Saurabh Bhattacharya
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
Saurabh Bhattacharya has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Manju Pandey
National Institutes of Technology, Raipur, India
4 shared publications Manju Pandey
Department of Computer Applications, National Institute of Technology Raipur, Raipur, India
3 shared publications- Dharmesh Dhabliya
Vishwakarma Institute of Technology, Pune, Maharashtra, India
2 shared publications - Monali Gulhane
Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, Maharashtra, India
2 shared publications - Nitin Rakesh
Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India
2 shared publications - Prashant Dhage
Symbiosis International (Deemed University)
2 shared publications
Latest Publications
- 31 October 2026
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 47 (10) , 3741-3752
Privacy-preserving AI-driven healthcare analytics in post-quantum clouds
Healthcare analytics leverages Artificial Intelligence and Cloud Computing in disease prediction, Clinical Decisions Making, Personalized Treatment and Remote M...
- 31 October 2026
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 47 (10) , 3741-3752
Privacy-preserving AI-driven healthcare analytics in post-quantum clouds
Healthcare analytics leverages Artificial Intelligence and Cloud Computing in disease prediction, Clinical Decisions Making, Personalized Treatment and Remote M...
- Open Access
- 17 February 2026
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 7 (1s) , 389–398
PREDICTIVE ANALYSIS FOR CAREER GROWTH IN PERFORMING ARTS
Career growth in the performing arts has become a critical research direction as the careers of artistic professionals are becoming more and more data-driven and competitive. Contrary to traditional career trajectories, the performance art industry success depends on a multifaceted interaction of both technical capabilities, training level, audience acceptance, career contact network and subjective judgments. The paper suggests a more detailed predictive analytics model to simulate and predict career development paths of performing artists through a combination of quantitative performance metrics with qualitative predictors of portfolios, reviews, and sentiment analysis. The model integrates machine-learning-based classification-models with time-series forecasting in order to achieve both the status at present and longitudinal developmental patterns of the career. The structured dataset containing training history, audition results, performance, and engagement are preprocessed by applying feature engineering, normalization, encoding and imbalance control methods. Random Forest, XGBoost, Support Vector Machines, and Artificial Neural Networks are used to perform predictive modeling to calculate the likelihood of career progression in multiple horizons. Also, sentiment analysis of reviews, social media response and expert commentaries are also included to refine the predictive accuracy and contextual relevance. Experimental findings originate to show that ensemble and deep learning models are superior compared to conventional ones in modelling nonlinear connections and time-varying effects of artistic careers.
- 17 February 2026
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 7 (1s) , 389–398
Open AccessPREDICTIVE ANALYSIS FOR CAREER GROWTH IN PERFORMING ARTS
Career growth in the performing arts has become a critical research direction as the careers of artistic professionals are becoming more and more data-driven and competitive. Contrary to traditional career trajectories, the performance art industry success depends on a multifaceted interaction of both technical capabilities, training level, audience acceptance, career contact network and subjective judgments. The paper suggests a more detailed predictive analytics model to simulate and predict career development paths of performing artists through a combination of quantitative performance metrics with qualitative predictors of portfolios, reviews, and sentiment analysis. The model integrates machine-learning-based classification-models with time-series forecasting in order to achieve both the status at present and longitudinal developmental patterns of the career. The structured dataset containing training history, audition results, performance, and engagement are preprocessed by applying feature engineering, normalization, encoding and imbalance control methods. Random Forest, XGBoost, Support Vector Machines, and Artificial Neural Networks are used to perform predictive modeling to calculate the likelihood of career progression in multiple horizons. Also, sentiment analysis of reviews, social media response and expert commentaries are also included to refine the predictive accuracy and contextual relevance. Experimental findings originate to show that ensemble and deep learning models are superior compared to conventional ones in modelling nonlinear connections and time-varying effects of artistic careers.
