DocumentCode :
1748912
Title :
A hybrid intelligent system for medical diagnosis
Author :
Meesad, Phayung ; Yen, Gary G.
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
Volume :
4
fYear :
2001
fDate :
2001
Firstpage :
2558
Abstract :
We propose a novel hybrid intelligent system (HIS) that is a combination of numerical and linguistic knowledge representation. The proposed HIS is a hierarchical integration of an incremental learning fuzzy neural network (ILFN) and a fuzzy linguistic model optimized via the genetic algorithm. The ILFN is self-organizing network with the capability of fast, online, incremental learning. The linguistic model is constructed based on knowledge embedded in the trained ILFN. The knowledge captured from the low-level ILFN can be mapped to the higher-level linguistic model and vice versa. The GA is applied to optimize the linguistic model to maintain high accuracy and comprehensibility. The resulted HIS is capable of dealing with low-level numerical computation and higher-level linguistic computation. After the system completely constructed, it can incrementally learn new information in both numerical and linguistic structures. To evaluate the system´s performance the well-known benchmark Wisconsin breast cancer data was studied as an application to medical diagnosis. The simulation results show that the proposed HIS perform better than the individual standalone systems
Keywords :
diagnostic expert systems; fuzzy neural nets; genetic algorithms; knowledge representation; learning (artificial intelligence); medical diagnostic computing; self-organising feature maps; Wisconsin breast cancer data; fuzzy linguistic model; fuzzy neural network; genetic algorithm; hybrid intelligent system; incremental learning; knowledge representation; self-organizing network; Breast cancer; Computational modeling; Fuzzy neural networks; Genetic algorithms; Hybrid intelligent systems; Knowledge representation; Medical diagnosis; Medical simulation; Self-organizing networks; System performance;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
ISSN :
1098-7576
Print_ISBN :
0-7803-7044-9
Type :
conf
DOI :
10.1109/IJCNN.2001.938772
Filename :
938772
Link To Document :
بازگشت