Artificial Way of Characterizing Unsupervised Data using Auto-Encoders With Deep Learning Cluster Analysis
E. Laxmi Lydia1, Gogineni Hima Bindu2, Pasam Prudhvi Kiran3, Kollati Vijaya Kumar4

1Dr. E. Laxmi Lydia, Department of Computer Science Engineering, Vignan’s Institute of Information Technology Autonomous, Visakhapatnam (Andhra Pradesh), India.
2Gogineni Hima Bindu, Assistant Professor, MCA, Vignan’s Institute of Information Technology Autonomous, Visakhapatnam (Andhra Pradesh), India.
3Pasam Prudhvi Kiran, Assistant Professor, IT, Vignan’s Institute of Information Technology Autonomous, Visakhapatnam (Andhra Pradesh), India.
4Dr. Kollati Vijaya Kumar, Associate Professor, Department of CSE, Vignan’s Institute of Engineering for Women, Visakhapatnam (Andhra Pradesh), India.
Manuscript received on 26 March 2019 | Revised Manuscript received on 05 April 2019 | Manuscript Published on 27 April 2019 | PP: 555-559 | Volume-7 Issue-6S2 April 2019 | Retrieval Number: F10740476S219/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Most data processing methods for structural, unstructural and semi-structural data are not usually trained to process Big Data. In this 21st century, processing techniques for big data have reached the advanced level of processing data through deep neural networks, which are highly sophisticated in achieving an optimized solution.Autoencoder is a dynamic approach which also combines both supervised learning and unsupervised clustering with minimum reconstruction error.This paper advances the pattern clustering and multidimensional visualization of data.Deep Convolutional Auto-encoder, CDNNbased deep clustering algorithmscomprise of multilayer perceptions improves robustness using Deep Convolutional Embedding Clustering(DCEC), Clustering Convolutional Neural Network (CCNN) clustering algorithms. The objective of this paper is to reduce the computational complexity, enhance reliability, and effective simultaneous feature learning for nonlinear transformational data usingautencoders in convolutional networks.
Keywords: Autoencoders, Convolutional Neural Network, Deep Learning Clustering Algorithms, Multilayer Perceptron.
Scope of the Article: Deep Learning