You are in:Home/Publications/Superior Neuro-Fuzzy Classification Systems. Neural Computing and Applications, Springer, DOI: 10.1007/s00521-012-1231-8. [ISI Indexed: Impact Factor: 1.763].

Dr. Assoc. Prof. Ahmad Taher Azar :: Publications:

Title:
Superior Neuro-Fuzzy Classification Systems. Neural Computing and Applications, Springer, DOI: 10.1007/s00521-012-1231-8. [ISI Indexed: Impact Factor: 1.763].
Authors: Azar AT, El-Said SA
Year: 2012
Keywords: Not Available
Journal: Not Available
Volume: Not Available
Issue: Not Available
Pages: Not Available
Publisher: Not Available
Local/International: International
Paper Link:
Full paper Not Available
Supplementary materials Not Available
Abstract:

Although adaptive neuro-fuzzy inference system (ANFIS) has very fast convergence time, it is not suitable for classification problems because its outputs are not integer. In order to overcome this problem, this paper provides four adaptive neuro-fuzzy classifiers; adaptive neuro-fuzzy classifier with linguistic hedges (ANFCLH), linguistic hedges neuro-fuzzy classifier with selected features (LHNFCSF), conjugate gradient neuro-fuzzy classifier (SCGNFC) and speeding up scaled conjugate gradient neuro-fuzzy classifier (SSCGNFC). These classifiers are used to achieve very fast, simple and efficient breast cancer diagnosis. Both SCGNFC and SSCGNFC systems are optimized by scaled conjugate gradient algorithms. In these two systems, k-means algorithm is used to initialize the fuzzy rules. Also, Gaussian membership function is only used for fuzzy set descriptions, because of its simple derivative expressions. The other two systems are based on linguistic hedges (LH) tuned by scaled conjugate gradient. The classifiers performances are analyzed and compared by applying them to breast cancer diagnosis. The results indicated that SCGNFC, SSCGNFC and ANFCLH achieved the same accuracy of 97.6608 % in the training phase while LHNFCSF performed better than other methods in the training phase by achieving an accuracy of 100 %. In the testing phase, the overall accuracies of LHNFCSF achieved 97.8038 %, which is superior also to other methods. Applying LHNFCSF not only reduces the dimensions of the problem, but also improves classification performance by discarding redundant, noise-corrupted or unimportant features. Also, the k-means clustering algorithm was used to determine the membership functions of each feature. LHNFCSF achieved mean RMSE values of 0.0439 in the training phase after feature selection and gives the best testing recognition rates of 98.8304 and 98.0469 during training and testing phases, respectively using two clusters for each class. The results strongly suggest that ANFCLH can aid in the diagnosis of breast cancer and can be very helpful to the physicians for their final decision on their patients.

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus