Harish Reddy Gantla
Research Subjects
Harish Reddy Gantla has a total of 102 co-authors. Here are the top co-authors by number of shared publications:
- Udit Mamodiya
Faculty of Engineering and Technology, Poornima University, Jaipur, India
7 shared publications - Subarno Bhattacharyya
O.P. Jindal Global University, India
3 shared publications - Indra Kishor
Poornima Institute of Engineering and Technology, Jaipur, India
2 shared publications Parul Goyal
M.M. Engineering College, Maharishi Markandeshwar University, India
2 shared publicationsR. Thamizhamuthu
SRM Institute of Science and Technology, India
2 shared publications- Sayed Sayeed Ahmad
De Montfort University, Dubai, UAE
2 shared publications
Latest Publications
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 299-324
Machine Learning and AI-Driven Smart Sensing Technologies for Accurate Detection of Adulterated Food Products
This study suggests an AI-based multimodal smart sensing system to accurately and timely detect adulterated food products using intelligent sensing and machine learning technologies. The framework is a fusion of the four techniques of spectroscopy, hyperspectral imaging, impedance sensing, gas sensing, and the 5th of IoT-based environmental monitoring within an adaptive multimodal learning architecture. The experimental data were obtained by spiking milk, honey, turmeric powder, coffee powder, olive oil, red pepper powder and processed meat products with varying environmental conditions. For classification, deep learning, ensemble learning, and adaptive feature fusion techniques were used and for real-time deployment on the edge, deep learning was used. With the proposed framework, classification accuracy was 98.14% on average, and the robustness was excellent in noisy and dynamic operational conditions.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 299-324
Machine Learning and AI-Driven Smart Sensing Technologies for Accurate Detection of Adulterated Food Products
This study suggests an AI-based multimodal smart sensing system to accurately and timely detect adulterated food products using intelligent sensing and machine learning technologies. The framework is a fusion of the four techniques of spectroscopy, hyperspectral imaging, impedance sensing, gas sensing, and the 5th of IoT-based environmental monitoring within an adaptive multimodal learning architecture. The experimental data were obtained by spiking milk, honey, turmeric powder, coffee powder, olive oil, red pepper powder and processed meat products with varying environmental conditions. For classification, deep learning, ensemble learning, and adaptive feature fusion techniques were used and for real-time deployment on the edge, deep learning was used. With the proposed framework, classification accuracy was 98.14% on average, and the robustness was excellent in noisy and dynamic operational conditions.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 215-238
Emerging Cybersecurity Challenges in Machine Learning-Enabled Smart Heterogeneous Networks
The chapter tries to resolve this emerging problem of machine learning-based smart heterogeneous networks, and cybersecurity by creating a multi-layered security infrastructure which is scalable to detect and react to security attacks in real-time. It proposes a multi-modal deep learning (CNNLSTM), adaptive control by reinforcement learning, and privacy-sensitive controls, such as federated learning. Heterogeneous datasets, including the IoT traffic, intrusion detection benchmarks, and multi-step attack scenarios, which are synthetic, are trained and tested with the model. The accuracy, precision, recall, F1-score, AUC-ROC, and the computational efficiency metrics are used to measure the performance in dynamic and noisy settings. The suggested framework is also a better performer than the baseline models, where accuracy is 98.37 and has a better ability to resist multi-step and evolving cyber threats. Integration of reinforcement learning increases adaptability and multi-modal features fusion increases detection accuracy.
- 25 September 2026
- Published by IGI Global Scientific Publishing
- p. 215-238
Emerging Cybersecurity Challenges in Machine Learning-Enabled Smart Heterogeneous Networks
The chapter tries to resolve this emerging problem of machine learning-based smart heterogeneous networks, and cybersecurity by creating a multi-layered security infrastructure which is scalable to detect and react to security attacks in real-time. It proposes a multi-modal deep learning (CNNLSTM), adaptive control by reinforcement learning, and privacy-sensitive controls, such as federated learning. Heterogeneous datasets, including the IoT traffic, intrusion detection benchmarks, and multi-step attack scenarios, which are synthetic, are trained and tested with the model. The accuracy, precision, recall, F1-score, AUC-ROC, and the computational efficiency metrics are used to measure the performance in dynamic and noisy settings. The suggested framework is also a better performer than the baseline models, where accuracy is 98.37 and has a better ability to resist multi-step and evolving cyber threats. Integration of reinforcement learning increases adaptability and multi-modal features fusion increases detection accuracy.
