Shrish Verma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shrish Verma has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Naresh Kumar Nagwani
National Institute of Technology
6 shared publications - Alok Naugarhiya
National Institute of Technology Raipur
3 shared publications - Mahesh Vaidya
Indian Institute of Science Bengaluru,Department of Electronic Systems Engineering,Bengaluru,India
3 shared publications - Guru Prasad Mishra
Department of Electronics and Communication Engineering National Institute of Technology Raipur Raipur India
2 shared publications - Mridu Sahu
National Institute of Technology Raipur
2 shared publications - Narendra Digambar Londhe
Electrical Engineering Department, National Institute of Technology Raipur
2 shared publications
Latest Publications
- Open Access
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2512 (1)
An overview-artifacts and their reduction techniques in cardiac computed tomography
This paper presents the detailed overview on the artifacts related to Computed Tomography (CT) specifically Cardiac CT (CCT), their classification and various reduction techniques. In CCT, the motion artifacts occurs mainly due to the pumping of the heart which has to be reduced during and post CT reconstruction. The main drawback of CT machine is that it emits high radiation during scanning. Therefore, Low Dose CT (LDCT) and Limited Angle CT (LACT) have been proposed by various researchers to overcome the problem of emission of high radiation during scanning which provides better image quality with minimum radiation. However, the artifacts generated during scanning and in image reconstruction phase also affects the quality of the image which makes it a challenging task to medical experts during their interpretation. In view of that, the extensive research have been carried out by various researchers to reduce the noises or artifacts using traditional and machine learning techniques in recent past. Finally, the paper is concluded by presenting the current state of art deep learning approaches to enhance the performance of the existing methods.
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2512 (1)
Open AccessAn overview-artifacts and their reduction techniques in cardiac computed tomography
This paper presents the detailed overview on the artifacts related to Computed Tomography (CT) specifically Cardiac CT (CCT), their classification and various reduction techniques. In CCT, the motion artifacts occurs mainly due to the pumping of the heart which has to be reduced during and post CT reconstruction. The main drawback of CT machine is that it emits high radiation during scanning. Therefore, Low Dose CT (LDCT) and Limited Angle CT (LACT) have been proposed by various researchers to overcome the problem of emission of high radiation during scanning which provides better image quality with minimum radiation. However, the artifacts generated during scanning and in image reconstruction phase also affects the quality of the image which makes it a challenging task to medical experts during their interpretation. In view of that, the extensive research have been carried out by various researchers to reduce the noises or artifacts using traditional and machine learning techniques in recent past. Finally, the paper is concluded by presenting the current state of art deep learning approaches to enhance the performance of the existing methods.
- 2 April 2023
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 70 (4) , 4189-4202
ASDC-Net: Optimized Convolutional Neural Network-Based Automatic Autism Spectrum Disorder Classification Using rs-fMRI Data
Progressive neurological disorders such as Autism Spectrum Disorder (ASD) affects one in every 160 children across the country. The latest diagnostic criteria for ASD are concentrated primarily on assessing behavior. The ASD diagnostic process, on the other hand, is often time-consuming and costly, putting a significant financial burden on patient families. This paper presents an automated clinical diagnosis system for classifying ASD and typical controls (TC) using a generalized end-to-end Convolutional neural network (CNN), a deep learning (DL)-based model referred to as ASDC-Net. The proposed model provides accelerated training through Batch Normalization (BN), reducing the internal covariate shift. The resulting classification system uses functional connectivity patterns or connectomes of CC400 brain parcellation atlas of resting-state functional MRI data (rs-fMRI). The performance of the proposed model has been assessed using 1035 subjects from the Autism Brain Imaging Data Exchange (ABIDE), including 530 TC and 505 ASD. The model achieves an accuracy of (Acc) of 76.72% as compared to state-of-the-art (SOTA) methods in classifying ASD outperforming several peer machine learning (ML) and DL models. Furthermore, the Diagnostic Odd Ratio (DOR) and Matthews Correlation Coefficient (MCC) have been introduced to evaluate the effectiveness of the classifier. The evaluation metrics indicate that the suggested method is efficient and raises the prospect of helping the clinician team with the early diagnosis of ASD.
- 2 April 2023
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 70 (4) , 4189-4202
ASDC-Net: Optimized Convolutional Neural Network-Based Automatic Autism Spectrum Disorder Classification Using rs-fMRI Data
Progressive neurological disorders such as Autism Spectrum Disorder (ASD) affects one in every 160 children across the country. The latest diagnostic criteria for ASD are concentrated primarily on assessing behavior. The ASD diagnostic process, on the other hand, is often time-consuming and costly, putting a significant financial burden on patient families. This paper presents an automated clinical diagnosis system for classifying ASD and typical controls (TC) using a generalized end-to-end Convolutional neural network (CNN), a deep learning (DL)-based model referred to as ASDC-Net. The proposed model provides accelerated training through Batch Normalization (BN), reducing the internal covariate shift. The resulting classification system uses functional connectivity patterns or connectomes of CC400 brain parcellation atlas of resting-state functional MRI data (rs-fMRI). The performance of the proposed model has been assessed using 1035 subjects from the Autism Brain Imaging Data Exchange (ABIDE), including 530 TC and 505 ASD. The model achieves an accuracy of (Acc) of 76.72% as compared to state-of-the-art (SOTA) methods in classifying ASD outperforming several peer machine learning (ML) and DL models. Furthermore, the Diagnostic Odd Ratio (DOR) and Matthews Correlation Coefficient (MCC) have been introduced to evaluate the effectiveness of the classifier. The evaluation metrics indicate that the suggested method is efficient and raises the prospect of helping the clinician team with the early diagnosis of ASD.
- 17 December 2022
- Published by Springer Nature
- p. 53-64
Low Loss Enabled Semi-superjunction 4H-SiC IGBT for High Voltage and Current Application
- 17 December 2022
- Published by Springer Nature
- p. 53-64
Low Loss Enabled Semi-superjunction 4H-SiC IGBT for High Voltage and Current Application
- 24 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 69 (3) , 1604-1607
Collector Engineered Bidirectional Insulated Gate Bipolar Transistor With Low Loss
The collector engineered bidirectional insulated gate bipolar transistor (CEB-IGBT) with p-buffer and semi-superjunction (Semi-SJ) is proposed. The structural modification at collector side provides support to reverse breakdown voltage ( $BV_R$ ) in two ways. First, the p-buffer layer allows the device to deplete completely and eliminates premature breakdown effects. Second, the Semi-SJ region introduces an electric field component in the x-direction ( $E_X$ ) in order to further improve the $BV_R$ . The overall increased electric field, which is a resultant of $E_X$ and $E_Y$ , improves $BV_R$ by 53.83% compared to nonpunchthrough IGBT (NPT-IGBT). The efficient potential distribution in the drift region provides support to forward breakdown ( $BV_F$ ) as well. The n-layer below p-body acts as a field stop (FS) layer, which reduces the leakage current during the off-state condition. The p-buffer, which injects higher minority charges along the drift side and n-layer with charge storage effect collectively, provides conductivity modulation in the epitaxial region in order to increase current handling capability. This high collector current density leads to reduce $V_{{on}}$ by 14.5% compared to NPT-IGBT. Furthermore, the charge coupling effect of Semi-SJ region enables the proposed device to turn-off quickly with higher pillar doping and reduces turn-off loss ( $E_{{off}}$ ) in comparison with NPT-IGBT.- 24 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 69 (3) , 1604-1607
Collector Engineered Bidirectional Insulated Gate Bipolar Transistor With Low Loss
The collector engineered bidirectional insulated gate bipolar transistor (CEB-IGBT) with p-buffer and semi-superjunction (Semi-SJ) is proposed. The structural modification at collector side provides support to reverse breakdown voltage ( $BV_R$ ) in two ways. First, the p-buffer layer allows the device to deplete completely and eliminates premature breakdown effects. Second, the Semi-SJ region introduces an electric field component in the x-direction ( $E_X$ ) in order to further improve the $BV_R$ . The overall increased electric field, which is a resultant of $E_X$ and $E_Y$ , improves $BV_R$ by 53.83% compared to nonpunchthrough IGBT (NPT-IGBT). The efficient potential distribution in the drift region provides support to forward breakdown ( $BV_F$ ) as well. The n-layer below p-body acts as a field stop (FS) layer, which reduces the leakage current during the off-state condition. The p-buffer, which injects higher minority charges along the drift side and n-layer with charge storage effect collectively, provides conductivity modulation in the epitaxial region in order to increase current handling capability. This high collector current density leads to reduce $V_{{on}}$ by 14.5% compared to NPT-IGBT. Furthermore, the charge coupling effect of Semi-SJ region enables the proposed device to turn-off quickly with higher pillar doping and reduces turn-off loss ( $E_{{off}}$ ) in comparison with NPT-IGBT.- 25 June 2021
