Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Results
References
All Topics
Computer Science
Artificial Intelligence

A fuzzy-genetic approach to breast cancer diagnosis

Profile image of Carlos AndresCarlos Andres

1999, Artificial Intelligence in Medicine

Abstract

The automatic diagnosis of breast cancer is an important, real-world medical problem. In this paper we focus on the Wisconsin breast cancer diagnosis (WBCD) problem, combining two methodologies-fuzzy systems and evolutionary algorithms -so as to automatically produce diagnostic systems. We find that our fuzzy-genetic approach produces systems exhibiting two prime characteristics: first, they attain high classification performance (the best shown to date), with the possibility of attributing a confidence measure to the output diagnosis; second, the resulting systems involve a few simple rules, and are therefore (human-) interpretable. (C.A. Peñ a-Reyes), moshe.sipper@di.epfl.ch (M. Sipper) 0933-3657/99/$ -see front matter © 1999 Elsevier Science B.V. All rights reserved. PII: S 0 9 3 3 -3 6 5 7 ( 9 9 ) 0 0 0 1 9 -6 C.A. Peña-Reyes, M. Sipper / Artificial Intelligence in Medicine 17 (1999) 131-155 132

Figures (15)
Fig. 1. Example of a fuzzy variable with two possible fuzzy values labeled Low and High, and orthogonal membership functions, plotted above as degree of membership versus input values. P and d define the start point and the length of membership function edges, respectively. The orthogonality condition means that the sum of all membership functions at any point is one. In the figure, an example value wu is assigned the membership values ,y(u) = 0.8 and Myign(u) = 0.2 (as can be seen py 54(u) + Lipign(U) = 1).
Fig. 1. Example of a fuzzy variable with two possible fuzzy values labeled Low and High, and orthogonal membership functions, plotted above as degree of membership versus input values. P and d define the start point and the length of membership function edges, respectively. The orthogonality condition means that the sum of all membership functions at any point is one. In the figure, an example value wu is assigned the membership values ,y(u) = 0.8 and Myign(u) = 0.2 (as can be seen py 54(u) + Lipign(U) = 1).
Fig. 2. Basic structure of a fuzzy inference system. A fuzzy inference system is a rule-based system that uses fuzzy logic, rather than Boolean logic, to reason about data [33]. Its basic structure includes four main components, as depicted in Fig. 2: (1) a fuzzifier, which translates crisp (real-valued) inputs into fuzzy values; (2) an inference engine that applies a fuzzy reasoning mechanism to obtain a fuzzy output; (3) a defuzzifier, which translates this latter output into a crisp value; and (4) a knowledge base, which contains both an
Fig. 2. Basic structure of a fuzzy inference system. A fuzzy inference system is a rule-based system that uses fuzzy logic, rather than Boolean logic, to reason about data [33]. Its basic structure includes four main components, as depicted in Fig. 2: (1) a fuzzifier, which translates crisp (real-valued) inputs into fuzzy values; (2) an inference engine that applies a fuzzy reasoning mechanism to obtain a fuzzy output; (3) a defuzzifier, which translates this latter output into a crisp value; and (4) a knowledge base, which contains both an
Parameter classification of fuzzy inference systems Table 1 ensemble of fuzzy rules, known as the rule base, and an ensemble of membership functions, known as the database.
Parameter classification of fuzzy inference systems Table 1 ensemble of fuzzy rules, known as the rule base, and an ensemble of membership functions, known as the database.
Fig. 4. Proposed diagnosis system. Note that the fuzzy subsystem displayed to the left is in fact the entire fuzzy inference system of Fig. 2.
Fig. 4. Proposed diagnosis system. Note that the fuzzy subsystem displayed to the left is in fact the entire fuzzy inference system of Fig. 2.
Parameters encoding of an individual’s genome* * Total genome length is 54+18N,, where N, denotes the number of rules (JN, is set a priori to a value between | and 5, and is fixed during the genetic algorithm run). Table 2
Parameters encoding of an individual’s genome* * Total genome length is 54+18N,, where N, denotes the number of rules (JN, is set a priori to a value between | and 5, and is fixed during the genetic algorithm run). Table 2
Fig. 5. Example of a genome for a single-rule system, (a) Genome encoding. The first 18 positions encode the parameters P and d for the nine variables v,-vo. The rest encode the membership function applicable for the nine antecedents of the rule; (b) Interpretation. Database and rule base of the single-rule system encoded by (a). The parameters P and d are interpreted as illustrated in Fig. 1. To evolve the fuzzy inference system, we used a genetic algorithm with a fixed population size of 200 individuals, and fitness-proportionate selection (Section 1.3). The algorithm terminates when the maximum number of generations, G,,,, 1S reached (we set Gyax = 2000 + SO0(N,, i.e. dependent on the number of rules used