- 29 July 2026
- Published by Springer Nature
- p. 299-310
Unveiling the Unseen Realms of Melanoma Through Deep Transfer Learning
- 29 July 2026
- Published by Springer Nature
- p. 299-310
Unveiling the Unseen Realms of Melanoma Through Deep Transfer Learning
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 1-34
Digital Forensics in the Age of Artificial Intelligence
The scale, heterogeneity, and velocity of modern digital evidence have outpaced traditional forensic workflows, while existing AI-based solutions often lack explainability and legal defensibility. This chapter proposes an AI-driven digital forensic framework integrating automated evidence acquisition, multimodal correlation, explainable inference, and human-in-the-loop validation. The methodology emphasizes behavior-centric reconstruction, confidence quantification, and adversarial robustness to ensure forensic soundness. Experimental evaluation on heterogeneous forensic datasets shows that the proposed framework achieves 91.6% evidence detection accuracy, reducing the false positive rate to 7.3%, compared to 82–87% accuracy and 10–13% false positives reported in recent AI-based forensic approaches. Investigator trust scores improved to 4.6/5, outperforming post-hoc explainability baselines (3.4–4.2/5), while maintaining near-linear scalability under increasing evidence volume.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 1-34
Digital Forensics in the Age of Artificial Intelligence
The scale, heterogeneity, and velocity of modern digital evidence have outpaced traditional forensic workflows, while existing AI-based solutions often lack explainability and legal defensibility. This chapter proposes an AI-driven digital forensic framework integrating automated evidence acquisition, multimodal correlation, explainable inference, and human-in-the-loop validation. The methodology emphasizes behavior-centric reconstruction, confidence quantification, and adversarial robustness to ensure forensic soundness. Experimental evaluation on heterogeneous forensic datasets shows that the proposed framework achieves 91.6% evidence detection accuracy, reducing the false positive rate to 7.3%, compared to 82–87% accuracy and 10–13% false positives reported in recent AI-based forensic approaches. Investigator trust scores improved to 4.6/5, outperforming post-hoc explainability baselines (3.4–4.2/5), while maintaining near-linear scalability under increasing evidence volume.
- 24 March 2026
- Published by Springer Nature
- p. 45-61
A Federated Learning Framework for Privacy-Preserving Healthcare Diagnostics Using Biomedical Signal Analysis
- 24 March 2026
- Published by Springer Nature
- p. 45-61
A Federated Learning Framework for Privacy-Preserving Healthcare Diagnostics Using Biomedical Signal Analysis
- 24 March 2026
- Published by Springer Nature
- p. 324-340
An Intelligent Hybrid Framework of Genetic Algorithms and Neural Networks for Climate Prediction
- 24 March 2026
- Published by Springer Nature
- p. 324-340
An Intelligent Hybrid Framework of Genetic Algorithms and Neural Networks for Climate Prediction
- 6 March 2026
- Published by IGI Global Scientific Publishing
- p. 159-186
Education and E-Governance in the Age of Digital Transformation
The sudden explosion into the digital revolution has essentially changed the operational role of the government and institutions and revealed dramatic inequalities in technological preparedness and institutional flexibility. Digital reforms in most developing settings have become unfortunate failures in that technologies may evolve faster than model strategies could keep pace causing a disparity between access and resilience. In order to fill these gaps, a Resilience-Oriented Digital Transformation Framework (RDTF) is introduced in the study to establish a computational model with technological, institutional, and human-capacity layer, which leads to an integrated framework to describe institutional maturity. To represent interdependencies in the three layers and describe a dynamic measure of systemic and stable robustness, we used a Digital Transformation Resilience Index (DTRI) by the use of weighted normalization and adaptive aggregation.
- 6 March 2026
- Published by IGI Global Scientific Publishing
- p. 159-186
Education and E-Governance in the Age of Digital Transformation
The sudden explosion into the digital revolution has essentially changed the operational role of the government and institutions and revealed dramatic inequalities in technological preparedness and institutional flexibility. Digital reforms in most developing settings have become unfortunate failures in that technologies may evolve faster than model strategies could keep pace causing a disparity between access and resilience. In order to fill these gaps, a Resilience-Oriented Digital Transformation Framework (RDTF) is introduced in the study to establish a computational model with technological, institutional, and human-capacity layer, which leads to an integrated framework to describe institutional maturity. To represent interdependencies in the three layers and describe a dynamic measure of systemic and stable robustness, we used a Digital Transformation Resilience Index (DTRI) by the use of weighted normalization and adaptive aggregation.
- 20 February 2026
- Published by IGI Global Scientific Publishing
- p. 1-32
Integrating Neuromorphic and Quantum Computing Paradigms for Real-Time Internet of Things Analytics
The explosive increase in the number of Internet of Things (IoT) deployments has increased the pressure on analytics systems that are capable of functioning in real time without being power-intensive and scalable in the presence of unlimited amounts of data. Traditional cloud-based and even edge-based AI systems are unable to strike a balance between the low-latency requirements and the in-depth analytical reasoning, especially when the level of data uncertainty and the scale of the system grows. The hybrid neuromorphic-quantum analytics model suggested in this paper integrates event-driven spiking neuromorphic quantum-assisted inference selectively invoked on complex or uncertain cases, that is, on the edge with event-driven spiking neural networks. The neuromorphic processing deals with inference with high frequency and low latency, and quantum analytics is triggered because of the confidencebased orchestration to decide on ambivalent pattern and global correlations.