- Published by Seventh Sense Research Group Journals in International Journal of Engineering Trends and Technology
- Vol. 69 (6) , 216-224
Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks
Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks
- 25 June 2021
- Published by Seventh Sense Research Group Journals in International Journal of Engineering Trends and Technology
- Vol. 69 (6) , 216-224
Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks
Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks
- 10 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (15) , 16927-16936
A Thresholding-Free State Detection Approach for Home Appliance Control Using P300-Based BCI
The main objective of brain-computer interface (BCI)-based asynchronous system is to detect user’s intentional control (IC) and non-control (NC) states. In IC state, users are constantly adapting to the BCI system and making selections, whereas in NC state, users ignore to focus on the BCI system. Most of the current methods for IC or NC state detection are based on thresholding. However, choosing a suitable threshold is often time-consuming. Moreover, the chosen threshold may be insufficient over a long period of time due to the variability of EEG signals. This article proposes an asynchronous P300-based row-column paradigm (RCP) system for home appliances control. The proposed system is able to detect IC and NC states of the subject. A novel 2×3 matrix consisting of home appliances (such as light, fan, mobile device, door, television, and electric heater) has been proposed as an RCP. For stimulation, technical paper & video clip were shown on a computer screen to the users. Step-wise linear discriminant analysis (SWLDA) classifier was employed in the proposed thresholding-free asynchronous-BCI system to distinguishes between user IC and NC states. In the proposed experiment, fourteen healthy and nine paralyzed persons have participated as volunteer subjects. The synchronous mode average classification accuracy of 92.44% and 89.33% was achieved for healthy and paralyzed participants, respectively. Thereafter, the average asynchronous mode accuracy of 94.28% and 92.11% with very less false activation rate (FARs) of 0.15/min and 0.162/min was achieved for healthy and paralyzed participants, respectively. As an application, the developed P300-based speller was used to control home appliances by issuing different commands. The experimental results validated the effectiveness of the proposed method and presents future direction to use the system for paralyzed patients.
- 10 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (15) , 16927-16936
A Thresholding-Free State Detection Approach for Home Appliance Control Using P300-Based BCI
The main objective of brain-computer interface (BCI)-based asynchronous system is to detect user’s intentional control (IC) and non-control (NC) states. In IC state, users are constantly adapting to the BCI system and making selections, whereas in NC state, users ignore to focus on the BCI system. Most of the current methods for IC or NC state detection are based on thresholding. However, choosing a suitable threshold is often time-consuming. Moreover, the chosen threshold may be insufficient over a long period of time due to the variability of EEG signals. This article proposes an asynchronous P300-based row-column paradigm (RCP) system for home appliances control. The proposed system is able to detect IC and NC states of the subject. A novel 2×3 matrix consisting of home appliances (such as light, fan, mobile device, door, television, and electric heater) has been proposed as an RCP. For stimulation, technical paper & video clip were shown on a computer screen to the users. Step-wise linear discriminant analysis (SWLDA) classifier was employed in the proposed thresholding-free asynchronous-BCI system to distinguishes between user IC and NC states. In the proposed experiment, fourteen healthy and nine paralyzed persons have participated as volunteer subjects. The synchronous mode average classification accuracy of 92.44% and 89.33% was achieved for healthy and paralyzed participants, respectively. Thereafter, the average asynchronous mode accuracy of 94.28% and 92.11% with very less false activation rate (FARs) of 0.15/min and 0.162/min was achieved for healthy and paralyzed participants, respectively. As an application, the developed P300-based speller was used to control home appliances by issuing different commands. The experimental results validated the effectiveness of the proposed method and presents future direction to use the system for paralyzed patients.