Fig. 5. Example of a genome for a single-rule system, (a) Genome encoding. The first 18 positions encode the parameters P and d for the nine variables v,-vo. The rest encode the membership function applicable for the nine antecedents of the rule; (b) Interpretation. Database and rule base of the single-rule system encoded by (a). The parameters P and d are interpreted as illustrated in Fig. 1. To evolve the fuzzy inference system, we used a genetic algorithm with a fixed population size of 200 individuals, and fitness-proportionate selection (Section 1.3). The algorithm terminates when the maximum number of generations, G,,,, 1S reached (we set Gyax = 2000 + SO0(N,, i.e. dependent on the number of rules used
Summary of results of 120 evolutionary runs, divided according to the three experimental categories discussed in the text (i.e. the three classes which differ in the training-set to test-set ratio)* * The table lists the average performance over all 120 runs, where the averaging is done over the best individual of each run. The performance value denotes the percentage of cases correctly classified. Three such performance values are shown, (1) performance over the training set; (2) performance over the test set; and (3) overall performance, considering the entire database. In addition, the average number of variables per rule is also shown.
Summary of results of 120 evolutionary runs, divided according to the three experimental categories discussed in the text (i.e. the three classes which differ in the training-set to test-set ratio)* * The table lists the average performance over all 120 runs, where the averaging is done over the best individual of each run. The performance value denotes the percentage of cases correctly classified. Three such performance values are shown, (1) performance over the training set; (2) performance over the test set; and (3) overall performance, considering the entire database. In addition, the average number of variables per rule is also shown.
Fig. 6. Summary of results of 120 evolutionary runs. The histogram depicts the number of systems exhibiting a given performance level at the end of the evolutionary run. The performance considered is that of the best individual of the run, measured as the overall percentage of correctly classified cases over the entire database.
Fig. 6. Summary of results of 120 evolutionary runs. The histogram depicts the number of systems exhibiting a given performance level at the end of the evolutionary run. The performance considered is that of the best individual of the run, measured as the overall percentage of correctly classified cases over the entire database.
* The first three approaches—those of Setiono [27], Setiono and Liu [28], and Taha and Ghosh [30]—involve Boolean rule bases extracted from trained neural networks; the last approach is our own previous work [25]. Shown above are the classification performance values of the top systems obtained by these approaches, along with the average number of variables-per-rule given in parentheses. Results are divided into five classes, in accordance with the number of rules-per-system, going from one-rule systems to five-rule ones. > Note that Taha and Ghosh [30] obtained slightly better results for the five-rules case by directly using their trained neural networks, rather than the extracted rule-haced eveteme Herein anr interect liew with thece latter riule-haced eveteme Comparison of the best systems evolved by our approach with the top systems obtained by four other rule-based diagnostic approaches*
* The first three approaches—those of Setiono [27], Setiono and Liu [28], and Taha and Ghosh [30]—involve Boolean rule bases extracted from trained neural networks; the last approach is our own previous work [25]. Shown above are the classification performance values of the top systems obtained by these approaches, along with the average number of variables-per-rule given in parentheses. Results are divided into five classes, in accordance with the number of rules-per-system, going from one-rule systems to five-rule ones. > Note that Taha and Ghosh [30] obtained slightly better results for the five-rules case by directly using their trained neural networks, rather than the extracted rule-haced eveteme Herein anr interect liew with thece latter riule-haced eveteme Comparison of the best systems evolved by our approach with the top systems obtained by four other rule-based diagnostic approaches*
This completes the fuzzification phase (the ‘fuzzifier’ unit of Fig. 2). Having computed these membership values, the inference engine (Fig. 2) can now go on to compute the so-called truth value of each rule. This truth value is computed by applying the fuzzy ‘and’ operator (Section 1.2) to combine the antecedent clauses (the membership values) in a fuzzy manner; this results in the output truth value, namely, a continuous value which represents the rule’s degree of activation. Thus, a rule is not merely either activated or not, but in fact is activated to a certain degree represented by a value between 0 and 1. In our example, the rule activation values are as follows (remember that we ‘chucked out’ rule 2, since it was found to never fire): The membership value of each variable is then computed in accordance with the (evolved) database of Fig. 7:
