Ankit Shah
Research Subjects
Ankit Shah has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Mamta Padole
Faculty of Technology and Engineering, The Maharaja Sayajirao University of Baroda, Vadodara, India
8 shared publications Kinjal Adhvaryu
2 shared publications- Kinjal Adhvaryu
Sal Engineering College, Gujarat Technological University
2 shared publications Margi Engineer
Shankersinh Vaghela Bapu Institute of Technology,Department of Information Technology and Computer Engineering,Gandhinagar,Gujarat,India
2 shared publications- Roshni Rawal
Adani Institute of Digital Technology Management
2 shared publications Chetan Kapadiya
1 shared publication
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 414-421
Role of Technothics and Gen-AI in Industry 5.0
- 21 January 2026
- Published by Springer Nature
- p. 126-136
Ethical Considerations and the Impact of Large Language Models on Automated Feedback Generation and Data Analysis
- 21 January 2026
- Published by Springer Nature
- p. 126-136
Ethical Considerations and the Impact of Large Language Models on Automated Feedback Generation and Data Analysis
- 1 October 2025
- Published by Springer Nature
- p. 183-196
Evaluating the Efficacy of Generative Adversarial Networks in Data Augmentation for Machine Learning Models
- 1 October 2025
- Published by Springer Nature
- p. 183-196
Evaluating the Efficacy of Generative Adversarial Networks in Data Augmentation for Machine Learning Models
- RetractedOpen Access
- 16 July 2024
- Published by EDP Sciences in ITM Web of Conferences
- Vol. 65, 03007
Feature Importance in Machine Learning with Explainable Artificial Intelligence (XAI) for Rainfall Prediction
Precipitation expectation is a pivotal subject for the administration of water assets and counteraction of hydrological calamities. To make a precipitation forecast and find the essential elements influencing precipitation, this study presents a logical profound learning approach in two sections. The initial segment with a consideration system which could foresee precipitation, while second part the clarification figures attribution values for the information weather conditions elements to evaluate their significance. A contextual investigation is led on hourly precipitation information for India’s population wise top eight urban cities. The outcomes predominantly demonstrate that the main elements for precipitation whose component esteem is adversely/decidedly corresponded with its attribution esteem. The review’s importance lies in upgrading the giving interpretability through recognizable proof of persuasive variables, which works with long haul arranging of water assets and more profound comprehension of mind-boggling climate frameworks.
- 16 July 2024
- Published by EDP Sciences in ITM Web of Conferences
- Vol. 65, 03007
RetractedOpen AccessFeature Importance in Machine Learning with Explainable Artificial Intelligence (XAI) for Rainfall Prediction
Precipitation expectation is a pivotal subject for the administration of water assets and counteraction of hydrological calamities. To make a precipitation forecast and find the essential elements influencing precipitation, this study presents a logical profound learning approach in two sections. The initial segment with a consideration system which could foresee precipitation, while second part the clarification figures attribution values for the information weather conditions elements to evaluate their significance. A contextual investigation is led on hourly precipitation information for India’s population wise top eight urban cities. The outcomes predominantly demonstrate that the main elements for precipitation whose component esteem is adversely/decidedly corresponded with its attribution esteem. The review’s importance lies in upgrading the giving interpretability through recognizable proof of persuasive variables, which works with long haul arranging of water assets and more profound comprehension of mind-boggling climate frameworks.
- Open Access
Deep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework
Cyber vulnerability management is a critical function of a cybersecurity operations center (CSOC) that helps protect organizations against cyber-attacks on their computer and network systems. Adversaries hold an asymmetric advantage over the CSOC, as the number of deficiencies in these systems is increasing at a significantly higher rate compared to the expansion rate of the security teams to mitigate them in a resource-constrained environment. The current approaches are deterministic and one-time decision-making methods, which do not consider future uncertainties when prioritizing and selecting vulnerabilities for mitigation. These approaches are also constrained by the sub-optimal distribution of resources, providing no flexibility to adjust their response to fluctuations in vulnerability arrivals. We propose a novel framework, Deep VULMAN, consisting of a deep reinforcement learning agent and an integer programming method to fill this gap in the cyber vulnerability management process. Our sequential decision-making framework, first, determines the near-optimal amount of resources to be allocated for mitigation under uncertainty for a given system state and then determines the optimal set of prioritized vulnerability instances for mitigation. Our proposed framework outperforms the current methods in prioritizing the selection of important organization-specific vulnerabilities, on both simulated and real-world vulnerability data, observed over a one-year period.