- 1 November 2020
- Published by Elsevier in Materials Today: Proceedings
- Vol. 46, 4587-4592
Lateral variation doped wide bottom trench gate IGBT for reduced on-resistance with improved gate charge
- 1 November 2020
- Published by Elsevier in Materials Today: Proceedings
- Vol. 46, 4587-4592
Lateral variation doped wide bottom trench gate IGBT for reduced on-resistance with improved gate charge
- 16 April 2019
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 68 (1) , 265-282
Pulmonary Nodule Detection in CT Images Using Optimal Multilevel Thresholds and Rule-based Filtering
Lung cancer is the most common cancer causing the highest mortality rate as per the analysis of previous and recent year worldwide statistics. The main reason behind the high mortality is late detection of its fatal stage. Early detection of lung nodules offers challenging tasks due to nodules’ types, size, unfavorable locations, and attachment with the vessels. In this paper, we propose a method of early detection of lung nodules in computed tomography images, which can assist radiologists to locate the suspected nodules. The method consists of three major sections, i.e. the extraction and segmentation of lung parenchyma through clustering algorithm, extraction and highlighting the region of interests through optimal multilevel thresholding using particle swarm optimization, selection and application of 2D features to detect the initial nodule candidates and further iteratively false positive reduction by the analysis of 3D features. We used 84 CT scans with 301 nodules taken from publically available Lung Image Database Consortium – Image Database Resource Initiative (LIDC-IDRI) data set for experiment. In general for all types of nodules, the proposed method achieved an overall sensitivity of 84.05% with a reduced false positive rate of 1.93 per CT scan. Our results have been compared with the methods from literature which show improved false positive rate along with comparable sensitivity.
- 16 April 2019
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 68 (1) , 265-282
Pulmonary Nodule Detection in CT Images Using Optimal Multilevel Thresholds and Rule-based Filtering
Lung cancer is the most common cancer causing the highest mortality rate as per the analysis of previous and recent year worldwide statistics. The main reason behind the high mortality is late detection of its fatal stage. Early detection of lung nodules offers challenging tasks due to nodules’ types, size, unfavorable locations, and attachment with the vessels. In this paper, we propose a method of early detection of lung nodules in computed tomography images, which can assist radiologists to locate the suspected nodules. The method consists of three major sections, i.e. the extraction and segmentation of lung parenchyma through clustering algorithm, extraction and highlighting the region of interests through optimal multilevel thresholding using particle swarm optimization, selection and application of 2D features to detect the initial nodule candidates and further iteratively false positive reduction by the analysis of 3D features. We used 84 CT scans with 301 nodules taken from publically available Lung Image Database Consortium – Image Database Resource Initiative (LIDC-IDRI) data set for experiment. In general for all types of nodules, the proposed method achieved an overall sensitivity of 84.05% with a reduced false positive rate of 1.93 per CT scan. Our results have been compared with the methods from literature which show improved false positive rate along with comparable sensitivity.
- 30 January 2019
- Published by IOP Publishing in Materials Research Express
- Vol. 6 (4) , 046424
Strained superjunction U-MOSFET with insulating layer between alternate pillars
- 30 January 2019
- Published by IOP Publishing in Materials Research Express
- Vol. 6 (4) , 046424
Strained superjunction U-MOSFET with insulating layer between alternate pillars
- Open Access
- 22 June 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (21)
An Empirical Analysis on Reducing Open Source Software Development Tasks using Stack Overflow
An Empirical Analysis on Reducing Open Source Software Development Tasks using Stack Overflow
- 22 June 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (21)
Open AccessAn Empirical Analysis on Reducing Open Source Software Development Tasks using Stack Overflow
An Empirical Analysis on Reducing Open Source Software Development Tasks using Stack Overflow