This completes the fuzzification phase (the ‘fuzzifier’ unit of Fig. 2). Having computed these membership values, the inference engine (Fig. 2) can now go on to compute the so-called truth value of each rule. This truth value is computed by applying the fuzzy ‘and’ operator (Section 1.2) to combine the antecedent clauses (the membership values) in a fuzzy manner; this results in the output truth value, namely, a continuous value which represents the rule’s degree of activation. Thus, a rule is not merely either activated or not, but in fact is activated to a certain degree represented by a value between 0 and 1. In our example, the rule activation values are as follows (remember that we ‘chucked out’ rule 2, since it was found to never fire): The membership value of each variable is then computed in accordance with the (evolved) database of Fig. 7:
To gain an intuitive understanding of how a classification value is computed, let us sketch a simple example. Referring to the system of Fig. 4, assume that the following values are presented as inputs (these represent case # 145 of the WBCD database):
To gain an intuitive understanding of how a classification value is computed, let us sketch a simple example. Referring to the system of Fig. 4, assume that the following values are presented as inputs (these represent case # 145 of the WBCD database):
* Results are divided into five classes, in accordance with the number of rules-per-system, going from three-rule systems to seven-rule ones. We performed 5-7 runs per class, totaling 31 runs in all; shown above are the resulting best systems as well as the average per class. Results include the overall classification performance and the average number of variables-per-rule in parentheses. Results of evolutionary runs in which the variables-per-rule constraint has been removed*
* Results are divided into five classes, in accordance with the number of rules-per-system, going from three-rule systems to seven-rule ones. We performed 5-7 runs per class, totaling 31 runs in all; shown above are the resulting best systems as well as the average per class. Results include the overall classification performance and the average number of variables-per-rule in parentheses. Results of evolutionary runs in which the variables-per-rule constraint has been removed*
Results of evolutionary runs in which the default diagnosis is benign (rather than malignant)* * Results are divided into five classes, in accordance with the number of rules-per-system, going fron one-rule systems to five-rule ones. We performed 4-6 runs per class, totaling 27 runs in all; shown abov are the resulting best systems as well as the average per class. Results include the overall classificatior performance and the average number of variables-per-rule in parentheses. Note that we slightly modifiec the genomic representation (Section 4.2), such that if consequents are malignant, and the else consequen is benign. Table 6
Results of evolutionary runs in which the default diagnosis is benign (rather than malignant)* * Results are divided into five classes, in accordance with the number of rules-per-system, going fron one-rule systems to five-rule ones. We performed 4-6 runs per class, totaling 27 runs in all; shown abov are the resulting best systems as well as the average per class. Results include the overall classificatior performance and the average number of variables-per-rule in parentheses. Note that we slightly modifiec the genomic representation (Section 4.2), such that if consequents are malignant, and the else consequen is benign. Table 6
Summary of top 45 evolutionary runs (of 120) described in Section 5.1, divided according to the three experimental categories discussed in the text (i.e. the three classes whicl differ in the training-set to test-set ratio)* * For each of the 45 evolved systems, the table lists its fitness value, its performance, and its average number of variables-per-rule. As explained in Section 5.1, the performance value denotes the percentage of cases correctly classified. Three such performance values are shown, (1) performance over the training set; (2) performance over the test set; and 3) overall performance, considering the entire database.
Summary of top 45 evolutionary runs (of 120) described in Section 5.1, divided according to the three experimental categories discussed in the text (i.e. the three classes whicl differ in the training-set to test-set ratio)* * For each of the 45 evolved systems, the table lists its fitness value, its performance, and its average number of variables-per-rule. As explained in Section 5.1, the performance value denotes the percentage of cases correctly classified. Three such performance values are shown, (1) performance over the training set; (2) performance over the test set; and 3) overall performance, considering the entire database.

