Shiv Kumar 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
Research Subjects
Shiv Kumar Verma has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Abdulmunafi Salisu Umar1 shared publication
Anil Kumar
Dept. of CS, Delhi Univ., New Delhi, India
1 shared publication- Anil Kumar
School of Computing Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, 201306, India
1 shared publication Arhe Amukoto
1 shared publication- Divyesh Patel
IIT Roorkee
1 shared publication - Felix Nwokekeh1 shared publication
Latest Publications
- 2 June 2026
- Published by Springer Nature
- p. 277-288
Password Strength Classification Using Machine Learning and Cryptography
- 2 June 2026
- Published by Springer Nature
- p. 277-288
Password Strength Classification Using Machine Learning and Cryptography
- 26 May 2026
- Published by World Scientific Pub Co Pte Ltd in Advances in Data Science and Adaptive Analysis
- Vol. 18 (04)
Deep Learning Approach with Attention Mechanism for Multivariate Mixed Traffic Flow Prediction
Traffic congestion is a major challenge in urban areas, primarily driven by industrialization, urbanization, and population growth. Governments and transportation agencies worldwide are actively seeking effective solutions to mitigate this issue. This study addresses traffic prediction under mixed traffic conditions by categorizing vehicles, which is essential for understanding and managing heterogeneous traffic flows. We propose a predictive model that forecasts traffic in terms of categorized vehicle speed and volume. The model integrates a Convolutional Long Short-Term Memory (ConvLSTM) neural network with an LSTM-based attention mechanism to enhance spatiotemporal learning capabilities. It is trained on seven multivariate features, including categorized vehicular speeds, time of day, and day of the week, using the same set of features as input for forecasting. The performance of the proposed model is evaluated against various baseline neural network architectures, including Dense, Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and ConvLSTM. Experimental results demonstrate that the proposed model outperforms these baselines in terms of prediction accuracy and stability. In particular, compared with the ConvLSTM model, the proposed approach achieves improvements of 48.06% in mean squared error (MSE), 14.40% in mean absolute error (MAE), and 14.51% in mean pinball loss (MPL), demonstrating the effectiveness of incorporating the attention mechanism for improved traffic forecasting under mixed traffic conditions.
- 26 May 2026
- Published by World Scientific Pub Co Pte Ltd in Advances in Data Science and Adaptive Analysis
- Vol. 18 (04)
Deep Learning Approach with Attention Mechanism for Multivariate Mixed Traffic Flow Prediction
Traffic congestion is a major challenge in urban areas, primarily driven by industrialization, urbanization, and population growth. Governments and transportation agencies worldwide are actively seeking effective solutions to mitigate this issue. This study addresses traffic prediction under mixed traffic conditions by categorizing vehicles, which is essential for understanding and managing heterogeneous traffic flows. We propose a predictive model that forecasts traffic in terms of categorized vehicle speed and volume. The model integrates a Convolutional Long Short-Term Memory (ConvLSTM) neural network with an LSTM-based attention mechanism to enhance spatiotemporal learning capabilities. It is trained on seven multivariate features, including categorized vehicular speeds, time of day, and day of the week, using the same set of features as input for forecasting. The performance of the proposed model is evaluated against various baseline neural network architectures, including Dense, Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and ConvLSTM. Experimental results demonstrate that the proposed model outperforms these baselines in terms of prediction accuracy and stability. In particular, compared with the ConvLSTM model, the proposed approach achieves improvements of 48.06% in mean squared error (MSE), 14.40% in mean absolute error (MAE), and 14.51% in mean pinball loss (MPL), demonstrating the effectiveness of incorporating the attention mechanism for improved traffic forecasting under mixed traffic conditions.
- Open Access
- 1 December 2025
- Published by The ScienceIn Publishing in Journal of Integrated Science and Technology
- Vol. 14 (1)
Structure based virtual screening of natural phytochemicals to identify potential CDK6 inhibitors for possible therapeutic intervention in acute myeloid leukemia
Acute myeloid leukemia is one of the most prominent forms of acute leukemia in adults, which account for 32% of the overall incidents of adult leukemia, AML is a leukemia of bone marrow and blood characterized by uncontrolled proliferation of myeloid cells. CDK6 protein plays a crucial role in the regulation of cell cycle by forming complexes with cyclin D1, D2, D3 ensuring transition of cell cycle from D1 to S phase, this study focuses on identify the potential inhibitors of CDK6 protein for the management of AML. In silico approach was employed to identify the potential CDK6 protein inhibitors from natural compounds for the management of AML. 6,996 natural phytochemical compounds were screened, the top five compounds, were selected with the docking score ranging from −11.8 to −10.2 kcal/mol, which is better than the reference compound (−9.6 kcal/mol). Molecular dynamic simulations were performed for the top five chosen natural phytochemical compounds, i,e., Serpentinine, Strychnochrysine, Licoagrone, Tovophyllin B, and Isopsoralidin to further assess their stability and intermolecular interaction and they all displayed a good interaction with target protein. MM/GBSA was utilized to calculate free binding energy, in which all compounds showed reasonable stability (−80.06 to −41.52). Furthermore, ADME analysis demonstrated drug-likeness and pharmacokinetics properties of the chosen compounds. Hence these natural phytochemical compounds as potential inhibitors of CDK6 protein could be used for the management of AML.
