Abstract

The aim of this research is to develop and propose a single-layer semi-supervised feed forward neural network clustering method with one epoch training in order to solve the problems of low training speed, accuracy and high time and memory complexities of clustering. A code book of non-random weights is learned through the input data directly. Then, the best match weight (BMW) vector is mined from the code book, and consequently an exclusive total threshold of each input data is calculated based on the BMW vector. The input data are clustered based on their exclusive total thresholds. Finally, the method assigns a class label to each input data by using a K-step activation function for comparing the total thresholds of the training set and the test set. The class label of other unlabeled and unknown input test data are predicted based on their clusters or trial and error technique, and the number of clusters and density of each cluster are updated. In order to evaluate the results , the proposed method was used to cluster five datasets, namely thebreast cancer Wisconsin, Iris, Spam, Arcene and Yeast from the University of California Irvin (UCI) repository and a breast cancer dataset from the University of Malaya Medical center (UMMC), and their results were compared with the results of the several related methods. The experimental results show the superiority of the proposed method.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.