26
Computational Model for Artificial Learning Using Formal Concept Analysis 8th International Conference on Computer Engineering and Systems (ICCES’ 2013), EGYPT Mona Nagy ElBedwehy Department of Mathematics, Faculty of Science, Damietta University Email: [email protected] Scientific Research Group in Egypt (SRGE), http://www.egyptscience.net

Computational model for artificial learning using formal concept analysis

Embed Size (px)

Citation preview

Page 1: Computational model for artificial learning using formal concept analysis

Computational Model for Artificial Learning Using Formal Concept Analysis

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Mona Nagy ElBedwehy Department of Mathematics, Faculty of Science, Damietta University

Email: [email protected]

Scientific Research Group in Egypt (SRGE),

http://www.egyptscience.net

Page 2: Computational model for artificial learning using formal concept analysis

2

Agenda Motivation

Contribution

Introduction

Background

Classification Learning

Formal Concept Analysis (FCA)

Computational Models

Proposed Computational Model

Experimental Results and Discussions

Conclusion

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Page 3: Computational model for artificial learning using formal concept analysis

3

Motivation

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Artificial intelligence

Em

bra

ces

Artificial Learning

Understand mechanisms embodied in human and

translating it into computer programs

Developing programs that learn from past data

Page 4: Computational model for artificial learning using formal concept analysis

4

Motivation –Cont. Many applications have a huge amount of data.

civil registration record

Unfortunately, the ability of understanding and using it does

not keep track with its growth.

Methods to generate a “summary” that represent a

conceptualization of the data set. similarities among different citizens (City=Cairo, Gender= Female)

Machine learning provides tools by which large quantities of

data can be automatically analyzed to overcome these

limitations and difficulties. Analysis of urban area population increase

Marketing analysis of store departments

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Formal Concept Analysis is a technique that enables resolution of such problems.

Page 5: Computational model for artificial learning using formal concept analysis

5

Contribution We formulate a computational model for

binary classification process using formal concept analysis.

The classification rules are derived and applied successfully for different study cases.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Page 6: Computational model for artificial learning using formal concept analysis

6

Introduction Machine learning is concerned (on the whole) with

concept learning and classification learning. The latter is simply a generalization of the former.

Classification permits predictions to be derived on the basis of common properties of a class of entities or phenomena.

We will concern on the second approach of the AL that is concerned on the classification learning.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Classification learning is a learning algorithm for classifying unseen examples into predefined classes

based on a set of training examples.

Page 7: Computational model for artificial learning using formal concept analysis

7

Background Classification Learning Generalize classes description by identifying the

common “core” characteristics of a set of training objects to generate knowledge that will enable novel objects to be identified as belonging to one of the classes.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Classification Learning Algorithms

Decision Trees Statistical Classification Neural Networks Symbolic

algorithms

CART Prism SVM Naïve Bayes

Bayesian Networks

Backpropagation The proposed model

Page 8: Computational model for artificial learning using formal concept analysis

8

Background Formal Concept Analysis (1) Formal Concept Analysis (FCA) is a method used for

investigating and processing explicitely given information, in order to allow for meaningful and comprehensive interpretation.

Proposed by Wille. An analysis of data. Structures of formal abstractions of concepts of human

thought. Formal emphasizes that the concepts are mathematical

objects, rather than concepts of mind.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Page 9: Computational model for artificial learning using formal concept analysis

9

Background Formal Concept Analysis (2)

A formal concept is constituted by two parts

Having a certain relation Every object belonging to this concept has all the attributes

in B. Every attribute belonging to this concept is shared by all

objects in A. A is called the concept's extent. B is called the concept's intent.

A: set of

objects

B: set of

attributes

Relations

What is a Concept?

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Page 10: Computational model for artificial learning using formal concept analysis

10

Background Formal Concept Analysis (3)

Object cluster is the set of all objects that share a common subset of attributes.

Attribute cluster is the set of all attributes shared by one of the natural object clusters.

FCA matrix specifying a set of objects and attributes

clusters of attributes clusters of objects

Duck Goose Parrot

Has beak Has feather Has two legs

Object_1 Attribute_1 Attribute_2 Attribute_3

relation

Objects Attributes 8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Object_2

Input Output

Page 11: Computational model for artificial learning using formal concept analysis

11

Background Mathematical Definition of FCA A formal concept is defined within a context.