- 1 December 2025
- Published by The ScienceIn Publishing in Journal of Integrated Science and Technology
- Vol. 14 (1)
Open AccessStructure based virtual screening of natural phytochemicals to identify potential CDK6 inhibitors for possible therapeutic intervention in acute myeloid leukemia
Acute myeloid leukemia is one of the most prominent forms of acute leukemia in adults, which account for 32% of the overall incidents of adult leukemia, AML is a leukemia of bone marrow and blood characterized by uncontrolled proliferation of myeloid cells. CDK6 protein plays a crucial role in the regulation of cell cycle by forming complexes with cyclin D1, D2, D3 ensuring transition of cell cycle from D1 to S phase, this study focuses on identify the potential inhibitors of CDK6 protein for the management of AML. In silico approach was employed to identify the potential CDK6 protein inhibitors from natural compounds for the management of AML. 6,996 natural phytochemical compounds were screened, the top five compounds, were selected with the docking score ranging from −11.8 to −10.2 kcal/mol, which is better than the reference compound (−9.6 kcal/mol). Molecular dynamic simulations were performed for the top five chosen natural phytochemical compounds, i,e., Serpentinine, Strychnochrysine, Licoagrone, Tovophyllin B, and Isopsoralidin to further assess their stability and intermolecular interaction and they all displayed a good interaction with target protein. MM/GBSA was utilized to calculate free binding energy, in which all compounds showed reasonable stability (−80.06 to −41.52). Furthermore, ADME analysis demonstrated drug-likeness and pharmacokinetics properties of the chosen compounds. Hence these natural phytochemical compounds as potential inhibitors of CDK6 protein could be used for the management of AML.
- 14 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 1021-1025
Secure Supply Chain Management Framework Using Otway-Rees Protocol
By compromising third-party defenses or exploiting a vulnerability in a vendor-provided solution, an attacker with access to client data and systems can get access to supply chain management's digital infrastructure. There is a risk of losing openness, traceability, and integrity as a result of the problems. We will provide a secure supply chain management architecture that uses the symmetric key, the Otway-Rees protocol for session key generation, and BlockChain to guarantee on-time commodity delivery to customers in this work.
- 14 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 1021-1025
Secure Supply Chain Management Framework Using Otway-Rees Protocol
By compromising third-party defenses or exploiting a vulnerability in a vendor-provided solution, an attacker with access to client data and systems can get access to supply chain management's digital infrastructure. There is a risk of losing openness, traceability, and integrity as a result of the problems. We will provide a secure supply chain management architecture that uses the symmetric key, the Otway-Rees protocol for session key generation, and BlockChain to guarantee on-time commodity delivery to customers in this work.
- 1 January 2019
- Published by EAGE Publications bv
- Vol. 2019 (1) , 1-2
Heliborne Geophysical Mapping of Hard Rock Quifer with Special Reference to Data Density on Mapping Resolution
- 1 January 2019
- Published by EAGE Publications bv
- Vol. 2019 (1) , 1-2
Heliborne Geophysical Mapping of Hard Rock Quifer with Special Reference to Data Density on Mapping Resolution
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 314-322
Multi-Level Secured Encryption Technique Using Enhanced Fractal Image Watermarking
With the rapid enhancement of internet the digital multimedia such as images, audio, video are easily reproduced and distributed. The main issue of securing the data and information is born from the dependency upon the encoding and steganography individually. Because of that, the hidden secret messages can be easily broken and contents are detected. The image watermarking is the method of embedding hidden data into original image for the purpose of security. In this paper, we have purposed a new watermarking technique combined with RSA and fractal image coding for the purpose of image security and high image quality, with the help of which we have tried to overcome the drawbacks of previous watermarking techniques. In this new technique the information or the watermark is encoded using RSA and the encoded image is hidden into the fractal codes of an image. Experimental results show that the proposed algorithm enhances the security against attacks such as cutting, random noise attack and JPEG compression and provide high quality of image. Results of proposed method are better as compared to results of fractal image watermarking that are measuring by parameters such PSNR, BER and MSE.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 314-322
Multi-Level Secured Encryption Technique Using Enhanced Fractal Image Watermarking
With the rapid enhancement of internet the digital multimedia such as images, audio, video are easily reproduced and distributed. The main issue of securing the data and information is born from the dependency upon the encoding and steganography individually. Because of that, the hidden secret messages can be easily broken and contents are detected. The image watermarking is the method of embedding hidden data into original image for the purpose of security. In this paper, we have purposed a new watermarking technique combined with RSA and fractal image coding for the purpose of image security and high image quality, with the help of which we have tried to overcome the drawbacks of previous watermarking techniques. In this new technique the information or the watermark is encoded using RSA and the encoded image is hidden into the fractal codes of an image. Experimental results show that the proposed algorithm enhances the security against attacks such as cutting, random noise attack and JPEG compression and provide high quality of image. Results of proposed method are better as compared to results of fractal image watermarking that are measuring by parameters such PSNR, BER and MSE.