Related papers

Using a genetic-fuzzy algorithm as a computer aided diagnosis tool on Saudi Arabian breast cancer database
Fairouz Tchier

Mathematical biosciences, 2017

The computer-aided diagnosis has become one of the major research topics in medical diagnostics. In this research paper, we focus on designing an automated computer diagnosis by combining two major methodologies, namely the fuzzy base systems and the evolutionary genetic algorithms and applying them to the Saudi Arabian breast cancer diagnosis database, to be employed for assisting physicians in the early detection of breast cancers, and hence obtaining an early-computerized diagnosis complementary to that by physicians. Our hybrid algorithm, the genetic-fuzzy algorithm, has produced optimized diagnosis systems that attain high classification performance, in fact, our best three rule system obtained a 97% accuracy, with simple and well interpretive rules, and with a good degree of confidence of 91%.

View PDFchevron_right
Using a GeneticFuzzy Algorithm as a Computer Aided Breast Cancer Diagnostic Tool
abir alharbi

PubMed, 2016

Computeraided diagnosis of breast cancer is an important medical approach. In this research paper, we focus on combining two major methodologies, namely fuzzy base systems and the evolutionary genetic algorithms and on applying them to the Saudi Arabian breast cancer diagnosis database, to aid physicians in obtaining an earlycomputerized diagnosis and hence prevent the development of cancer through identification and removal or treatment of premalignant abnormalities; early detection can also improve survival and decrease mortality by detecting cancer at an early stage when treatment is more effective. Our hybrid algorithm, the geneticfuzzy algorithm, has produced optimized systems that attain high classification performance, with simple and readily interpreted rules and with a good degree of confidence.

View PDFchevron_right
Breast Cancer Diagnosis Based on Genetic-fuzzy Logic and ANFIS Using WBCD
Khaled Hosny

International Journal of Fuzzy Logic Systems, 2020

Breast cancer is conspicuously one of the most common diseases that cause death for women. Besides, it is increasing with high rates. Consequently, Breast Cancer must be discovered in early stages to avoid death or losing part of the body due to late diagnosis. Thus, there are many researches for computerizing breast cancer diagnosis with different techniques. It reduces human decision rate in order to decrease the mortality rate through the disease. Therefore, we have a major motivation for this highly significant work. The primary focus of the research is to produce a multi-model that can predict the diagnosis whether benign (noncancerous) or malignant (cancerous) nature of a tumor with high accuracy using two methods. The first method is a combining of two major methodologies, namely the fuzzy based systems and the evolutionary genetic algorithms (GFIS). The second method intends to an integrated view of implementing an adaptive neuro-fuzzy inference system (ANFIS) with feature selection using principle component analysis (PCA). Wisconsin breast cancer database (WBCD) is applied because it contained records of patients with known diagnosis. The proposed target of this research compares breast cancer diagnosis based on physical characteristics of the tumour between GFIS and ANFIS. GFIS has achieved a high performance with 97.7% however ANFIF has achieved the highest accuracy with 99.1%.

View PDFchevron_right
A Hybrid Artificial Immune Genetic Algorithm with Fuzzy Rules for Breast Cancer Diagnosis
Mohamed Osama

2008

The automatic diagnosis of breast cancer is an important, real-world medical problem. In this paper we give an introduction to fuzzy systems, genetic algorithms and artificial immune system, and then we introduce a hybrid algorithm that gathers the genetic algorithms with the artificial immune system in one algorithm. The genetic algorithm, the artificial immune system and the hybrid algorithm were implemented and tested on the Wisconsin breast cancer diagnosis (WBCD) problem in order to generate a fuzzy rule system for breast cancer diagnosis. The hybrid algorithm generated a fuzzy system which reached the maximum classification ratio earlier than the two other ones. The motivations of using fuzzy rules incorporate with evolutionary algorithms in the underline problem are attaining high classification performance with the possibility of attributing a confidence measure (degree of benignity or malignancy) to the output diagnosis beside the simplicity of the diagnosis system which means that the system is human interpretable.