Definition 1 A formal context is (O, A, R) where O (objects) and A (attributes), and R is a binary relation between O and A.

Equation (1) represents the set of attributes common to the objects in M, while the set of objects which have all attributes in B is represented as in Equation (2).

(1)

(2)

Definition 2 A formal concept of the context (O, A, R) is a pair (M, B) of , , B’= M and M’=B.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

'M a A o Ra for all o M

'B o O o Ra for all a B

M O B A

Page 12: Computational model for artificial learning using formal concept analysis

12

Background Computational Models

Assume that the human brain is an information processing system and that thinking is a form of computing.

Processes information by taking input and follows, a step-by-step algorithm to get a specific output.

The aim of computational modeling is to:

increase our knowledge.

improve our understanding of how the human brain works

build computer systems that can execute a given task optimally and in the most efficient possible way.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Page 13: Computational model for artificial learning using formal concept analysis

13

The Proposed Computational Model

Induces the classification rules which characterize each class.

In the proposed model: 1. Convert the given data into a binary data. Binary

data are data those unit can take on only two possible values termed 0 and 1. We do extension to the collection of attributes by new attributes to represent the binary data.

2. Use FCA to describe the classification process, so the following two functions are presented:

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

( ) | ,o a A o a R R

| ,a o O o a R N

Page 14: Computational model for artificial learning using formal concept analysis

14

The Proposed Computational Model

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Input Data training data and a partition of the training set OC1 , OC2

Add R(a) with maximum no. of objects in Dci to FCi

Compute k- Conjunction

for A

Find R(a)

Add a to AC1 & R(a) to DC1

Convert the given data into a binary data

If R(a) O ø add attribute to FCi, remove R(a) from O and Dci

R(a) OC1 ø R(a) OC2= ø

R(a) OC1 = ø R(a) OC2 ø

Add a to AC2 & R(a) to DC2

While DCi ø

Whi

le O

ø

While last attribute in k- Conjunction is not reached

Page 15: Computational model for artificial learning using formal concept analysis

15

Experimental Results And Discussions (1)

The proposed model is applied to the following datasets from the well-known UCI repository of machine learning datasets that haven’t missing attributes.

Table I. Datasets used in learning the concept classification

Note: Monk3 problem contains 5% noise data.

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Dataset Description No. of

classes

No. of

attributes

No. of

instances

monk1 Monk’s Problem1 2 6 432

monk2 Monk’s Problem2 2 6 432

monk3 Monk’s Problem3 2 6 432

D1 Acute Inflammations(Inflammation

of urinary bladder) 2 6 120

D2 Acute Inflammations

(Nephritis of renal pelvis origin) 2 6 120

Page 16: Computational model for artificial learning using formal concept analysis

16

Experimental Results And Discussions (2)

Some performance indices are calculated for the proposed model such as the following, where TP (true positive), TN (true negative), FP (false positive), FN (false negative).

The performance indices of the proposed model are

compared with Support Vector Machine (SVM) and Classification and Regression Tree (CART).

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

,TP

Sensitivity RecallTP FN

,TN

SpecificityTN FP

,TP

PP PrecisionTP FP

TNNP

TN FN

2( ),

Precision RecallF Measure

Precision Recall

,TP TN

AccuracyTP FP TN FN

Page 17: Computational model for artificial learning using formal concept analysis

17

Experimental Results And Discussions (3)

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Da

ta

Correct Incorrect Misclassified

SVM CART P. model SVM CART P. model SVM CART P. model

monk1 66.20% 83.33% 92.59% 33.80% 16.67% 0.00% 0.00% 0.00% 7.41%

monk2 63.19% 61.11% 63.66% 36.81% 38.89% 18.06% 0.00% 0.00% 18.28%

monk3 78.70% 97.22% 86.11% 21.30% 2.78% 7.18% 0.00% 0.00% 6.71%

D1 100.0% 85.00% 100.0% 0.00% 15.00% 0.00% 0.00% 0.00% 0.00%

D2 100.0% 100.0% 100.0% 0.00% 0.00% 0.00% 0.00% 0.00% 0.00%

Table II. Comparison of classification accuracy: SVM, CART and the proposed model (P. model)

Page 18: Computational model for artificial learning using formal concept analysis

18

Experimental Results And Discussions (4)