- 1 January 2018
- Published by IGI Global Scientific Publishing
- p. 234-243
A New Approach for Reinforcement of Project DEMATEL-FMCDM-TODIM Fuzzy Approach
This chapter describes how an effective work towards software project risk plays a vital role in determining the accomplishment of any project. In this chapter, the aim is to associate fuzzy criteria decision-making based on the approaches for the development of an assessment framework. This framework will be helpful in terms of identification and ranking the software risk according to its characteristics which will be helpful in decision-making of a software lifecycle. For the assessment for the risk of a project, there is an integration of fuzzy decision-making trial, evaluation laboratory trial and fuzzy multi-criteria decision. This new method proposed will be effective in terms of ranking and as well as to measure the software risk factors.
- 1 January 2018
- Published by IGI Global Scientific Publishing
- p. 234-243
A New Approach for Reinforcement of Project DEMATEL-FMCDM-TODIM Fuzzy Approach
This chapter describes how an effective work towards software project risk plays a vital role in determining the accomplishment of any project. In this chapter, the aim is to associate fuzzy criteria decision-making based on the approaches for the development of an assessment framework. This framework will be helpful in terms of identification and ranking the software risk according to its characteristics which will be helpful in decision-making of a software lifecycle. For the assessment for the risk of a project, there is an integration of fuzzy decision-making trial, evaluation laboratory trial and fuzzy multi-criteria decision. This new method proposed will be effective in terms of ranking and as well as to measure the software risk factors.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 326-331
Entropy Based ROI Extraction and Modified Contour Model for Image Segmentation
Segmentation process of an Image, represents meaningful way for further analysis and use in medical imaging, remote sensing and military objects detection. Due to poor resolution, segmentation become complex especially is an image is blurred or mixed pixels. Active contour technique is popular to get smooth curve around the boundary of 2D images but due to image gradient this techniques is unable to detect the boundaries of an objects. In this paper, first to calculate the entropy threshold based method to find the region of interest, then further contour model was applied to extract the efficient external features. Using this method we have extracted external features of an image, while traditionally only internals feature was able to extract. From the results it has revealed that after comparing traditional and proposed method of segmentation we get more enhanced and accurate results.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 326-331
Entropy Based ROI Extraction and Modified Contour Model for Image Segmentation
Segmentation process of an Image, represents meaningful way for further analysis and use in medical imaging, remote sensing and military objects detection. Due to poor resolution, segmentation become complex especially is an image is blurred or mixed pixels. Active contour technique is popular to get smooth curve around the boundary of 2D images but due to image gradient this techniques is unable to detect the boundaries of an objects. In this paper, first to calculate the entropy threshold based method to find the region of interest, then further contour model was applied to extract the efficient external features. Using this method we have extracted external features of an image, while traditionally only internals feature was able to extract. From the results it has revealed that after comparing traditional and proposed method of segmentation we get more enhanced and accurate results.
- Open Access
- 4 March 2016
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Hybrid Image Fusion Algorithm Using Laplacian Pyramid and PCA Method
- 4 March 2016
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessHybrid Image Fusion Algorithm Using Laplacian Pyramid and PCA Method
- 4 March 2014
- Published by Springer Nature
- p. 183-193
Efficient Approach for Reconstruction of Convex Binary Images Branch and Bound Method
- 4 March 2014
- Published by Springer Nature
- p. 183-193
Efficient Approach for Reconstruction of Convex Binary Images Branch and Bound Method