- 1 March 2025
- Published by Springer Nature
- p. 441-449
Predictive Analytics for Cybersecurity Using AI and ML: An Ensemble Approach
- 1 March 2025
- Published by Springer Nature
- p. 441-449
Predictive Analytics for Cybersecurity Using AI and ML: An Ensemble Approach
- 1 March 2025
- Published by Springer Nature
- p. 451-462
Collaborative Defense Strategies: AI, ML, and Cybersecurity: A Comprehensive Study
- 1 March 2025
- Published by Springer Nature
- p. 451-462
Collaborative Defense Strategies: AI, ML, and Cybersecurity: A Comprehensive Study
- Open Access
- 23 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Building a Unified Framework to Standardize and Improve Interoperability in IoT Systems
- 23 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessBuilding a Unified Framework to Standardize and Improve Interoperability in IoT Systems
- Open Access
- 23 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Improving Healthcare with Remote Patient Monitoring and Real-Time Data Analytics Using IoT
- 23 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessImproving Healthcare with Remote Patient Monitoring and Real-Time Data Analytics Using IoT
- Open Access
- 21 December 2024
- Published by Auricle Global Society of Education and Research in Computer Fraud and Security
- p. 117-125
Quantum Cryptography: Enhancing Security in Quantum Computing Environments
When it comes to protecting data, quantum security is a huge step forward, especially in settings with quantum computers. The development of quantum technologies makes standard encryption methods more open to attacks from quantum computers that can use their computing power to break common encryption protocols. This essay looks into the basic ideas of quantum cryptography, with a focus on Quantum Key Distribution (QKD) as a key part of safe communication. Quantum key distribution (QKD) uses quantum physics ideas like superposition and entanglement to help two people make a shared secret key that can't be hacked. The paper talks about different QKD methods, like BB84 and E91, and looks at how they work and what security promises they offer. We look at the problems that come up with real-world uses, like flawed devices and influence from the surroundings, which can affect how accurate quantum states are.
- 21 December 2024
- Published by Auricle Global Society of Education and Research in Computer Fraud and Security
- p. 117-125
Open AccessQuantum Cryptography: Enhancing Security in Quantum Computing Environments
When it comes to protecting data, quantum security is a huge step forward, especially in settings with quantum computers. The development of quantum technologies makes standard encryption methods more open to attacks from quantum computers that can use their computing power to break common encryption protocols. This essay looks into the basic ideas of quantum cryptography, with a focus on Quantum Key Distribution (QKD) as a key part of safe communication. Quantum key distribution (QKD) uses quantum physics ideas like superposition and entanglement to help two people make a shared secret key that can't be hacked. The paper talks about different QKD methods, like BB84 and E91, and looks at how they work and what security promises they offer. We look at the problems that come up with real-world uses, like flawed devices and influence from the surroundings, which can affect how accurate quantum states are.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (3) , 6250-6261
PCFRIMDS: Smart Next-Generation Approach for Precision Crop and Fertilizer Recommendations Using Integrated Multimodal Data Fusion for Sustainable Agriculture
The demand for sustainable agricultural practices continues to rise, highlighting the need for precise crop and fertilizer recommendations to optimize yield while minimizing environmental impacts. Traditional methods often struggle to achieve this precision due to limitations in integrating diverse data sources and efficiently processing complex interactions. This paper addresses this challenge by introducing a novel methodology that seamlessly integrates multimodal data sources, including NPK values, moisture content, image analysis, and geographical information, to provide accurate and customized recommendations for crops and fertilizers. The proposed methodology employs a systematic fusion of Frequency patterns, entropy patterns, S Transform components, and convolutional components extracted from the data sources. These components are then transformed into Bidirectional Gated Recurrent Unit (BiGRU) features, which are meticulously selected using an exclusively designed Ant Lion Fuzzy Principal Component Analyzer (ALFPCA). The selected features are further processed through our Graph Convolutional FPMax Model (GCFPMax) for crop recommendations and our Recurrent FPMax Model (RFPMax) for fertilizer recommendations. The findings demonstrate that our proposed model significantly enhances the precision of crop recommendations by 3.5%, accuracy by 4.9%, recall by 2.5%, area under the curve (AUC) by 3.9%, and specificity by 2.9% while concurrently reducing the delay by 8.3%. Similarly, the precision of fertilizer recommendations improved by 1.9%, accuracy by 2.5%, recall by 3.5%, AUC by 3.9%, and Specificity by 4.5%, with a delay reduction of 8.5%. The significant improvements in recommendation accuracy and efficiency highlight our approach’s transformative impact on achieving sustainable farming practices.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (3) , 6250-6261
PCFRIMDS: Smart Next-Generation Approach for Precision Crop and Fertilizer Recommendations Using Integrated Multimodal Data Fusion for Sustainable Agriculture
The demand for sustainable agricultural practices continues to rise, highlighting the need for precise crop and fertilizer recommendations to optimize yield while minimizing environmental impacts. Traditional methods often struggle to achieve this precision due to limitations in integrating diverse data sources and efficiently processing complex interactions. This paper addresses this challenge by introducing a novel methodology that seamlessly integrates multimodal data sources, including NPK values, moisture content, image analysis, and geographical information, to provide accurate and customized recommendations for crops and fertilizers. The proposed methodology employs a systematic fusion of Frequency patterns, entropy patterns, S Transform components, and convolutional components extracted from the data sources. These components are then transformed into Bidirectional Gated Recurrent Unit (BiGRU) features, which are meticulously selected using an exclusively designed Ant Lion Fuzzy Principal Component Analyzer (ALFPCA). The selected features are further processed through our Graph Convolutional FPMax Model (GCFPMax) for crop recommendations and our Recurrent FPMax Model (RFPMax) for fertilizer recommendations. The findings demonstrate that our proposed model significantly enhances the precision of crop recommendations by 3.5%, accuracy by 4.9%, recall by 2.5%, area under the curve (AUC) by 3.9%, and specificity by 2.9% while concurrently reducing the delay by 8.3%. Similarly, the precision of fertilizer recommendations improved by 1.9%, accuracy by 2.5%, recall by 3.5%, AUC by 3.9%, and Specificity by 4.5%, with a delay reduction of 8.5%. The significant improvements in recommendation accuracy and efficiency highlight our approach’s transformative impact on achieving sustainable farming practices.