- 20 February 2026
- Published by IGI Global Scientific Publishing
- p. 1-32
Integrating Neuromorphic and Quantum Computing Paradigms for Real-Time Internet of Things Analytics
The explosive increase in the number of Internet of Things (IoT) deployments has increased the pressure on analytics systems that are capable of functioning in real time without being power-intensive and scalable in the presence of unlimited amounts of data. Traditional cloud-based and even edge-based AI systems are unable to strike a balance between the low-latency requirements and the in-depth analytical reasoning, especially when the level of data uncertainty and the scale of the system grows. The hybrid neuromorphic-quantum analytics model suggested in this paper integrates event-driven spiking neuromorphic quantum-assisted inference selectively invoked on complex or uncertain cases, that is, on the edge with event-driven spiking neural networks. The neuromorphic processing deals with inference with high frequency and low latency, and quantum analytics is triggered because of the confidencebased orchestration to decide on ambivalent pattern and global correlations.
- 20 February 2026
- Published by IGI Global Scientific Publishing
- p. 303-332
Quantum-Enhanced Neuromorphic Computing for Real-World Applications in Vision Speech Healthcare and Smart Cities
Smart systems deployed in vision, speech, healthcare, and smart city settings are increasingly working under severe requirements of latency, energy use and uncertainty, revealing inherent weaknesses in standard deep learning methods, as well as in single- shots of quantum computing. Although both neuromorphic computing and quantum-enhanced learning have been demonstrated to be promising, independently, neither approach can provide a tradeoff between real-time performance and global reasoning. This paper discusses the absence of a single and deployment focused model that would bring neuromorphic efficiency and quantum expressiveness to a single system. In our proposal, a quantum-enhanced neuromorphic computing system, event-driven spiking neural networks are used to do continuous, low-power perception and quantum-assisted machinery used to invoke uncertainty-aware classification and global optimization.
- 20 February 2026
- Published by IGI Global Scientific Publishing
- p. 303-332
Quantum-Enhanced Neuromorphic Computing for Real-World Applications in Vision Speech Healthcare and Smart Cities
Smart systems deployed in vision, speech, healthcare, and smart city settings are increasingly working under severe requirements of latency, energy use and uncertainty, revealing inherent weaknesses in standard deep learning methods, as well as in single- shots of quantum computing. Although both neuromorphic computing and quantum-enhanced learning have been demonstrated to be promising, independently, neither approach can provide a tradeoff between real-time performance and global reasoning. This paper discusses the absence of a single and deployment focused model that would bring neuromorphic efficiency and quantum expressiveness to a single system. In our proposal, a quantum-enhanced neuromorphic computing system, event-driven spiking neural networks are used to do continuous, low-power perception and quantum-assisted machinery used to invoke uncertainty-aware classification and global optimization.
- 14 November 2025
- Published by IGI Global Scientific Publishing
- p. 289-312
Benchmarking the Robustness of Federated Learning Frameworks Under Adversarial Conditions
Federated Learning (FL) has emerged as a promising instance that enables collaborative model training to be delivered while the privacy. However, its decentralized nature reveals FL systems at significant risks, including data and model poisoning, Byzantine failures, and privacy forecast attacks, which weaken the strength and reliability. This chapter presents a comprehensive benchmarking study of the widely adopted FL framework in anti -anti -conditions. We provide an overview of threats and evaluation methods using a certification matrix and attack simulation. Benchmarking results highlight both strengths and limitations, showing the main trade-off between safety, measurement, and efficiency. We discuss defense techniques such as stronger consolidation, discrepancies, differential privacy, and anti-training. The real-world case studies of healthcare, finance, and IOT show practical effects. In the end, we outline open challenges and future directions to enable secure and trusted FL systems.
- 14 November 2025
- Published by IGI Global Scientific Publishing
- p. 289-312
Benchmarking the Robustness of Federated Learning Frameworks Under Adversarial Conditions
Federated Learning (FL) has emerged as a promising instance that enables collaborative model training to be delivered while the privacy. However, its decentralized nature reveals FL systems at significant risks, including data and model poisoning, Byzantine failures, and privacy forecast attacks, which weaken the strength and reliability. This chapter presents a comprehensive benchmarking study of the widely adopted FL framework in anti -anti -conditions. We provide an overview of threats and evaluation methods using a certification matrix and attack simulation. Benchmarking results highlight both strengths and limitations, showing the main trade-off between safety, measurement, and efficiency. We discuss defense techniques such as stronger consolidation, discrepancies, differential privacy, and anti-training. The real-world case studies of healthcare, finance, and IOT show practical effects. In the end, we outline open challenges and future directions to enable secure and trusted FL systems.