Using Deep Artificial Neural Networks in Remote Sensing Classification.


Assoc. Prof./ Ahmed Serwa

dr.a.serwa@m-eng.helwan.edu.eg
Faculty of Engineering, Helwan University,
Egypt


Biography
Dr. Serwa is an associate professor of RS and Geoinformatics in the Faculty of Engineering, Helwan University, Egypt. His research interests include using AI in RS, geomatics, geoinformatics, photogrammetry, and Geodesy. He is a lecturer at the British University of Hertfordshire in the Administrative Capital. Dr. Serwa obtained his MSc from Assiut University and PhD in Civil Engineering from Azhar University, Egypt in 2003 and 2009, respectively.


Abstract
Artificial Intelligence (AI) is the common scientific language today. Artificial Neural Networks (ANN) obtain more importance after the innovation of deep learning (DL) approach. This lecture is oriented towards development of soft computational simulator for geomatics research using ANN supporting the deep approach. Deep ANN Designer and Optimizer (DANNDO) software is developed to achieve the research objective. Multi-layer Perceptron (MLP) architecture is applied in this simulator. Geomatics RS multi-spectral data is selected to be a testing paradigm to insure the reliability of the developed simulator. The developed simulator proved the high performance of applying both shallow and deep ANN (DANN).