View PDFchevron_right
Fuzzy relational model and genetic algorithms for early detection and diagnosis of breast cancer in Saudi Arabia
abir alharbi

Filomat, 2016

Breast Cancer (BC) is considered as the most implacable malignancy and the leading cause of mortality among women in general and in Saudi Arabia specially. Most of the previous work in Saudi Arabia on this subject was on epidemiology, knowledge of (BC) and practice of breast self-examination (BSE), etiological factors, metastases and rate of survival. Early detection and diagnosis of Breast Cancer (BC) is an important, real-world medical problem. In this paper, we propose a soft computing methodology to build a Breast Cancer (BC) diagnosis system with high capabilities as described by Andres et al. [4] but on the Saudi Arabian breast cancer dataset and using a simplified fitness function. We focus on combining fuzzy concepts and genetic algorithms so as to automatically produce diagnostic systems to support and assist the expert to understand and evaluate its results with high classification performance.

View PDFchevron_right
A Computational Approach for Better Classification of Breast Cancer using GeneticAlgorithm
Dr. Prakash Bethapudi

International Journal of Advanced Trends in Computer Science and Engineering

The proposed work presents a competent diagnosis technique in classifying benign and malignant breast cancer cases using Genetic Algorithm. The breast cancer dataset (Wisconsin Breast Cancer (WBC)) was taken fromUCI Machine Learning Repository, center for machine learning and intelligence systems. Using the proposed Genetic algorithmbased on 3-fold cross validation method, and executing on multiple rules, we obtained preeminent classification accuracy of 97.7% which classified more accurately when compared with the other existing systems. The experimental outcomesillustrate that the categorization using genetic algorithm is loftier to the other classifiers which used WBC dataset. All experiments are carried out on MATLAB.

View PDFchevron_right
Diagnosing Breast Cancer with the Aid of Fuzzy Logic Based on Data Mining of a Genetic Algorithm in Infrared Images
Mohammad Mohammad-zadeh

2012

Background: Breast cancer is one of the most prevalent cancers among women today. The importance of breast cancer screening, its role in the timely identification of patients, and the reduction in treatment expenses are considered to be among the highest sanitary priorities of a modern country. Thermal imaging clearly possesses a special role in this stage due to rapid diagnosis and use of harmless rays.

View PDFchevron_right
A Fuzzy-ACO Method for Detect Breast Cancer
amin einipour

Global Journal of Health Science, 2011

Data mining usually means the methodologies and tools for the efficient new knowledge discovery from databases. It is also a form of knowledge discovery essential for solving problems in a specific domain. For instance, the data mining approaches are applied in the filed of medical diagnosis recently. A major class of problems in medical science involves the diagnosis of disease, based upon various tests performed upon the patient. When several tests are involved, the ultimate diagnosis may be difficult to obtain, even for a medical expert. This has given rise, over the past few decades, to computerized diagnostic tools, intended to aid the physician in making sense out of the welter of data. Specifically, where breast cancer is concerned, the treating physician is interested in ascertaining whether the patient under examination exhibits the symptoms of a benign case, or whether her case is a malignant one. In this paper, we have focused on breast cancer diagnosis by combination of fuzzy systems and evolutionary algorithms. Fuzzy rules are desirable because of their interpretability by human experts. Ant colony algorithm is employed as evolutionary algorithm to optimize the obtained set of fuzzy rules. Results on breast cancer diagnosis data set from UCI machine learning repository show that the proposed approach would be capable of classifying cancer instances with high accuracy rate in addition to adequate interpretability of extracted rules.

View PDFchevron_right

References (33)