Open AccessDeep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework
Cyber vulnerability management is a critical function of a cybersecurity operations center (CSOC) that helps protect organizations against cyber-attacks on their computer and network systems. Adversaries hold an asymmetric advantage over the CSOC, as the number of deficiencies in these systems is increasing at a significantly higher rate compared to the expansion rate of the security teams to mitigate them in a resource-constrained environment. The current approaches are deterministic and one-time decision-making methods, which do not consider future uncertainties when prioritizing and selecting vulnerabilities for mitigation. These approaches are also constrained by the sub-optimal distribution of resources, providing no flexibility to adjust their response to fluctuations in vulnerability arrivals. We propose a novel framework, Deep VULMAN, consisting of a deep reinforcement learning agent and an integer programming method to fill this gap in the cyber vulnerability management process. Our sequential decision-making framework, first, determines the near-optimal amount of resources to be allocated for mitigation under uncertainty for a given system state and then determines the optimal set of prioritized vulnerability instances for mitigation. Our proposed framework outperforms the current methods in prioritizing the selection of important organization-specific vulnerabilities, on both simulated and real-world vulnerability data, observed over a one-year period.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 1282-1302
“Saksham Model” Performance Improvisation Using Node Capability Evaluation in Apache Hadoop
Big Data processing and analysis requires tremendous processing capability. Distributed computing brings many commodity systems under the common platform to answer the need for Big Data processing and analysis. Apache Hadoop is the most suitable set of tools for Big Data storage, processing, and analysis. But Hadoop found to be inefficient when it comes to heterogeneous set computers which have different processing capabilities. In this research, we propose the Saksham model which optimizes the processing time by efficient use of node processing capability and file management. The proposed model shows the performance improvement for Big Data processing. To achieve better performance, Saksham model uses two vital aspects of heterogeneous distributed computing: Effective block rearrangement policy and use of node processing capability. The results demonstrate that the proposed model successfully achieves better job execution time and improves data locality.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 1282-1302
“Saksham Model” Performance Improvisation Using Node Capability Evaluation in Apache Hadoop
Big Data processing and analysis requires tremendous processing capability. Distributed computing brings many commodity systems under the common platform to answer the need for Big Data processing and analysis. Apache Hadoop is the most suitable set of tools for Big Data storage, processing, and analysis. But Hadoop found to be inefficient when it comes to heterogeneous set computers which have different processing capabilities. In this research, we propose the Saksham model which optimizes the processing time by efficient use of node processing capability and file management. The proposed model shows the performance improvement for Big Data processing. To achieve better performance, Saksham model uses two vital aspects of heterogeneous distributed computing: Effective block rearrangement policy and use of node processing capability. The results demonstrate that the proposed model successfully achieves better job execution time and improves data locality.
- 5 May 2020
- Published by Taylor & Francis
- p. 415-421
Fog Computing for Internet of Medical Things Based Healthcare Systems
In today’s era of Internet of Medical Things (IoT) there is a need of collective bandwidth, low power consumption, latency, real-time interaction, geographical distribution, heterogeneity, and wireless access for providing better Quality of Services (QoS). Internet of Medical Things (IoMT) technology brings many challenges along with the services it provides. Initially, Cloud computing was used to store data, process and analyze the data but due to many provocations, there is a need of an intermediate layer for fast processing and servicing, that is how Fog layer is introduced. Where Cloud services lack to provide enough benefits in IoMT, Fog layer suffice all that services. This paper presents a comparison between ECG monitoring system implemented on cloud and fog platform. Results of comparison prove that IoMT implemented using Fog layer is much more efficient than the implemented on cloud platform.
