Indian Journal of Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Design and Identify Tubercle Bacilli Diagnosis System with TSK-type Neuro Fuzzy Controllers


Affiliations
1 Department of Electrical Engineering, National Chiao Tung University, Taiwan, Province of China
 

This paper proposes a TSK-type Neuro Fuzzy Controllers (TFC) with a group interaction-based evolutionary algorithm (GIEA) for constructing the tubercle bacilli diagnosis system (TBDS). The proposed GIEA is designed basing on symbiotic evolution which each chromosome in the population represents only partial solution. The whole solution consists of several chromosomes. The GIEA is different from the traditional symbiotic evolution. Each population in the GIEA is divided into several groups. Each group represents a set of the chromosomes that belong to only one fuzzy rule. Moreover, in the GIEA,the interaction ability is considered that the chromosomes will interact with other groups to generate the better chromosomes by elites-base interaction crossover strategy (EICS). In the TBDS, the EICS is used to train the TBDS. After trained by the EICS, the TBDS can diagnose the visible tubercle bacilli. The performance of the GIEA achieves better than other existing models in tubercle bacilli.

Keywords

Neuro Fuzzy Controllers, Tubercle Bacilli, Symbiotic Evolution, Reinforcement Learning
User

  • Karr CL (1991) Design of an adaptive fuzzy logic controller using a genetic algorithm. Proc. The Fourth Int. Conf. Genetic Algorithms. 450–457.

  • Lee M and Takagi H (1993) Integrating design stages of fuzzy systems using genetic algorithms. Proc. 2nd IEEE Int. Conf. Fuzzy Systems. 612-617.

  • Lin CT and Jou CP (2000) GA-based fuzzy reinforcement learning for control of a magnetic bearing system. IEEE Trans. Syst., Man, Cybern., Part B. 30(2), 276-289.

  • Juang CF, Lin JY and Lin CT (2000) Genetic reinforcement learning through symbiotic evolution for fuzzy controller design. IEEE Trans. Syst., Man, Cybern., Part B. 30(2), 290-302.

  • Tang KS (1996) Genetic algorithms in modeling and optimization. Ph.D. Dissertation. Dep. Electron. Eng., City Univ. Hong Kong.

  • Lin CJ and Hsu YC (2007) Reinforcement Hybrid Evolutionary Learning for Recurrent wavelet-based neuro-fuzzy controllers. IEEE Trans. Fuzzy Systs. 15(4), 729-745.

  • Levente FA, Razvan A and Catharine JC (2008) A.W. Sarah and S. Nicholas, A genetic algorithm optimized fuzzy neural network analysis of the affinity of inhibitors for HIV-1 protease. Bioorganic & Medicinal Chemistry. 16(6), 2903-2911.

  • Benamrane N, Aribi A and Kraoula L (2006) Fuzzy Neural Networks and Genetic Algorithms for Medical Images Interpretation. IEEE Proc. of the conf. on Geometric Modeling and Imaging: New Trends.

  • Wang S, Fu D, Xu M and Hu D (2007) Advanced fuzzy cellular neural network: Application to CT liver images. Artificial Intelligence in Medicine. 39(1), 65-77.

  • Jafar T, Afshar SJ and Muhammad AD (2012) A new method for position control of a 2-DOF robot arm using neuro–fuzzy controller. Indian J.Sci.Technol. 5(3), 2253-2257.

  • Forero M, Sroubek F and Cristobal G (2004) Identification of tuberculosis bacteria based on shape and color. Real-Time Imaging, 10(4), 251-262.

  • Ziehl-Neelsen stain, http://en.wikipedia.org/wiki/Ziehl-Neelsen_stain.

  • N. Otsu, A threshold selection method from gray-level histogram, IEEE Trans. on Systems, Man and Cybernetics, 9(1): 62-66, 1979.

  • Liu L and Sclaroff S (2001) Medical image segmentation and retrieval via deformable models,.Proc. IEEE Int. Conf. on Image Processing. 3, 1071-1074.

  • Takagi T and Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Systems Man Cybern. 15, 116-132.

  • Michalewicz Z (1999) Genetic Algorithms+Data Structures=Evolution Programs. New York: Springer-Verlag.

  • Tanese R (1989) Distributed genetic algorithm. Proc. Int. Conf. Genetic Algorithms. 434–439.

  • Arabas J, Michalewicz Z and Mulawka J (1994) GAVaPS-A genetic algorithm with varying population size. Proc. IEEE Int. Conf. Evolutionary Computation, Orlando. 73–78.

  • Moriarty DE and Miikkulainen R (1996) Efficient reinforcement learning through symbiotic evolution. Mach. Learn. 22, 11–32.

  • Smith SE, Forrest S and Perelson AS (1993) Searching for diverse, cooperative populations with genetic algorithms, Evol. Comput. 1(2), 127–149.

  • Cordon O, Herrera F, Hoffmann F and Magdalena L (2001) Genetic fuzzy systems evolutionary tuning and learning of fuzzy knowledge bases. Advances in Fuzzy Systems-Applications and Theory, NJ: World Scientific Publishing. 19.

  • Weaver JR and Au JL (1997) Application of automatic thresholding in image analysis scoring of cells in human solid tumors labeled for proliferation markers, Cytometry A. 29, 128-135.

  • Wu K, Gauthier D and Levine MD (1995) Live Cell Image Segmentation. IEEE Trans. on Biomedical Engineering. 42, 1-12.

  • Grefenstette JJ (1986) Optimization of control parameters for genetic algorithms. IEEE Trans. Syst. Man Cybern. 6(1) 122–128.

  • Gomez FJ (2003) Robust non-linear control through neuroevolution. Ph.D. Disseration, The University of Texas at Austin.

  • Lin CJ and Xu YJ (2006) A Self-Adaptive Neural Fuzzy Network with Group-Based Symbiotic Evolution and Its Prediction Applications, Fuzzy Sets and Systems. 157, 1036-1056.


Abstract Views: 456

PDF Views: 135




  • Design and Identify Tubercle Bacilli Diagnosis System with TSK-type Neuro Fuzzy Controllers

Abstract Views: 456  |  PDF Views: 135

Authors

Hsien-Tse Chen
Department of Electrical Engineering, National Chiao Tung University, Taiwan, Province of China
Sheng-Fuu Lin
Department of Electrical Engineering, National Chiao Tung University, Taiwan, Province of China
Yung-Chi Hsu
Department of Electrical Engineering, National Chiao Tung University, Taiwan, Province of China

Abstract


This paper proposes a TSK-type Neuro Fuzzy Controllers (TFC) with a group interaction-based evolutionary algorithm (GIEA) for constructing the tubercle bacilli diagnosis system (TBDS). The proposed GIEA is designed basing on symbiotic evolution which each chromosome in the population represents only partial solution. The whole solution consists of several chromosomes. The GIEA is different from the traditional symbiotic evolution. Each population in the GIEA is divided into several groups. Each group represents a set of the chromosomes that belong to only one fuzzy rule. Moreover, in the GIEA,the interaction ability is considered that the chromosomes will interact with other groups to generate the better chromosomes by elites-base interaction crossover strategy (EICS). In the TBDS, the EICS is used to train the TBDS. After trained by the EICS, the TBDS can diagnose the visible tubercle bacilli. The performance of the GIEA achieves better than other existing models in tubercle bacilli.

Keywords


Neuro Fuzzy Controllers, Tubercle Bacilli, Symbiotic Evolution, Reinforcement Learning

References





DOI: https://doi.org/10.17485/ijst%2F2012%2Fv5i12%2F30601