  1. Alander JT. An indexed bibliography of genetic algorithms with fuzzy logic. In: Pedrycz W, editor. Fuzzy Evolutionary Computation. Dordrecht: Kluwer, 1997:299 -318.
  2. Bellazzi R, Ironi L, Guglielmann R, Stefanelli M. Qualitative models and fuzzy systems: an integrated approach for learning from data. Artif Intell Med 1998;14(1 -2):5 -28.
  3. Bennett KP, Mangasarian OL. Neural network training via linear programming. In: Pardalos PM, editor. Advances in Optimization and Parallel Computing. Elsevier, 1992:56 -7.
  4. Cordon O, Herrera F, Lozano M. On the combination of fuzzy logic and evolutionary computa- tion: a short review and bibliography. In: Pedrycz W, editor. Fuzzy Evolutionary Computation. Kluwer, 1997:33-56.
  5. Espinosa JJ, Vandewalle J. Constructing fuzzy models with linguistic integrity. IEEE Transactions on Fuzzy Systems 1999, submitted for publication.
  6. Fogel DB. Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. Piscataway, NJ: IEEE Press, 1995.
  7. Fogel DB, Wasson III EC, Boughton EM, Porto VW. Evolving artificial neural networks for screening features from mammograms. Artif Intell Med 1998;14(3):317.
  8. Fukuda T, Shimojima K. Fusion of fuzzy, NN, GA to the intelligent robotics. Proceedings of the 1995 IEEE International Conference on Systems, Man and Cybernetics, Vol. 3. IEEE, 1995:2892 - 2897.
  9. Heider H, Drabe T. Fuzzy system design with a cascaded genetic algorithm. Proceedings of 1997 IEEE International Conference on Evolutionary Computation. IEEE and IEEE Neural Network Council and Evolutionary Programming Society, 1997:585 -588.
  10. Herrera F, Lozano M, Verdegay JL. Generating fuzzy rules from examples using genetic al- gorithms. In: Bouchon-Meunier B, Yager RR, Zadeh LA, editors. Fuzzy Logic and Soft Comput- ing. World Scientific, 1995:11-20.
  11. Jang J-S R, Sun C-T. Neuro-fuzzy modeling and control. Proceedings of the IEEE. 1995 83 (3):378-406.
  12. Karr CL. Genetic algorithms for fuzzy controllers. AI Expert 1991;6(2):26 -33.
  13. Karr CL, Freeman LM, Meredith DL. Improved fuzzy process control of spacecraft terminal rendezvous using a genetic algorithm. In: Rodriguez G, editor. Proceedings of Intelligent Control and Adaptive Systems Conference, Vol. 1196. SPIE, 1990:274 -288.
  14. Kovalerchuk B, Triantaphyllou E, Ruiz JF, Clayton J. Fuzzy logic in computer-aided breast cancer diagnosis: analysis of lobulation. Artif Intell Med 1997;11(1):75 -85.
  15. Koza JR. Genetic Programming. Cambridge, MA: MIT Press, 1992.
  16. Lee K-M, Kwak D-H, Lee-Kwang H. Fuzzy inference neural network for fuzzy model tuning. IEEE Trans Syst Man Cybern 1996;26(4):637-45.
  17. Lee MA, Takagi H. Integrating design stages of fuzzy systems using genetic algorithms. 1993 IEEE International Conference on Fuzzy Systems. IEEE, 1993:612 -617.
  18. Lin C-T, Lee CSG. Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems. IEEE Trans Fuzzy Syst 1994;2(1):46 -63.
  19. Mangasarian OL, Setiono R, Goldberg W-H. Pattern recognition via linear programming: Theory and application to medical diagnosis. In: Coleman TF, Li Y, editors. Large-Scale Numerical Optimization. SIAM, 1990:22-31.
  20. Mangasarian OL, Street WN, Wolberg WH. Breast cancer diagnosis and prognosis via linear programming. Mathematical Programming Technical Report 94-10, University of Wisconsin, 1994.
  21. Mendel JM. Fuzzy logic systems for engineering: a tutorial. Proceedings of the IEEE, 83(3):345-377, 1995.
  22. Merz CJ, Murphy PM. UCI repository of machine learning databases. http://www.ics.uci.edu/ mlearn/MLRepository.html, 1996.
  23. Michalewicz Z. Genetic Algorithms + Data Structures=Evolution Programs, 3rd edition. Heidel- berg: Springer-Verlag, 1996.
  24. Nawa NE, Hashiyama T, Furuhashi T, Uchikawa Y. A study on fuzzy rules discovery using pseudo-bacterial genetic algorithm with adaptive operator. Proceedings of 1997 IEEE International Conference on Evolutionary Computation. IEEE and IEEE Neural Network Council and Evolu- tionary Programming Society, 1997.
  25. Pen ˜a-Reyes CA, Sipper M. Evolving fuzzy rules for breast cancer diagnosis. Proceedings of 1998 International Symposium on Nonlinear Theory and Applications (NOLTA'98), Vol. 2. Lausanne: Presses Polytechniques et Universitaires Romandes, 1998:369 -372.
  26. Pedrycz W, Valente de Oliveira J. Optimization of fuzzy models. IEEE Trans Syst Man Cybern 1996;26(4):627-36.
  27. Setiono R. Extracting rules from pruned neural networks for breast cancer diagnosis. Artificial Intelligence in Medicine 1996:37-51.
  28. Setiono R, Liu H. Symbolic representation of neural networks. IEEE Computer 1996;29(3):71 -7.
  29. Sierra B, Larranaga P. Predicting survival in malignant skin melanoma using Bayesian networks automatically induced by genetic algorithms. An empirical comparison between different ap- proaches. Artif Intell Med 1998;14(1-2):215 -36.
  30. Taha I, Ghosh J. Evaluation and ordering of rules extracted from feedforward networks. Proceed- ings of the IEEE International Conference on Neural Networks. 1997:221 -226.
  31. Vuorimaa P. Fuzzy self-organizing map. Fuzzy Sets Syst 1994;66:223 -31.
  32. Yager RR, Filev DP. Essentials of Fuzzy Modeling and Control. Wiley, 1994.
  33. Yager RR, Zadeh LA. Fuzzy Sets, Neural Networks, and Soft Computing. New York: Van Nostrand Reinhold, 1994. .

