Rocky Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rocky Kumar has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Gaurav Kumar
Poornima University, India
9 shared publications - Adarsh Kumar Pandey
Poornima University, India
8 shared publications - Sakshi Sharma
Poornima University, India
6 shared publications - Himanshi Sharma
Poornima University, Jaipur, India
4 shared publications - Hemant Kumar Upadhyay
Poornima University Jaipur, India
3 shared publications - Shikha Khullar
Poornima University, Jaipur, India
3 shared publications
Latest Publications
- 30 November 2026
- Published by IGI Global Scientific Publishing
- p. 301-326
AI-Powered Alternatives to Animal Testing
Ethical, scientific and translational limitations of animal testing have increased the global pursuit of high quality, human relevant, biomedical research, toxicological, and drug development alternatives. The combination of artificial intelligence (AI) and cell-based assays, organ-on-chip (OoC) technologies, and computational modelling, is transforming the paradigm of experimental research by promoting predictive, scalable, and ethically responsible research. The chapter gives a general but inclusionary review of AI-based substitutes of animal testing in reference to three pillars of change, including advanced cell-based systems, micro physiological organ-on-chip technology, and AI-enabled virtual bodies (in silico models).The chapter starts with the analysis of the historical dependence on animal models, regulatory/ethical forces behind replacing, minimizing, and refining (3Rs).
- 30 November 2026
- Published by IGI Global Scientific Publishing
- p. 301-326
AI-Powered Alternatives to Animal Testing
Ethical, scientific and translational limitations of animal testing have increased the global pursuit of high quality, human relevant, biomedical research, toxicological, and drug development alternatives. The combination of artificial intelligence (AI) and cell-based assays, organ-on-chip (OoC) technologies, and computational modelling, is transforming the paradigm of experimental research by promoting predictive, scalable, and ethically responsible research. The chapter gives a general but inclusionary review of AI-based substitutes of animal testing in reference to three pillars of change, including advanced cell-based systems, micro physiological organ-on-chip technology, and AI-enabled virtual bodies (in silico models).The chapter starts with the analysis of the historical dependence on animal models, regulatory/ethical forces behind replacing, minimizing, and refining (3Rs).
- 5 November 2026
- Published by IGI Global Scientific Publishing
- p. 263-294
Machine Learning-Driven Intrusion and Anomaly Detection for Advanced Cybersecurity Systems
The fast growth of digital infrastructures and connected systems has made organizations much more vulnerable to highly sophisticated cyber threats. Traditional security mechanisms are often unable to detect changing patterns of attack and zero-day attacks, demonstrating the importance of intelligent and adaptive cybersecurity solutions. Machine learning-based intrusion and anomaly detection systems have become powerful ways of detecting malicious activities and strengthening current cybersecurity systems. This research aims to discuss the application of machine learning methods to detect network intrusions and abnormal system behaviours in advanced cybersecurity environments. By using deep learning system algorithms such as decision tree, support vector machines and deep learning algorithms, these systems aim to analyse large scale network traffic and behavioural data to detect possible threats in real time.
- 5 November 2026
- Published by IGI Global Scientific Publishing
- p. 263-294
Machine Learning-Driven Intrusion and Anomaly Detection for Advanced Cybersecurity Systems
The fast growth of digital infrastructures and connected systems has made organizations much more vulnerable to highly sophisticated cyber threats. Traditional security mechanisms are often unable to detect changing patterns of attack and zero-day attacks, demonstrating the importance of intelligent and adaptive cybersecurity solutions. Machine learning-based intrusion and anomaly detection systems have become powerful ways of detecting malicious activities and strengthening current cybersecurity systems. This research aims to discuss the application of machine learning methods to detect network intrusions and abnormal system behaviours in advanced cybersecurity environments. By using deep learning system algorithms such as decision tree, support vector machines and deep learning algorithms, these systems aim to analyse large scale network traffic and behavioural data to detect possible threats in real time.
