 2:

Every node in this layer is a fixed node .The output is the product of all the incoming

signals.

(13)

Each node represents the fire strength of the rule.

Layer 3:

Every node in this layer is affixed node labeled N. The ith node calculates the ratio of the

ith rules firing strength to the sum of all rules firing strengths:

2,1,

21

3

i

www

wo i

ii

(14)

Output of this layer will be called Normalized firing strengths.

Layer 4:

Every node i in this layer is an adaptive node with a node function:

)(4

rqpwfwo iiiiiii yx (15)

Wiis the normalized firing strength from layer 3. {P i, qi, ri} is the parameter set of this

node. These are referred to as consequent parameters.

Layer 5:

The single node in this layer is a fixed node labeled sum, which computes the overall

output as the summation of all incoming signals:


34/42

25

ww

fwfwo

i ii

iiii

21

2

12

1

5

(16)

Constructed an adaptive network that has exactly the same function as a Sugeno fuzzy

model.


35/42

26

4. Implementation

4.1 Implementation Using Neural Network

MATLAB (Matrix Laboratory) is a programming language and a development environment

for matrix-based computation. Of particular interest to us here is the Neural Network

Toolbox, which constitutes one of the most comprehensive neural network packages

currently available.

Artificial Intelligence involves the training and performance artificial neural networks on the

problem of classifying result on database. In proposed work as shown in below Figure 4.1

training dataset contains 13 attributes as input and one value for target classification. The

descriptions of 13 attributes are as shown in table 4.1.Weight will be updated for reducing

error and finally one network will be created, which will be directly used for testing.

Figure 0-1 Training and testing of proposed NN


36/42

27

4.1.1 Selection of Parameters

a) Selection of transfer function

net = newff(AX,AY,15, {'tansig' 'purelin'},'trainlm') Where newff is the feed-forward neural

network with input AX, target AY and here 15 neurons in hidden layer.

Transig:- Tansig is a transfer function. Transfer functions calculate a layer's output from its

net input. However, it may be more accurate and is recommended for application.

Purelin:- Purelin is a neural transfer function. Transfer functions calculate a layer's output

from its net input.

b) Selection of training function

Trainlm:- Trainlm is a network training function that updates weight and bias values

according to Levenberg-Marquardt optimization. It is often the fastest backpropagation

algorithm in the toolbox, and is highly recommended as a first-choice supervised algorithm,

although it does require more memory than other algorithms.

c) The Normalization of input data:

Normalization of Each ALL input data is required to be brought in the range between [0 -1]

and thus avoiding undue bias to some of the inputs.

The network is simulated and its output plotted against the targets.

Y= sim(net, p)

The sim command causes the specified Simulink model to be executed. The model is

executed with the data passed to the sim command, which may include parameter values

specified in an options structure. The values in the structure override the values shown for

block diagram parameters in the Configuration Parameters dialog box, and the structure may

set additional parameters that are not otherwise available (such as DstWorkSpace). The

parameters in an options structure are useful for setting conditions for a specific simulation

run.

4.1.2 Training Network Algorithm

In the proposed approach, we train the network as follows:

First, let input cardinality (number of sensor inputs) of the neural networks equal to

13 attribute

Generate training pairs based on attribute


37/42

28

Second, output values of each of these input patterns are decided based on

experimentation/ by training pairs generated by experts. We have used standard -

Cleveland data

Neural network is trained accordingly to the training pairs generated and performance

of the network can be checked using proper evaluating function e.g. MSE (mean

square error)

If any correction is required; make adjustment to step no. 3 and then repeat steps.

4.2 Implementation using fuzzy logic

In the proposed approach, we train the network as follows:

Define inputs from the data.

Define each input membership function.

Define rules in rule base.

Check result.

4.2.1 Simulation Result

1. Rule Editor

Figure 0-2 Rule Editor


38/42

29

2. Rule Viewer

Figure 0-3 Rule Viewer

3. Surface Viewer

Figure 0-4 Surface viewer of blood sugar and cp


39/42

30

Figure 0-5 Surface Viewer Cholesterol and cp

Figure 0-6 Surface Viewer Cp and Bp


40/42

31

Figure 0-7 Surface Viewer Of Bp and Blood sugar

4.3 Future work

Understanding of ANFIS using simple example

Creation of network based on ANFIS(Adaptive Neuro-fuzzy inference system)

and implementation

Comparison of results by NN,FIS and ANFIS


41/42

32

Summary

Standard data set is used for such computation Different Neural network adjustable

parameters/transfer functions are fine-tuned by performing number of experiments.With the

help of both neural network and fuzzy system stage of stroke condition in patience isanalyzed.


42/42

References

Books

1 Simon Haykin, Neural Network a comprehensive foundation, Pearson

Education Asia, 2nd Edition, 19992 RC Chakraborty, Soft Computing-Fundamental of neural network, Dec-

2009

Papers

3 Orrawan Kumdee, Hirosato Seki, Hiroaki Ishii, Thongchai Bhongmakapat

and Panrasee Ritthipravat,Prediction of nasopharyngeal carcinoma

recurrence by neuro-fuzzy techniques, fuzzy sets and systems, pp . 95-

111, Elsevier Ltd, 2012.

4 Resul Das, Ibrahim Turkoglu, Abdulkadir Senger,Effective diagnosis of

heart disease through neural networks ensembles, Expert System with

Application,pp. 7675-7680 Elsevier Ltd, 2009

5 Mahmut Tokmakcl,Demet Vnalan, Ferhan Soyuer and Ahmet

Ozturk,The Reevaluate Statistical results of quality of life in patients

with cerebrovascular disease using Adptive network based fuzzy inference

system,Expert System with Application ,pp.958-963 Elsevier Ltd, 2008

neuro fuzzy based heart desease diagnosis

Documents