Lijo T. George
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lijo T. George has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Ruta Kale
Tata Institute of Fundamental Research
2 shared publications - Yogesh Wadadekar
Tata Institute of Fundamental Research
2 shared publications - Ashwin Samudre
Allen Institute for Cell Science Seattle, Seattle, USA
1 shared publication Mahak Bansal
Viterbi School of Engineering, University of Southern California, 3650 McClintock Ave, Los Angeles, CA 90089, United States
1 shared publicationYogesh Wadadekar
National Centre for Radio Astrophysics, TIFR, Post Bag 3, Ganeshkhind, Pune 411007, India
1 shared publication
Latest Publications
- 30 October 2021
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 509 (2) , 2269-2280
Data-Efficient Classification of Radio Galaxies
The continuum emission from radio galaxies can be generally classified into different morphological classes such as FRI, FRII, Bent, or Compact. In this paper, we explore the task of radio galaxy classification based on morphology using deep learning methods with a focus on using a small scale dataset (∼2000 samples). We apply few-shot learning techniques based on Twin Networks and transfer learning techniques using a pre-trained DenseNet model with advanced techniques like cyclical learning rate and discriminative learning to train the model rapidly. We achieve a classification accuracy of over 92% using our best performing model with the biggest source of confusion being between Bent and FRII type galaxies. Our results show that focusing on a small but curated dataset along with the use of best practices to train the neural network can lead to good results. Automated classification techniques will be crucial for upcoming surveys with next generation radio telescopes which are expected to detect hundreds of thousands of new radio galaxies in the near future.
- 30 October 2021
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 509 (2) , 2269-2280
Data-Efficient Classification of Radio Galaxies
The continuum emission from radio galaxies can be generally classified into different morphological classes such as FRI, FRII, Bent, or Compact. In this paper, we explore the task of radio galaxy classification based on morphology using deep learning methods with a focus on using a small scale dataset (∼2000 samples). We apply few-shot learning techniques based on Twin Networks and transfer learning techniques using a pre-trained DenseNet model with advanced techniques like cyclical learning rate and discriminative learning to train the model rapidly. We achieve a classification accuracy of over 92% using our best performing model with the biggest source of confusion being between Bent and FRII type galaxies. Our results show that focusing on a small but curated dataset along with the use of best practices to train the neural network can lead to good results. Automated classification techniques will be crucial for upcoming surveys with next generation radio telescopes which are expected to detect hundreds of thousands of new radio galaxies in the near future.
- 11 August 2021
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 507 (3) , 4487-4506
Imaging results from the legacy Giant Metrewave Radio Telescope Galaxy Cluster Key Project
We have used archival Giant Metrewave Radio Telescope (GMRT) data to image and study 39 galaxy clusters. These observations were made as part of the GMRT Key Project on galaxy clusters between 2001 and 2004. The observations presented in this sample include 14 observations at 610 MHz, 29 at 325 MHz, and three at 244 MHz covering a redshift range of 0.02–0.62. Multifrequency observations were made for eight clusters. We analysed the clusters using the spam processing software and detected the presence of radio halo emission for the first time in the clusters RXC J0510−0801 and RXC J2211.7−0349. We also confirmed the presence of extended emission in 11 clusters which were known from the literature. In clusters where haloes were not detected, upper limits were placed using our own semi-automated program. We plot our detections and non-detections on the empirical LX−P1.4 and M500−P1.4 relation in radio halo clusters and discuss the results. The best fits follow a power law of the form |$L_{500} \propto P_{1.4}^{1.82}$| and |$M_{500} \propto P_{1.4}^{3.001}$| which is in accordance with the best estimates in the literature.
- 11 August 2021
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 507 (3) , 4487-4506
Imaging results from the legacy Giant Metrewave Radio Telescope Galaxy Cluster Key Project
We have used archival Giant Metrewave Radio Telescope (GMRT) data to image and study 39 galaxy clusters. These observations were made as part of the GMRT Key Project on galaxy clusters between 2001 and 2004. The observations presented in this sample include 14 observations at 610 MHz, 29 at 325 MHz, and three at 244 MHz covering a redshift range of 0.02–0.62. Multifrequency observations were made for eight clusters. We analysed the clusters using the spam processing software and detected the presence of radio halo emission for the first time in the clusters RXC J0510−0801 and RXC J2211.7−0349. We also confirmed the presence of extended emission in 11 clusters which were known from the literature. In clusters where haloes were not detected, upper limits were placed using our own semi-automated program. We plot our detections and non-detections on the empirical LX−P1.4 and M500−P1.4 relation in radio halo clusters and discuss the results. The best fits follow a power law of the form |$L_{500} \propto P_{1.4}^{1.82}$| and |$M_{500} \propto P_{1.4}^{3.001}$| which is in accordance with the best estimates in the literature.
- Open Access
- 1 February 2021
- Published by Springer Nature in Experimental Astronomy
- Vol. 51 (2) , 235-248
An upper limit calculator (UL-CALC) for undetected extended sources with radio interferometers: radio halo upper limits
- 1 February 2021
- Published by Springer Nature in Experimental Astronomy
- Vol. 51 (2) , 235-248
Open AccessAn upper limit calculator (UL-CALC) for undetected extended sources with radio interferometers: radio halo upper limits