- 27 October 2026
- Published by IGI Global Scientific Publishing
- p. 291-326
Digital Earth Twins as Green AI Infrastructures for Sustainable and Intelligent Societies
Digital Earth Twins (DETs) enable sustainable, intelligent societies through a new class of Green AI–powered infrastructures.Utilising the Earth Observation Systems in real-time, Environmental Physics-based models, geospatial intelligence, and Artificial Intelligence, DETs can continuously monitor and forecast climate and environmental threats while ensuring responsible energy and computing performance. This chapter discusses how Green AI principles like hybrid physical-AI modelling, minimised computational overhead, and sustainable AI governance contribute to the ecological and social value-added Digital Earth Twins. Key architectural elements of Digital Earth Twins are discussed, including data pipelines, multimodal integration of geospatial datasets, knowledge graphs, and AI-based simulation engines. The chapter will highlight DET applications for climate resilience; reducing disaster risk; managing water/energy resources; monitoring biodiversity; and promoting sustainable urban development.
- 27 October 2026
- Published by IGI Global Scientific Publishing
- p. 291-326
Digital Earth Twins as Green AI Infrastructures for Sustainable and Intelligent Societies
Digital Earth Twins (DETs) enable sustainable, intelligent societies through a new class of Green AI–powered infrastructures.Utilising the Earth Observation Systems in real-time, Environmental Physics-based models, geospatial intelligence, and Artificial Intelligence, DETs can continuously monitor and forecast climate and environmental threats while ensuring responsible energy and computing performance. This chapter discusses how Green AI principles like hybrid physical-AI modelling, minimised computational overhead, and sustainable AI governance contribute to the ecological and social value-added Digital Earth Twins. Key architectural elements of Digital Earth Twins are discussed, including data pipelines, multimodal integration of geospatial datasets, knowledge graphs, and AI-based simulation engines. The chapter will highlight DET applications for climate resilience; reducing disaster risk; managing water/energy resources; monitoring biodiversity; and promoting sustainable urban development.
- 20 October 2026
- Published by IGI Global Scientific Publishing
- p. 411-440
Artificial Intelligence and Strategic Competition
Artificial Intelligence (AI) is reshaping modern warfare, defense planning, and global security. This chapter compares the military AI strategies of the United States, China, and Russia, focusing on AI-powered warfare, autonomous weapons, cyber operations, intelligence systems, and human–machine collaboration. It examines how each nation leverages AI to strengthen defense capabilities and gain strategic advantages. The analysis highlights the United States' technological leadership through innovation and defense investment, China's rapid advancement via Military-Civil Fusion, and Russia's emphasis on cyber and information warfare. The chapter also discusses challenges such as autonomous warfare risks, strategic stability, and AI governance, while exploring emerging trends including quantum AI, multi-domain operations, and autonomous decision-making systems.
- 20 October 2026
- Published by IGI Global Scientific Publishing
- p. 411-440
Artificial Intelligence and Strategic Competition
Artificial Intelligence (AI) is reshaping modern warfare, defense planning, and global security. This chapter compares the military AI strategies of the United States, China, and Russia, focusing on AI-powered warfare, autonomous weapons, cyber operations, intelligence systems, and human–machine collaboration. It examines how each nation leverages AI to strengthen defense capabilities and gain strategic advantages. The analysis highlights the United States' technological leadership through innovation and defense investment, China's rapid advancement via Military-Civil Fusion, and Russia's emphasis on cyber and information warfare. The chapter also discusses challenges such as autonomous warfare risks, strategic stability, and AI governance, while exploring emerging trends including quantum AI, multi-domain operations, and autonomous decision-making systems.
- 11 September 2026
- Published by IGI Global Scientific Publishing
- p. 227-256
Data-Driven Conversational Intelligence
Artificial Intelligence (AI) has revolutionized digital marketing by enabling personalized, data-driven, and real-time customer interactions. Conversational AI and intelligent chatbots have emerged as powerful tools for enhancing customer engagement, improving service efficiency, and optimizing marketing outcomes. This chapter explores data-driven conversational intelligence and its role in improving chatbot performance within AI-enabled marketing platforms. It examines key technologies such as Natural Language Processing (NLP), Machine Learning (ML), Deep Learning (DL), and conversational analytics. The chapter also discusses optimization techniques, including customer behavior analysis, sentiment analysis, predictive analytics, and recommendation systems. Additionally, it highlights key performance metrics for chatbot evaluation and presents applications across industries such as e-commerce, finance, healthcare, education, and retail. Ethical considerations, including privacy, transparency, algorithmic bias, and responsible AI governance, are also addressed.
