Mallareddy Adudhodla
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mallareddy Adudhodla has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Niladri Maiti
Central Asian University
2 shared publications - Ramesh N. Koppar
Department of Computer Science & Engineering, Sai Vidya Institute of Technology, Rajanukunte, Bangalore, India
2 shared publications - Shashank Shekhar Tiwari
Department of Information Technology Rajkiya Engineering College Ambedkar Nagar
2 shared publications - Vasavi Bande
Department of Information Technology, Maturi Venkata Subbarao (MVSR) Engineering College, Hyderabad, India
2 shared publications - .M. Pounambal
Vellore Institute of Technology
1 shared publication - Akash Jain
Shri Shankaracharya Institute of Professional Management and Technology
1 shared publication
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 49-65
Edge Computing and IoT for Efficient Healthcare Data Processing
- 2 July 2026
- Published by Springer Nature
- p. 49-65
Edge Computing and IoT for Efficient Healthcare Data Processing
- 2 July 2026
- Published by Springer Nature
- p. 67-80
Deep Learning for Disease Prediction and Early Diagnosis
- 2 July 2026
- Published by Springer Nature
- p. 67-80
Deep Learning for Disease Prediction and Early Diagnosis
- 26 July 2025
- Published by Springer Nature in International Journal of Information Technology
- p. 1-7
Deep learning-based steganography framework to enhance ad-hoc cloud security
- 26 July 2025
- Published by Springer Nature in International Journal of Information Technology
- p. 1-7
Deep learning-based steganography framework to enhance ad-hoc cloud security
- 25 July 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 17 (8) , 4687-4693
Dynamic fuzzy logic model for adaptive driver drowsiness detection systems
- 25 July 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 17 (8) , 4687-4693
Dynamic fuzzy logic model for adaptive driver drowsiness detection systems
- Open Access
- 2 July 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- p. 95-101
Federated Learning and Cryptography: A Secure Framework for IoT Data Privacy
As the Internet of Things (IoT) continues to expand, the protection of user data privacy and the security of IoT systems have become increasingly critical. This paper proposes a secure framework that integrates Federated Learning (FL) with advanced cryptographic techniques to address privacy concerns while enabling collaborative machine learning across heterogeneous IoT devices. The proposed framework allows local data processing on IoT devices, ensuring that sensitive information remains decentralized and is never exposed to potential breaches during model training. By employing techniques such as Additive Homomorphic Encryption (AHE) and Secure Multi-Party Computation (SMPC), our approach enables the secure aggregation of model updates while maintaining data confidentiality and integrity. Furthermore, the framework effectively minimizes communication overhead and computational demands, making it suitable for resource-constrained IoT environments. This study not only enhances privacy protections and data security but also improves the efficiency of data analytics in smart cities, healthcare, and industrial applications. Future work will investigate the scalability and adaptability of this framework in real-world scenarios, paving the way for a more secure and privacy-oriented IoT ecosystem.
- 2 July 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- p. 95-101
Open AccessFederated Learning and Cryptography: A Secure Framework for IoT Data Privacy
As the Internet of Things (IoT) continues to expand, the protection of user data privacy and the security of IoT systems have become increasingly critical. This paper proposes a secure framework that integrates Federated Learning (FL) with advanced cryptographic techniques to address privacy concerns while enabling collaborative machine learning across heterogeneous IoT devices. The proposed framework allows local data processing on IoT devices, ensuring that sensitive information remains decentralized and is never exposed to potential breaches during model training. By employing techniques such as Additive Homomorphic Encryption (AHE) and Secure Multi-Party Computation (SMPC), our approach enables the secure aggregation of model updates while maintaining data confidentiality and integrity. Furthermore, the framework effectively minimizes communication overhead and computational demands, making it suitable for resource-constrained IoT environments. This study not only enhances privacy protections and data security but also improves the efficiency of data analytics in smart cities, healthcare, and industrial applications. Future work will investigate the scalability and adaptability of this framework in real-world scenarios, paving the way for a more secure and privacy-oriented IoT ecosystem.
- Open Access
- 2 July 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- p. 102-110
Explainable AI And Blockchain: Interpretable Machine Learning Models With Cryptographic Security For Critical Decision-Making
Explainable Artificial Intelligence (XAI) is crucial for ensuring trust and transparency in AI systems, especially in critical decision-making scenarios (IBM). As AI becomes more integrated into various sectors, understanding how these systems arrive at specific outputs is essential for accountability and ethical considerations (IBM). This essay explores the intersection of XAI and blockchain technology, focusing on the development of interpretable machine learning models with cryptographic security (1 Block XAI: Review of Blockchain for Explainable Artificial Intelligence). Blockchain's decentralized and immutable nature can provide a robust framework for XAI, ensuring that AI decision-making processes are transparent, auditable, and secure (IBM). This study investigates various interpretable machine learning models, such as decision trees and linear regression, and their integration with cryptographic techniques to enhance data privacy and security (Christoph Molnar). By leveraging blockchain's cryptographic features, sensitive data used in AI models can be protected, while XAI techniques provide insights into the model's decision-making process (Nalini). The synergy between XAI and blockchain offers a promising approach for building trustworthy AI systems that can be confidently deployed in high-stakes applications, promoting transparency and accountability in AI-driven decisions (IBM).