Table III. Comparison of classification accuracy: SVM, CART and the proposed model (P. model) : misclassified assigned to majority class

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Dataset Correct Accuracy Incorrect Accuracy

SVM CART P. model SVM CART P. model

monk1 66.20% 83.33% 100.0% 33.80% 16.67% 0.00%

monk2 63.19% 61.11% 76.39% 36.81% 38.89% 23.61%

monk3 78.70% 97.22% 87.27% 21.30% 2.78% 12.73%

D1 100.0% 85.00% 100.0% 0.00% 15.00% 0.00%

D2 100.0% 100.0% 100.0% 0.00% 0.00% 0.00%

Page 19: Computational model for artificial learning using formal concept analysis

19

Experimental Results And Discussions (5)

Table IV. Comparison of performance indices for SVM, CART and the proposed model for monk1

Table V. Comparison of performance indices for SVM, CART and the proposed model for monk2

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

TP TN FP FN Sen. Spe. PP NP FM

P. model 216 216 0 0 100% 100% 100% 100% 100%

SVM 137 149 67 79 63.43% 68.98% 67.16% 65.35% 65.24%

CART 168 192 24 48 77.78% 88.89% 87.50% 80.00% 82.35%

TP TN FP FN Sen. Spe. PP NP FM

P. model 244 86 56 46 84.14% 60.56% 81.33% 65.15% 82.71%

SVM 259 14 128 31 89.31% 9.86% 66.93% 31.11% 76.52%

CART 199 65 77 91 68.62% 45.77% 72.10% 41.67% 70.32%

Page 20: Computational model for artificial learning using formal concept analysis

20

Experimental Results And Discussions (6)

Table VI. Comparison of performance indices for SVM, CART and the proposed model for monk3

Table VII. Comparison of performance indices for SVM, CART and the proposed model for inflammation of urinary bladder

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

TP TN FP FN Sen. Spe. PP NP FM

P. model 199 179 49 5 97.55% 78.51% 80.24% 97.28% 88.05%

SVM 157 183 45 47 76.96% 80.26% 77.72% 79.57% 77.34%

CART 204 216 12 0 100% 94.74% 94.44% 100% 97.14%

TP TN FP FN Sen. Spe. PP NP FM

P. model 23 17 0 0 100% 100% 100% 100% 100%

SVM 23 17 0 0 100% 100% 100% 100% 100%

CART 17 17 0 6 73.91% 100% 100% 73.91%% 85.00%

Page 21: Computational model for artificial learning using formal concept analysis

21

Experimental Results And Discussions (7)

Table VIII. Comparison of performance indices for SVM, CART and the proposed model for D2

ROC curve is a graphical plot that illustrates the performance of a binary classifier system.

ROC is created by plotting the fraction of true positives out of the positives (sensitivity) vs. the fraction of false positives out of the negatives (1-specificity)

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

TP TN FP FN Sen. Spe. PP NP FM

P. model 17 23 0 0 100% 100% 100% 100% 100%

SVM 17 23 0 0 100% 100% 100% 100% 100%

CART 17 23 0 0 100% 100% 100% 100% 100%

Page 22: Computational model for artificial learning using formal concept analysis

22

Experimental Results And Discussions (8)

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

ROC curve for Monk1 ROC curve for Monk2

Page 23: Computational model for artificial learning using formal concept analysis

23

Experimental Results And Discussions (9)

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

ROC curve for Monk3 ROC curve for D1

Page 24: Computational model for artificial learning using formal concept analysis

24

Experimental Results And Discussions (10)

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

ROC curve for D2

Page 25: Computational model for artificial learning using formal concept analysis

25

Conclusion

8th International Conference on Computer Engineering and Systems (ICCES’2013), EGYPT

Artificial learning is concerned with the classification learning that is a supervised learning algorithm embodied in the human mind.

Proposed a computational model for classification learning process which is described in terms of formal concept analysis (FCA).

The proposed model characterizes each class and predict the class label of a new object.

The performance of the proposed model has been evaluated for the real world data which led to get on classification rules from the training data that enable us from predicting the outcome of unseen data in a test set.

The proposed model has superior performance comparing with CART and SVM.

Page 26: Computational model for artificial learning using formal concept analysis

26

Thank you

http://www.egyptscience.net

8th International Symposium Advances in Artificial Intelligence and Applications (AAIA'13)