- 11 September 2026
- Published by IGI Global Scientific Publishing
- p. 227-256
Data-Driven Conversational Intelligence
Artificial Intelligence (AI) has revolutionized digital marketing by enabling personalized, data-driven, and real-time customer interactions. Conversational AI and intelligent chatbots have emerged as powerful tools for enhancing customer engagement, improving service efficiency, and optimizing marketing outcomes. This chapter explores data-driven conversational intelligence and its role in improving chatbot performance within AI-enabled marketing platforms. It examines key technologies such as Natural Language Processing (NLP), Machine Learning (ML), Deep Learning (DL), and conversational analytics. The chapter also discusses optimization techniques, including customer behavior analysis, sentiment analysis, predictive analytics, and recommendation systems. Additionally, it highlights key performance metrics for chatbot evaluation and presents applications across industries such as e-commerce, finance, healthcare, education, and retail. Ethical considerations, including privacy, transparency, algorithmic bias, and responsible AI governance, are also addressed.
- 7 September 2026
- Published by Taylor & Francis
- p. 76-102
Metaheuristics and Optimization in Agricultural AI
Agricultural systems are critical to the world’s food supply, yet many issues (climate variability, new plant diseases, lack of resources, increasing production demands) pose challenges for food production on a global level today. Artificial intelligence has become prominent in agriculture through the following applications: detecting plant diseases; estimating crop yield; and using precision agriculture. Machine learning and deep learning models perform well; however, numerous attributes related to performance hinder these models. For instance, the data used to train machine learning algorithms is often high-dimensional and contains complex nonlinear relationships; the data may also include errors in measurement and feature selection as well as being costly to tune hyperparameters effectively through traditional grid or random search means. This chapter contains a study of various metaheuristic optimization algorithms designed to optimize artificial intelligence models used within agriculture, including Genetic Algorithms, Particle Swarm Optimization, Ant Colony Optimization, Firefly Algorithm, Differential Evolution, and hybrid optimization design approaches and their associated advantages when optimizing deep learning hyperparameters, selecting optimal features for machine learning algorithms, and creating efficient resource allocation strategies for precision agriculture in plant disease detection. Metaheuristic-based optimization methods are better than conventional techniques in terms of accuracy, convergence rate, and robustness for working with noisy, heterogeneous and high-dimensional agricultural datasets, based on the results of a comparative analysis. In addition to examining technical performance, the chapter also covers practical applications of intelligent irrigation scheduling, fertilizer optimization, drone-path planning, and energy-efficient smart farming systems. It evaluates the major challenges of computational cost, data availability, model interpretability, and the ability to scale the methods across different crops and regions. Future research directions discussed in the chapter are: hybrid optimization models; energy-efficient algorithms; edge-based deployment; and quantum-inspired metaheuristics. In summary, this chapter provides an organized framework for how metaheuristic optimization techniques can be implemented to agricultural AI; thus, bridging the divide between optimization theory and applied agriculture.
- 7 September 2026
- Published by Taylor & Francis
- p. 76-102
Metaheuristics and Optimization in Agricultural AI
Agricultural systems are critical to the world’s food supply, yet many issues (climate variability, new plant diseases, lack of resources, increasing production demands) pose challenges for food production on a global level today. Artificial intelligence has become prominent in agriculture through the following applications: detecting plant diseases; estimating crop yield; and using precision agriculture. Machine learning and deep learning models perform well; however, numerous attributes related to performance hinder these models. For instance, the data used to train machine learning algorithms is often high-dimensional and contains complex nonlinear relationships; the data may also include errors in measurement and feature selection as well as being costly to tune hyperparameters effectively through traditional grid or random search means. This chapter contains a study of various metaheuristic optimization algorithms designed to optimize artificial intelligence models used within agriculture, including Genetic Algorithms, Particle Swarm Optimization, Ant Colony Optimization, Firefly Algorithm, Differential Evolution, and hybrid optimization design approaches and their associated advantages when optimizing deep learning hyperparameters, selecting optimal features for machine learning algorithms, and creating efficient resource allocation strategies for precision agriculture in plant disease detection. Metaheuristic-based optimization methods are better than conventional techniques in terms of accuracy, convergence rate, and robustness for working with noisy, heterogeneous and high-dimensional agricultural datasets, based on the results of a comparative analysis. In addition to examining technical performance, the chapter also covers practical applications of intelligent irrigation scheduling, fertilizer optimization, drone-path planning, and energy-efficient smart farming systems. It evaluates the major challenges of computational cost, data availability, model interpretability, and the ability to scale the methods across different crops and regions. Future research directions discussed in the chapter are: hybrid optimization models; energy-efficient algorithms; edge-based deployment; and quantum-inspired metaheuristics. In summary, this chapter provides an organized framework for how metaheuristic optimization techniques can be implemented to agricultural AI; thus, bridging the divide between optimization theory and applied agriculture.
