Introducing a software for innovative neuro-fuzzy clustering method named NFCMR

Main Article Content

Aref Shirazi
Adel Shirazy
Shahab Saki
Ardeshir Hezarkhani


An innovative neural-fuzzy clustering method is for predicting cluster (anomaly / background) of each new sample with the probability of its presence. This method which is a combination of the Fuzzy C-Means clustering method (FCM) and the General Regression Neural Network (GRNN), is an attempt to first divide the samples in the region by fuzzy method with the probability of being in each cluster and then with the results of this Practice, the artificial neural network is trained, and can analyze the new data entered in the region with the probable percentage of the clusters. More clearly, after a full mineral exploration, the sample can be attributed to a certain probable percentage of anomalies. To test the accuracy of this clustering in the form of the theory alone, a case study was conducted on the results of the analysis of regional alluvial sediments data in Birjand, IRAN, which resulted in satisfactory results. This software is written in MATLAB and its first application in mining engineering. This algorithm can be used in other similar applications in various sciences.


Download data is not yet available.

Article Details

How to Cite
Shirazi, A., Shirazy, A., Saki, S., & Hezarkhani, A. (2018). Introducing a software for innovative neuro-fuzzy clustering method named NFCMR. Global Journal of Computer Sciences: Theory and Research, 8(2), 62-69.