Using a Neurofuzzy Approach in a Medical Application

Today hybrid computing is a popular framework for solving complex problems such as in medical domain. Hybrid intelligent systems are systems that combine two or more intelligent techniques. Medicine and health care are closely related domains, where the types of problems faced are suitable for application of hybrid intelligent techniques. In this paper we present the initial evaluation of FUzzy NEUrule System which is a Neuro Fuzzy approach based on fuzzy Adaline neurons and uses Differential Evolution for optimization of membership functions. According to our previous Neuro-fuzzy approaches and a well-defined hybrid system HYMES, FUNEUS is an attempt to the direction for integration of neural and fuzzy components with Differential evolution. Despite the fact that it remains difficult to compare neurofuzzy systems conceptually and evaluate their performance, early experimental results in a medical database proved a promising performance and the need for further evaluation in other medical applications.

[1]  Rainer Storn,et al.  System design by constraint adaptation and differential evolution , 1999, IEEE Trans. Evol. Comput..

[2]  Witold Pedrycz,et al.  Heterogeneous fuzzy logic networks: fundamentals and development studies , 2004, IEEE Transactions on Neural Networks.

[3]  Tetsuyuki Takahama,et al.  Extraction of Rules from Coronary Heart Disease Database Using Automatically Defined Groups , 2004, KES.

[4]  Nikola Kasabov,et al.  Foundations Of Neural Networks, Fuzzy Systems, And Knowledge Engineering [Books in Brief] , 1996, IEEE Transactions on Neural Networks.

[5]  Jerry M. Mendel,et al.  Generating fuzzy rules by learning from examples , 1992, IEEE Trans. Syst. Man Cybern..

[6]  Ajith Abraham,et al.  Hybrid Intelligent Systems Design - A Review of a Decade of Research , 2000 .

[7]  I. Hatzilygeroudis,et al.  Combining expert systems and adaptive hypermedia technologies in a Web based educational system , 2005, Fifth IEEE International Conference on Advanced Learning Technologies (ICALT'05).

[8]  Piero P. Bonissone,et al.  Hybrid soft computing systems: industrial and commercial applications , 1999, Proc. IEEE.

[9]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[10]  Ioannis Hatzilygeroudis,et al.  FUNEUS: A Neurofuzzy Approach Based on Fuzzy Adaline Neurons , 2006, STAIRS.

[11]  Tarun Khanna,et al.  Foundations of neural networks , 1990 .

[12]  Danuta Rutkowska,et al.  Neuro-Fuzzy Architectures and Hybrid Learning , 2002, Studies in Fuzziness and Soft Computing.

[13]  Takumi Ichimura,et al.  Development of Coronary Heart Disease Database , 2004, KES.

[14]  Ioannis Hatzilygeroudis,et al.  HYMES: A HYbrid Modular Expert System with Efficient Inference and Explanation , 2001 .

[15]  Jude W. Shavlik,et al.  Combining Symbolic and Neural Learning , 1994, Machine Learning.

[16]  Lakhmi C. Jain,et al.  Knowledge-Based Intelligent Information and Engineering Systems , 2004, Lecture Notes in Computer Science.

[17]  Stephen I. Gallant,et al.  Neural network learning and expert systems , 1993 .

[18]  Amit Konar,et al.  Computational Intelligence: Principles, Techniques and Applications , 2005 .

[19]  Georgios Dounias,et al.  Adaptive systems and hybrid computational intelligence in medicine , 2004, Artif. Intell. Medicine.