This paper presents a Real Unsupervised Feed Forward Neural Network (RUFFNN) clustering method with one epoch training and data dimensionality reduction ability to overcome some critical problems such as low training speed, low accuracy as well as high memory complexity in this area. The RUFFNN method trains a code book of real weights by utilizing input data directly without using any random values. The Best Match Weight (BMW) vector is mined from the weight codebook and consequently the Total Threshold (TT) of each input data is computed based on the BMW. Finally, the input data are clustered based on their exclusive TT. For evaluation purposes, the clustering performance of the RUFFNN was compared to several related clustering methods using various data sets. The accuracy of the RUFFNN was measured through the number of clusters and the quantity of Correctly Classified Nodes(CCN).The superior clustering accuracies of 96.63%, 96.67% and 59.36% were for the breast cancer, iris and spam datasets from the UCI repository respectively. The memory complexity of the proposed method was O(m.n.sm) based on the number of nodes, attributes and size of the attribute.

[1] Andonie R. and Kovalerchuk B., “Neural Networks for Data Mining: Constrains and Open Problems,” in Proceeding of Ellensburg European Symposium on Artificial Neural Networks, Bruges, pp. 449- 458, 2007.

[2] Asadi R. and Abdul-Kareem S., “Review of Feed Forward Neural Network Classification Preprocessing Techniques,” in Proceeding of 3rd Internationa Conference Mathematical Sciences, Kuala Lumpur, pp. 567-573, 2014.

[3] Asadi R., Abdul-Kareem S., Asadi M., and Asadi S., “A Single-Layer Semi-Supervised Feed Forward Neural Network Clustering Method,” Malaysian Journal of Computer Science, vol. 28, no. 3, pp. 189-212, 2015.

[4] Asadi R., Hasan H., Sameem A., and Abdul- Kareem S., “Review of Current Online Dynamic Unsupervised Feed Forward Neural Network Classification,” in Proceeding of Computer Science and Electronics Engineering, Kuala Lumpur, pp. 21-28, 2014.

[5] Asuncion A. and Newman D., http://www.ics.uci.edu/~mlearn/MLRepository, Last Visited 2007.

[6] Camastra F. and Verri A., “A Novel Kernel Method for Clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 5, pp. 801-805, 2005.

[7] Chattopadhyay M., Dan P., and Mazumdar S., “Principal Component Analysis and Self- Organizing Map for Visual Clustering of Machine- Part Cell Formation in Cellular Manufacturing System,” Systems Research Forum, vol. 5, no. 1, pp. 1-25, 2011.

[8] Costa J. and Oliveira R., “Cluster Analysis using Growing Neural Gas and Graph Partitioning,” International Joint Conference on Neural Networks, Orlando, pp. 3051-3056, 2007.

[9] Germano, T., http://davis.wpi.edu/~matt/courses/soms, Last Visited 1999.

[10] Goebel M. and Gruenwald L., “A Survey of Data Mining and Knowledge Discovery Software Tools,” ACM SIGKDD Explorations Newsletter, vol. 1, no. 1, pp. 20-33, 1999.

[11] Gui V., Vasiu R., and Bojković Z., “A New Operator for Image Enhancement,” Facta Universitatis-Series: Electronics and Energetics, vol. 14, no. 1, pp. 109-117, 2001.

[12] Han J., Pei J., and Kamber M., Data Mining, Southeast Asia Edition: Concepts and Techniques, Morgan Kaufmann, 2006.

[13] Han J. and Kamber M., Data Mining: Concepts and Techniques, Morgan Kaufmann, 2006.

[14] Jacquier E., Kane A., and Marcus A., “Geometric or Arithmetic Mean: A Reconsideration,” An Unsupervised Feed Forward Neural Network Method for Efficient Clustering 441 Financial Analysts Journal, vol. 59, no. 6, pp. 46- 53, 2003.

[15] Kohonen T., Self-Organizing Maps, Springer, 1997.

[16] Linde Y., Buzo A., and Gray R., “An Algorithm for Vector Quantizer Design,” IEEE Transactions on Communications, vol. 28, no. 1, pp. 84-95, 1980.

[17] Martinetz T., Berkovich S., and Schulten K., “Neural-Gas̓ Network for Vector Quantization and its Application to Time-Series Prediction,” IEEE Transactions on Neural Networks, vol. 4, no. 4, pp. 558-569, 1993.

[18] Meskine F. and Bahloul S., “Privacy Preserving K- means Clustering: A Survey Research,” The International Arab Journal of Information Technology, vol. 9, no. 2, pp. 194-200, 2012.

[19] Murugappan I. and Vasudev M., “PCFA: Mining of Projected Clusters in High Dimensional Data Using Modified FCM Algorithm,” The International Arab Journal of Information Technology, vol. 11, no. 2, pp. 168-177, 2014.

[20] Serway R. and Jewett J., Physics for Scientists and Engineers with Modern Physics, Brooks Cole, 2013.

[21] Tesauro G., Touretzky D., and Leen T., Advances in Neural Information Processing Systems 7, MIT Press, 1995.

[22] Tong X., Qi L., Wu F., and Zhou H., “A Smoothing Method for Solving Portfolio Optimization with CVaR and Applications in Allocation of Generation Asset,” Applied Mathematics and Computation, vol. 216, no. 6, pp. 1723-1740, 2010.

[23] Werbos P., Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, Harvard University, 1974. Roya Asadi is a PhD of artificial intelligence (neural network) in computer science from the University of Malaya. Her interests include Artificial Neural Network modeling, Medical Informatics, Machine Learning, Data Mining, Image Processing. Mitra Asadi is a PhD candidate of Entrepreneurship Technology in Islamic Azad University- Central Tehran Branch, Iran. Her interests include: English Language Translation, Entrepreneurship Technology, and Management. Shokoofeh Asadi is Master of Agricultural Management Engineering from University of Science and research in Tehran- Iran. Her interests include: English Language Translation, Biological and Agricultural engineering, Management and leadership.