TY  - JOUR
T1  - Twin Stage Fuzzy Expert System Modeling for Lung Cancer Risk Diagnosis
AU - Gopalan, N.P. AU - Malathi, A. 
JO  - Asian Journal of Information Technology
VL  - 16
IS  - 6
SP  - 552
EP  - 560
PY  - 2017
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2017.552.560
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2017.552.560
KW  - Fuzzy logic
KW  -fuzzy expert system inference engine
KW  -lung cancer
KW  -demographic features
KW  -linguistic
KW  -variables
KW  -cancer risk factor
AB  - Soft computing for medical diagnosis in field of computer science has been a syndicate of
methodologies. These all work together in order to provide a facility to make decisions from consistent data or
experience of experts of related fields. Many artificial intelligence techniques such as fuzzy logic, neural
network, genetic algorithm, etc. or integration of those may be used in the field of medical science. These types
of methodologies have also been incorporated in order to diagnose the lung cancer disease. The main objective
of this study to develop a fuzzy expert system with number of linguistic variables as fuzzy feature sets along
with different membership functions to depict the risk factor in lung cancer disease. The risk level of disease
is decided by the rule set of the fuzzy system. For improving the accuracy of the system, we have designed two
stage fuzzy expert system with input of six features at each stage. The experimental results make obvious that
the proposed work has enhanced accuracy with reduced computing time.
ER  -