Related papers

Designing breast cancer diagnostic systems via a hybrid fuzzy-genetic methodology
carlos reyes

1999

The automatic diagnosis of breast cancer is an important, real-world medical problem. In the paper we focus on the Wisconsin breast cancer diagnosis (WBCD) problem, combining two methodologies-fuzzy systems and evolutionary algorithms-so as to automatically produce diagnostic systems. We find that our fuzzy-genetic approach produces systems exhibiting the highest classification performance shown to date, and which are also (human-)interpretable.

View PDFchevron_right
A Fuzzy-Genetic Algorithm Method for the Breast Cancer Diagnosis Problem
abir alharbi

2015

The computer-aided medical diagnosis of complex systems, such as breast cancer is an important medical problem. In this paper, we focus on combining two major methodologies, namely, the fuzzy-based systems and the evolutionary genetic algorithms to find a computer aided diagnosis system that will aid physicians in an early diagnosis of breast cancer in Saudi Arabia. Our results show that the fuzzy-genetics approach produces systems that attain high classification performance, with simple and well interpretive rules and a good degree of

View PDFchevron_right
Breast Cancer Diagnosis Using Genetic Fuzzy Rule Based System
Noor K Ayoob

Breast cancer diagnosis (WBCD) is an important, real-world medical problem. There are different artificial Intelligence techniques try to classify WBCD to help to minimize the errors that might occur when the doctors do not have adequate experience or because of stress . In this work , fuzzy genetic tool is used to present diagnostic system that classify WBCD cases automatically .The system provides two prime features: first, it attain high classification performance ; second, the resulting system consists of a few simple rules, and are therefore interpretable.

View PDFchevron_right
Improved Genetic-Fuzzy System For Breast Cancer Diagnosis
D. Devaraj

Breast cancer diagnosis is an important real world medical problem. Fuzzy Rule Based System (FRBS) has been successfully applied to many medical diagnosis problems. An important issue in the design of FRBS is the formation of fuzzy if-then rules and membership functions. This paper presents a Improved Genetic Algorithm (IGA) approach to obtain the optimal rule set and the membership function. Advanced genetic operators are applied to improve the performance of the GA in designing the fuzzy classifier. The performance of the proposed approach is demonstrated using Wisconsin breast cancer data available in the UCI machine learning repository. From the simulation study, it is found that the proposed IGFRBS produces a fuzzy diagnostic system, which has minimum number of rules and whose classification accuracy is better than the results reported in the literature.

View PDFchevron_right
Evolving Fuzzy Rules for Breast Cancer Diagnosis
Carlos Peña

1998

Abstract| We present an evolutionary approach for discovering fuzzy systems for breast cancer diagnosis. By judiciously designing an appropriate representation scheme (genome) and tness function, the genetic algorithm is then able to produce successful systems. These surpass the best known systems to date in terms of combined performance and simplicity.

View PDFchevron_right

Related topics

  • Engineering
  • Genetics
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence in Medicine
  • Evolutionary Algorithm
  • Fuzzy System
  • Breast Cancer Diagnosis
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved