[۷۵] B. Al-Kazemi and C. Mohan, “Discrete multi-phase particle swarm optimization,” in Information Processing with Evolutionary Algorithms, ed: Springer, 2005, pp. 305-327.
[۷۶] L. I. Kuncheva, “Combining classifiers: Soft computing solutions,” Pattern Recognition: From Classical to Modern Approaches, pp. 427-451, 2001.
[۷۷] H. Ishibuchi, et al., Classification and modeling with linguistic information granules: advanced approaches advanced approaches to linguistic data mining: Springer, 2005.
[۷۸] F. Herrera, “Genetic fuzzy systems: taxonomy, current research trends and prospects,” Evolutionary Intelligence, vol. 1, pp. 27-46, 2008.
[۷۹] H. Roubos and M. Setnes, “Compact and transparent fuzzy models and classifiers through iterative complexity reduction,” Fuzzy Systems, IEEE Transactions on, vol. 9, pp. 516-524, 2001.
[۸۰] M. A. Kbir, et al., “Hierarchical fuzzy partition for pattern classification with fuzzy if-then rules,” Pattern Recognition Letters, vol. 21, pp. 503-509, 2000.
[۸۱] P. Jaganathan, et al., “Classification rule discovery with ant colony optimization and improved Quick Reduct algorithm,” IAENG International Journal of Computer Science, vol. 33, pp. 50-55, 2007.
[۸۲] M. S. Abadeh, et al., “Induction of Fuzzy Classification systems via evolutionary ACO-based algorithms,” computer, vol. 35, p. 37, 2008.
[۸۳] K. Nozaki, et al., “Adaptive fuzzy rule-based classification systems,” Fuzzy Systems, IEEE Transactions on, vol. 4, pp. 238-250, 1996.
[۸۴] H. Ishibuchi, et al., “Voting in fuzzy rule-based systems for pattern classification problems,” Fuzzy Sets and Systems, vol. 103, pp. 223-238, 1999.
[۸۵] J. Han, et al., Data mining: concepts and techniques: Morgan kaufmann, 2006.
[۸۶] L. A. Zadeh, “Fuzzy sets,” Information and control, vol. 8, pp. 338-353, 1965.
[۸۷] M. F. Ganji and M. S. Abadeh, “Using fuzzy ant colony optimization for diagnosis of diabetes disease,” in Electrical Engineering (ICEE), 2010 18th Iranian Conference on, 2010, pp. 501-505.
[۸۸] C. Zhou, et al., “Evolving accurate and compact classification rules with gene expression programming,” Evolutionary Computation, IEEE Transactions on, vol. 7, pp. 519-531, 2003.
[۸۹] C. Merz, et al., “UCI repository of machine learning databases ” in , ed. University of California, Department of Information and Computer Science, Irvine, CA, 1996.

Abstract

Diagnosis of Diabetes disease or understand the high risk of developing diabetes is not often an easy task. As many of the diabetes’ symptoms are occurring in other diseases. Analyzing many factors to diagnose a disease of a patient makes the physician’s job more difficult to detect. A physician commonly makes decision by evaluating the current test results of a patient, and according to the previous decisions he has made on other patients with the same condition.
In this thesis, a rule based classifier algorithm has been used to classify the diabetics. Particle Swarm Optimization (PSO) has been used for extracting fuzzy rules and parameters for creating appropriate fuzzy membership functions. The proposed PSO has characteristics that are different from other PSO based algorithms, such as swarm diversity enhanced function and simultaneous evolve of membership functions and fuzzy rules. Proposed fuzzy system evaluated on Pima diabetes data set regarding to classification accuracy, sensitivity and specificity values. The obtained classification accuracy is 84.32% that outperforms several famous and recent methods in classification accuracy for diabetes disease diagnosis. Also, simulation results shows that proposed PSO based method for creating a fuzzy classifier has a compact fuzzy rule base that increases the interpretation ability of algorithm.

Keywords:

Diabetes disease detection, rule-based classifier, PSO, membership functions and fuzzy rules simultaneous evolving.

Ministry of Science, Reasrch and Technology
Mazandaran University of Science and Technology
In Partial Fulfillment of the Requirement for the degree of
Master of Science in
Information Technology Engineering
Title:
Designing a Fuzzy Classifier by a PSO-Based Approach for Diagnosis of Diabetes Diseases
Supervisor:
Dr Javad Vahidi
Advisor:
Dr Homayun Motameni
By:
Hossein Mahdian
(Winter 2014)

1. 1. Artificial Neural Networks (ANN) ↑

1. 1. decision trees ↑

1. 1. k-nearest neighbors (K-NN) ↑

1. 1. Support Vector Machine (SVM) ↑

1. 1. Feed-forward neural networks ↑

1. 1. Recurrent neural networks ↑

1. 1. Multi-Layer Perceptron ↑

1. 1. back-propagation ↑

1. 1. Particle Swarm Intelligence ↑

1. 1. Kernel Methods ↑

1. 1. Vapnik ↑

1. 1. maximum margin ↑

1. Support Vevtor ↑