- Open Access
- 1 January 2024
- Published by Science Research Society
- Vol. 20 (1s) , 269-288
Enhancing Agricultural Knowledge Management using an efficient & Novel Ontology-Based Approach Leveraging BERT-GPT and Graph Recurrent Q Learning Network
Agriculture, as one of the key drivers for human civilization, demands efficient methods for managing the extensive domain-specific knowledge. While ontologies, structured sets of terms and relationships within a specific domain, have played a pivotal role in structuring agricultural data, existing models lack the precision and adaptability necessary for the dynamic agricultural environment. This paper proposes a novel framework that integrates the strengths of BERT (Bidirectional Encoder Representations from Transformers) GPT (Generative Pre-trained Transformer), and Graph Recurrent Q Learning Network (GRQLN) for developing a dynamic and efficient ontology tool. BERT-GPT, with its powerful natural language processing capabilities, allows for accurate feature extraction from diverse text data, including government and farming sources. Meanwhile, GRQLN leverages graph neural networks and reinforcement learning to convert these features into an ontology graph, optimizing the representation process. The integration of these advanced technologies not only addresses the limitations of existing models but also enhances the precision of ontological query retrieval by 8.5%, accuracy by 8.3%, recall by 10.4%, AUC by 9.5%, and specificity by 9.4%, while reducing delay by 4.5%. The proposed model is a significant contribution to the field, offering a robust tool that empowers stakeholders with actionable insights derived from a vast expanse of agricultural knowledge, ultimately facilitating informed decision-making in the ever-evolving landscape of agricultural operations.
- 1 January 2024
- Published by Science Research Society
- Vol. 20 (1s) , 269-288
Open AccessEnhancing Agricultural Knowledge Management using an efficient & Novel Ontology-Based Approach Leveraging BERT-GPT and Graph Recurrent Q Learning Network
Agriculture, as one of the key drivers for human civilization, demands efficient methods for managing the extensive domain-specific knowledge. While ontologies, structured sets of terms and relationships within a specific domain, have played a pivotal role in structuring agricultural data, existing models lack the precision and adaptability necessary for the dynamic agricultural environment. This paper proposes a novel framework that integrates the strengths of BERT (Bidirectional Encoder Representations from Transformers) GPT (Generative Pre-trained Transformer), and Graph Recurrent Q Learning Network (GRQLN) for developing a dynamic and efficient ontology tool. BERT-GPT, with its powerful natural language processing capabilities, allows for accurate feature extraction from diverse text data, including government and farming sources. Meanwhile, GRQLN leverages graph neural networks and reinforcement learning to convert these features into an ontology graph, optimizing the representation process. The integration of these advanced technologies not only addresses the limitations of existing models but also enhances the precision of ontological query retrieval by 8.5%, accuracy by 8.3%, recall by 10.4%, AUC by 9.5%, and specificity by 9.4%, while reducing delay by 4.5%. The proposed model is a significant contribution to the field, offering a robust tool that empowers stakeholders with actionable insights derived from a vast expanse of agricultural knowledge, ultimately facilitating informed decision-making in the ever-evolving landscape of agricultural operations.