- 19 August 2026
- Published by IGI Global Scientific Publishing
- p. 205-248
AI-Enabled Neuromorphic Hardware for Secure and Trusted Semiconductor Systems
The growing use of artificial intelligence across edge devices, embedded systems, and autonomous machines has augmented concerns regarding the security of hardware, trustworthiness of data, and long-term dependability of these systems. The limitations of classical CMOS-based architectures in terms of energy efficiency, adaptability, and resistance to attack exacerbate this situation. In this landscape, neuromorphic computing may provide significant value as it pairs architectures that imitate the brain with state-of-the-art non-volatile semiconductor devices. This chapter focuses on the potential of AI-enabled neuromorphic hardware to be the basis for secure and trusted semiconductor systems based on memristors, ferroelectric field-effect transistors (FeFETs), phase-change memory (PCM), and spintronic devices. The chapter reviews device technologies but also explicitly relates intrinsic neuromorphic properties such as plasticity, stochasticity, and in-memory computation to specific hardware attack vectors including side-channel attacks, fault injection, and hardware Trojans.
- 19 August 2026
- Published by IGI Global Scientific Publishing
- p. 205-248
AI-Enabled Neuromorphic Hardware for Secure and Trusted Semiconductor Systems
The growing use of artificial intelligence across edge devices, embedded systems, and autonomous machines has augmented concerns regarding the security of hardware, trustworthiness of data, and long-term dependability of these systems. The limitations of classical CMOS-based architectures in terms of energy efficiency, adaptability, and resistance to attack exacerbate this situation. In this landscape, neuromorphic computing may provide significant value as it pairs architectures that imitate the brain with state-of-the-art non-volatile semiconductor devices. This chapter focuses on the potential of AI-enabled neuromorphic hardware to be the basis for secure and trusted semiconductor systems based on memristors, ferroelectric field-effect transistors (FeFETs), phase-change memory (PCM), and spintronic devices. The chapter reviews device technologies but also explicitly relates intrinsic neuromorphic properties such as plasticity, stochasticity, and in-memory computation to specific hardware attack vectors including side-channel attacks, fault injection, and hardware Trojans.
- 14 August 2026
- Published by IGI Global Scientific Publishing
- p. 419-442
Ethics, Privacy, and Governance in AI-Powered Education
Application of Artificial Intelligence (AI) to the sphere of education has already offered the opportunities of a self-reliant and personalized process of learning, however, it does not cause certain critical issues of morality, privacy, and control. Being intelligent tutoring systems, chatbots, adaptive learning platforms become a part of the classroom and online world, the concerns regarding the safety, transparency, and effectiveness of the algorithm and the ethics of the developers of the algorithm creation become an increasingly more evident one. The AI agents will most likely accumulate and manipulate sensitive student information which must be strictly controlled by the policies in order to promote accountability, fairness and adherence to international privacy laws including GDPR and FERPA.