- 5 May 2020
- Published by Taylor & Francis
- p. 415-421
Fog Computing for Internet of Medical Things Based Healthcare Systems
In today’s era of Internet of Medical Things (IoT) there is a need of collective bandwidth, low power consumption, latency, real-time interaction, geographical distribution, heterogeneity, and wireless access for providing better Quality of Services (QoS). Internet of Medical Things (IoMT) technology brings many challenges along with the services it provides. Initially, Cloud computing was used to store data, process and analyze the data but due to many provocations, there is a need of an intermediate layer for fast processing and servicing, that is how Fog layer is introduced. Where Cloud services lack to provide enough benefits in IoMT, Fog layer suffice all that services. This paper presents a comparison between ECG monitoring system implemented on cloud and fog platform. Results of comparison prove that IoMT implemented using Fog layer is much more efficient than the implemented on cloud platform.
- 5 May 2020
- Published by Taylor & Francis
- p. 617-624
Survey Paper on Efficient Security Mechanism in Iot Using Blockchain
Internet of things (IoT) is indicating exponential development in industry and research fields, yet regardless it experiences security vulnerabilities. Due to the massive scale, IoT security always remains a challenge. Security issues will keep on expanding with such a template, particularly for confidential information, such as information gathered with increasingly more refined associated gadgets (framing the IoT). In this way, IoT elements need to perceive and validate an authenticate and trade of information. Blockchain-based decentralized framework ready to meet security safeguarding in the IoT environment.
- 5 May 2020
- Published by Taylor & Francis
- p. 617-624
Survey Paper on Efficient Security Mechanism in Iot Using Blockchain
Internet of things (IoT) is indicating exponential development in industry and research fields, yet regardless it experiences security vulnerabilities. Due to the massive scale, IoT security always remains a challenge. Security issues will keep on expanding with such a template, particularly for confidential information, such as information gathered with increasingly more refined associated gadgets (framing the IoT). In this way, IoT elements need to perceive and validate an authenticate and trade of information. Blockchain-based decentralized framework ready to meet security safeguarding in the IoT environment.
- 14 March 2020
- Published by Springer Nature
- p. 217-226
Hadoop Performance Acceleration by Effective Data and Job Placement
- 14 March 2020
- Published by Springer Nature
- p. 217-226
Hadoop Performance Acceleration by Effective Data and Job Placement
- 28 February 2020
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 9 (3) , 3406-3409
Intelligent Cricket Team Selection by Predicting Individual Players’ Performance using Efficient Machine Learning Technique
In any game, selection of best players in a team plays vital role in overall team performance. The team selection in any sport is the key task to ensure good performance of the team. Players are selected based on different criteria. In game of cricket selection of players should consider parameters like players own performance, ground condition, weather forecasting, opposition strength and weakness etc. Machine learning can play vital role in players’ performance prediction. Machine learning uses historical data of team performance and past performance of individual players to predict overall performance of team. Prediction of individual player performance helps in team building process. Recently many researchers proposed model for prediction of player’s performance for a game of cricket. Researchers’ uses machine learning approach for prediction. However existing studies omits some vital features related to ground and weather in their study which have potential to make huge impact on player’s performance. We performed detailed study and literature survey to propose efficient performance prediction of players for game of cricket. Our model will help in best team selection and thus improves overall team performance.
- 28 February 2020
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 9 (3) , 3406-3409
Intelligent Cricket Team Selection by Predicting Individual Players’ Performance using Efficient Machine Learning Technique
In any game, selection of best players in a team plays vital role in overall team performance. The team selection in any sport is the key task to ensure good performance of the team. Players are selected based on different criteria. In game of cricket selection of players should consider parameters like players own performance, ground condition, weather forecasting, opposition strength and weakness etc. Machine learning can play vital role in players’ performance prediction. Machine learning uses historical data of team performance and past performance of individual players to predict overall performance of team. Prediction of individual player performance helps in team building process. Recently many researchers proposed model for prediction of player’s performance for a game of cricket. Researchers’ uses machine learning approach for prediction. However existing studies omits some vital features related to ground and weather in their study which have potential to make huge impact on player’s performance. We performed detailed study and literature survey to propose efficient performance prediction of players for game of cricket. Our model will help in best team selection and thus improves overall team performance.