A Hybrid Approach to Cognition in Radars

M. Justin Sagayaraj; Jithesh V.; J.B. Singh; Dange Roshani; K.G. Srinivasa

doi:10.14429/dsj.68.12228

M. Justin Sagayaraj Electronics and Radar Development Establishment, Bengaluru - 560 093
Jithesh V. Electronics and Radar Development Establishment, Bengaluru - 560 093
J.B. Singh Electronics and Radar Development Establishment, Bengaluru - 560 093
Dange Roshani Electronics and Radar Development Establishment, Bengaluru - 560 093
K.G. Srinivasa CBP Government Engineering College, Jaffarpur, New Delhi - 110 073

DOI: https://doi.org/10.14429/dsj.68.12228

Keywords: Cognitive radar, Cognitive architecture, Artificial cognitive system, Convolutional neural network, Long short-term memory - recurrent neural network

Abstract

In many engineering domains, cognition is emerging to play vital role. Cognition will play crucial role in radar engineering as well for the development of next generation radars. In this paper, a cognitive architecture for radars is introduced, based on hybrid cognitive architectures. The paper proposes deep learning applications for integrated target classification based on high-resolution radar range profile measurements and target revisit time calculation as case studies. The proposed architecture is based on the artificial cognitive systems concepts and provides a basis for addressing cognition in radars, which is inadequately explored for radar systems. Initial experimental studies on the applicability of deep learning techniques under this approach provided promising results.

Author Biographies

M. Justin Sagayaraj, Electronics and Radar Development Establishment, Bengaluru - 560 093

Mr Justin Sagayaraj M has received his MTech (Computer science and Engineering) from Indian Institute of Technology, Madras, MSc (computer Science) From Madurai Kamaraj University. Presently working as a scientist in DRDO-Electronics and Radar Development Establishment, Bengaluru. He has worked for many radar tracking systems and communication systems.

Jithesh V., Electronics and Radar Development Establishment, Bengaluru - 560 093

Mr V. Jithesh obtained his MSc and MPhil (Mathematics) from the University of Kerala and MTech (Computer Science) from Cochin University of Science and Technology, in 2001. Presently working as a scientist in DRDO-Electronics and Radar Development Establishment, Bengaluru. His areas of interest include : High performance computing, machine learning, radar target classification, signal and data processing algorithms, and computational electromagnetics.

J.B. Singh, Electronics and Radar Development Establishment, Bengaluru - 560 093

Mr Jang Bahadur Singh did his BE(Computer Science and Engineering) from Kumaum Engineering College, Dwarahat, in 1996. Presently working as a scientist in DRDO-Electronics and Radar Development Establishment, Bengaluru. He has worked for the development of radar data processors and is currently working in the area of radar simulators and IV and V of radar software.

Dange Roshani, Electronics and Radar Development Establishment, Bengaluru - 560 093

Ms Dange Roshani did her BE (Computer Technology) from Kavikulguru Institute of Technology and Science (KITS), Ramtek and MTech (CSE) from Vishveshwarya National Institute of Technology (VNIT), Nagpur, in 2014. She is working as a Junior Research Fellow at Electronics and Radar Development Establishment, Bengaluru. Her areas of interests include : Machine learning techniques, Advanced DB techniques and IOT.

K.G. Srinivasa, CBP Government Engineering College, Jaffarpur, New Delhi - 110 073

Dr K.G. Srinivasa obtained BE (Information Science and Engineering) and ME and PhD(Computer Science and Engineering) from Bangalore University, in 2000, 2003, and 2007, respectively. Currently working as an associate professor at CBP Govt. Engineering College, Jaffarpur, New Delhi. He has published 2 books, and more than 100 technical papers in Journals and Conferences. His research interests include : Cloud computing, data mining, soft computing, bioinformatics, FOSS and machine learning.