- 14 August 2026
- Published by IGI Global Scientific Publishing
- p. 419-442
Ethics, Privacy, and Governance in AI-Powered Education
Application of Artificial Intelligence (AI) to the sphere of education has already offered the opportunities of a self-reliant and personalized process of learning, however, it does not cause certain critical issues of morality, privacy, and control. Being intelligent tutoring systems, chatbots, adaptive learning platforms become a part of the classroom and online world, the concerns regarding the safety, transparency, and effectiveness of the algorithm and the ethics of the developers of the algorithm creation become an increasingly more evident one. The AI agents will most likely accumulate and manipulate sensitive student information which must be strictly controlled by the policies in order to promote accountability, fairness and adherence to international privacy laws including GDPR and FERPA.
- 7 August 2026
- Published by IGI Global Scientific Publishing
- p. 335-368
Explainable AI Platforms for Clinical Research and Precision Medicine
The integration of Artificial Intelligence (AI) into clinical research and precision medicine has been rapid and has revolutionized the data-driven innovation in the healthcare space. However, the growing dependence on complex machine learning and deep learning models has raised serious concerns about the lack of transparency, interpretability and trust in the models. Black-box AI systems can also limit clinician confidence, make it very difficult to get systems approved by regulators, and create tensions at the patient-facing decision-making level. This chapter examines the establishment and how to employ Explainable Artificial Intelligence (XAI) platforms adaptively towards clinical research ecosystem and precision medicine applications. It offers a day-to-day structured multi-layer design fitting data governance, predictive models, explainability engines and human in-the-loop validation mechanism. Special emphasis is placed on artificial intelligence-based patient recruitment; risk stratification; treatment individualisation; clinical decision support systems.
- 7 August 2026
- Published by IGI Global Scientific Publishing
- p. 335-368
Explainable AI Platforms for Clinical Research and Precision Medicine
The integration of Artificial Intelligence (AI) into clinical research and precision medicine has been rapid and has revolutionized the data-driven innovation in the healthcare space. However, the growing dependence on complex machine learning and deep learning models has raised serious concerns about the lack of transparency, interpretability and trust in the models. Black-box AI systems can also limit clinician confidence, make it very difficult to get systems approved by regulators, and create tensions at the patient-facing decision-making level. This chapter examines the establishment and how to employ Explainable Artificial Intelligence (XAI) platforms adaptively towards clinical research ecosystem and precision medicine applications. It offers a day-to-day structured multi-layer design fitting data governance, predictive models, explainability engines and human in-the-loop validation mechanism. Special emphasis is placed on artificial intelligence-based patient recruitment; risk stratification; treatment individualisation; clinical decision support systems.
- 31 July 2026
- Published by IGI Global Scientific Publishing
- p. 27-58
Parallel Computing and Blockchain for AI-Driven Cybersecurity
The multiplication of digital infrastructures and cloud services and of cyber-physical systems connected with each other has resulted in the significant growth of cybersecurity challenges. Traditional security mechanisms are usually not qualified to process large quantities of security data and identify complex cyber threats in real-time. The combination of artificial intelligence (AI), parallel computing, and blockchain technologies show a promising way forward on creating secure, scalable and resilient cybersecurity frameworks for distributed digital infrastructures. This Chapter puts forth a conceptual framework that incorporates parallel computing architectures and block-chain enabled security mechanisms in order to increase the efficiency and trustworthiness of AI-enabled Cybersecurity systems. Parallel computing helps high-performance processing of big amounts of network traffic and security logs, so that AI models can perform better analysis of picker threat patterns and find out anomalies more efficiently.
- 31 July 2026
- Published by IGI Global Scientific Publishing
- p. 27-58
Parallel Computing and Blockchain for AI-Driven Cybersecurity
The multiplication of digital infrastructures and cloud services and of cyber-physical systems connected with each other has resulted in the significant growth of cybersecurity challenges. Traditional security mechanisms are usually not qualified to process large quantities of security data and identify complex cyber threats in real-time. The combination of artificial intelligence (AI), parallel computing, and blockchain technologies show a promising way forward on creating secure, scalable and resilient cybersecurity frameworks for distributed digital infrastructures. This Chapter puts forth a conceptual framework that incorporates parallel computing architectures and block-chain enabled security mechanisms in order to increase the efficiency and trustworthiness of AI-enabled Cybersecurity systems. Parallel computing helps high-performance processing of big amounts of network traffic and security logs, so that AI models can perform better analysis of picker threat patterns and find out anomalies more efficiently.