Selvaraj Bharathiraja
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Selvaraj Bharathiraja has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Govindarajan Anusooya
Vellore Institute of Technology, Chennai Campus, Chennai 600127, India
2 shared publications - Kamsundher Sathyarajasekaran
Vellore Institute of Technology, Chennai Campus, Chennai 600127, India
2 shared publications - Rajesh Kanna Baskaran
School of Computing Science and Engineering, Vellore Institute of Technology, Chennai, India
2 shared publications Alla Parimala Chowdary
Vellore Institute of Technology, Chennai, Tamil Nadu, India
1 shared publication- Elangovan Muniyandy
Department of Biosciences, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India
1 shared publication G. Suganya
Vellore Institute of Technology, Chennai, Tamil Nadu, India
1 shared publication
Latest Publications
- 6 July 2023
- Published by Wiley
- p. 159-173
IoT‐Based Automatic Entry Check in COVID‐19 Pandemic
- Open Access
Self-Supervised Wavelet-Based Attention Network for Semantic Segmentation of MRI Brain Tumor
To determine the appropriate treatment plan for patients, radiologists must reliably detect brain tumors. Despite the fact that manual segmentation involves a great deal of knowledge and ability, it may sometimes be inaccurate. By evaluating the size, location, structure, and grade of the tumor, automatic tumor segmentation in MRI images aids in a more thorough analysis of pathological conditions. Due to the intensity differences in MRI images, gliomas may spread out, have low contrast, and are therefore difficult to detect. As a result, segmenting brain tumors is a challenging process. In the past, several methods for segmenting brain tumors in MRI scans were created. However, because of their susceptibility to noise and distortions, the usefulness of these approaches is limited. Self-Supervised Wavele- based Attention Network (SSW-AN), a new attention module with adjustable self-supervised activation functions and dynamic weights, is what we suggest as a way to collect global context information. In particular, this network’s input and labels are made up of four parameters produced by the two-dimensional (2D) Wavelet transform, which makes the training process simpler by neatly segmenting the data into low-frequency and high-frequency channels. To be more precise, we make use of the channel attention and spatial attention modules of the self-supervised attention block (SSAB). As a result, this method may more easily zero in on crucial underlying channels and spatial patterns. The suggested SSW-AN has been shown to outperform the current state-of-the-art algorithms in medical image segmentation tasks, with more accuracy, more promising dependability, and less unnecessary redundancy.
Open AccessSelf-Supervised Wavelet-Based Attention Network for Semantic Segmentation of MRI Brain Tumor
To determine the appropriate treatment plan for patients, radiologists must reliably detect brain tumors. Despite the fact that manual segmentation involves a great deal of knowledge and ability, it may sometimes be inaccurate. By evaluating the size, location, structure, and grade of the tumor, automatic tumor segmentation in MRI images aids in a more thorough analysis of pathological conditions. Due to the intensity differences in MRI images, gliomas may spread out, have low contrast, and are therefore difficult to detect. As a result, segmenting brain tumors is a challenging process. In the past, several methods for segmenting brain tumors in MRI scans were created. However, because of their susceptibility to noise and distortions, the usefulness of these approaches is limited. Self-Supervised Wavele- based Attention Network (SSW-AN), a new attention module with adjustable self-supervised activation functions and dynamic weights, is what we suggest as a way to collect global context information. In particular, this network’s input and labels are made up of four parameters produced by the two-dimensional (2D) Wavelet transform, which makes the training process simpler by neatly segmenting the data into low-frequency and high-frequency channels. To be more precise, we make use of the channel attention and spatial attention modules of the self-supervised attention block (SSAB). As a result, this method may more easily zero in on crucial underlying channels and spatial patterns. The suggested SSW-AN has been shown to outperform the current state-of-the-art algorithms in medical image segmentation tasks, with more accuracy, more promising dependability, and less unnecessary redundancy.
- Open Access
- 6 February 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (1) , 110-116
Power Consumption and Carbon Emission Equivalent for Virtualized Resources – An Analysis
The International Energy Agency (IEA) revealed that the worldwide energy-related carbon dioxide (CO2) situation has hit a historic high of 33.1 Giga tonnes (Gt) of CO2. 85% of the rise in emissions was due to China, India, and the United States. The increase in emissions in India was 4.8%, or 105 Mega tonnes (Mt) of CO2, with the increase in emissions being evenly distributed across the transportation and industrial sectors, according to Beloglazov et al (2011). Environmental contamination brought on by carbon emissions is harmful to the environment. As a result, there is an urgent need for the IT sectors to develop effective and efficient technology to eliminate such carbon emissions. The primary focus is on lowering carbon emissions due to widespread awareness of the issue.
- 6 February 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (1) , 110-116
Open AccessPower Consumption and Carbon Emission Equivalent for Virtualized Resources – An Analysis
The International Energy Agency (IEA) revealed that the worldwide energy-related carbon dioxide (CO2) situation has hit a historic high of 33.1 Giga tonnes (Gt) of CO2. 85% of the rise in emissions was due to China, India, and the United States. The increase in emissions in India was 4.8%, or 105 Mega tonnes (Mt) of CO2, with the increase in emissions being evenly distributed across the transportation and industrial sectors, according to Beloglazov et al (2011). Environmental contamination brought on by carbon emissions is harmful to the environment. As a result, there is an urgent need for the IT sectors to develop effective and efficient technology to eliminate such carbon emissions. The primary focus is on lowering carbon emissions due to widespread awareness of the issue.
- 22 March 2022
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 48 (2) , 1207-1219
A Deep Learning Framework for Image Authentication: An Automatic Source Camera Identification Deep-Net
- 22 March 2022
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 48 (2) , 1207-1219
A Deep Learning Framework for Image Authentication: An Automatic Source Camera Identification Deep-Net
- 19 April 2019
- Published by Springer Nature in Mobile Networks and Applications
- Vol. 24 (4) , 1174-1180
Anti-Forensics Contrast Enhancement Detection (AFCED) Technique in Images Based on Laplace Derivative Histogram
- 19 April 2019
- Published by Springer Nature in Mobile Networks and Applications
- Vol. 24 (4) , 1174-1180
Anti-Forensics Contrast Enhancement Detection (AFCED) Technique in Images Based on Laplace Derivative Histogram