- 2 July 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- p. 102-110
Open AccessExplainable AI And Blockchain: Interpretable Machine Learning Models With Cryptographic Security For Critical Decision-Making
Explainable Artificial Intelligence (XAI) is crucial for ensuring trust and transparency in AI systems, especially in critical decision-making scenarios (IBM). As AI becomes more integrated into various sectors, understanding how these systems arrive at specific outputs is essential for accountability and ethical considerations (IBM). This essay explores the intersection of XAI and blockchain technology, focusing on the development of interpretable machine learning models with cryptographic security (1 Block XAI: Review of Blockchain for Explainable Artificial Intelligence). Blockchain's decentralized and immutable nature can provide a robust framework for XAI, ensuring that AI decision-making processes are transparent, auditable, and secure (IBM). This study investigates various interpretable machine learning models, such as decision trees and linear regression, and their integration with cryptographic techniques to enhance data privacy and security (Christoph Molnar). By leveraging blockchain's cryptographic features, sensitive data used in AI models can be protected, while XAI techniques provide insights into the model's decision-making process (Nalini). The synergy between XAI and blockchain offers a promising approach for building trustworthy AI systems that can be confidently deployed in high-stakes applications, promoting transparency and accountability in AI-driven decisions (IBM).
- Open Access
- 17 March 2025
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 11 (2)
Machine Learning-Based Optimization for 5G Resource Allocation Using Classification and Regression Techniques
The rapid evolution of 5G networks necessitates efficient and adaptive resource allocation strategies to enhance network performance, minimize latency, and optimize bandwidth utilization. This study systematically evaluates multiple machine learning (ML) models, including Neural Networks, Support Vector Machines (SVM), Decision Trees, Ensemble Learning, and Regression-based approaches, to determine the most effective techniques for 5G resource allocation. The classification-based models demonstrated superior performance in predicting network congestion states, with Boosted Trees achieving the highest accuracy (94.1%), outperforming Bagged Trees (92.7%) and RUS Boosted Trees (93.8%). Among SVM classifiers, Gaussian SVM exhibited the highest accuracy (92.3%), highlighting its robustness in handling non-linearly separable data. Levenberg-Marquardt-trained Neural Networks (93.4%) outperformed SVM models in overall accuracy, emphasizing deep learning’s effectiveness in hierarchical feature representation. Meanwhile, regression-based models, particularly Gradient Boosting (R² = 0.96, MSE = 4.92), demonstrated the best predictive performance for continuous resource allocation optimization, surpassing Random Forest (R² = 0.94, MSE = 6.85) and Polynomial Regression (R² = 0.92, MSE = 9.21). The integration of Self-Organizing Maps (SOMs) for unsupervised network clustering further improved resource segmentation. Future research should explore Deep Reinforcement Learning (DRL) for autonomous 5G optimization and Explainable AI (XAI) techniques for improved interpretability in real-world deployments.
- 17 March 2025
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 11 (2)
Open AccessMachine Learning-Based Optimization for 5G Resource Allocation Using Classification and Regression Techniques
The rapid evolution of 5G networks necessitates efficient and adaptive resource allocation strategies to enhance network performance, minimize latency, and optimize bandwidth utilization. This study systematically evaluates multiple machine learning (ML) models, including Neural Networks, Support Vector Machines (SVM), Decision Trees, Ensemble Learning, and Regression-based approaches, to determine the most effective techniques for 5G resource allocation. The classification-based models demonstrated superior performance in predicting network congestion states, with Boosted Trees achieving the highest accuracy (94.1%), outperforming Bagged Trees (92.7%) and RUS Boosted Trees (93.8%). Among SVM classifiers, Gaussian SVM exhibited the highest accuracy (92.3%), highlighting its robustness in handling non-linearly separable data. Levenberg-Marquardt-trained Neural Networks (93.4%) outperformed SVM models in overall accuracy, emphasizing deep learning’s effectiveness in hierarchical feature representation. Meanwhile, regression-based models, particularly Gradient Boosting (R² = 0.96, MSE = 4.92), demonstrated the best predictive performance for continuous resource allocation optimization, surpassing Random Forest (R² = 0.94, MSE = 6.85) and Polynomial Regression (R² = 0.92, MSE = 9.21). The integration of Self-Organizing Maps (SOMs) for unsupervised network clustering further improved resource segmentation. Future research should explore Deep Reinforcement Learning (DRL) for autonomous 5G optimization and Explainable AI (XAI) techniques for improved interpretability in real-world deployments.
- Open Access
- 30 December 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 11 (1)
Blockchain and Deep Learning for Secure IoT: A Hybrid Cryptographic Approach
The Internet of Things (IoT) has revolutionized device connectivity, but its rapid expansion has raised significant security concerns related to data privacy, device integrity, and unauthorized access. This study explores a hybrid cryptographic approach leveraging blockchain technology and deep learning to enhance IoT security mechanisms. Blockchain provides a decentralized and immutable framework for securing data transactions, while deep learning algorithms can adaptively detect and neutralize attacks by analyzing large datasets. Our proposed method integrates smart contracts for enforcing access controls, ensuring only authorized devices interact within the network. Furthermore, advanced deep learning techniques enable real-time anomaly detection, identifying potential breaches and malicious activities effectively. The research addresses scalability challenges, computational efficiency, and energy consumption, offering tailored solutions suitable for resource-constrained IoT devices. By synthesizing blockchain and deep learning, this approach not only fortifies data integrity and confidentiality but also enhances user trust in IoT systems. Key findings indicate that employing this hybrid model can significantly reduce the incidence of cyberattacks and provide robust security solutions for diverse IoT applications, ranging from smart homes to healthcare and industrial automation. This study aims to establish a foundational framework for future research in secure IoT architectures, paving the way for broader implementation in real-world scenarios
- 30 December 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 11 (1)
Open AccessBlockchain and Deep Learning for Secure IoT: A Hybrid Cryptographic Approach
The Internet of Things (IoT) has revolutionized device connectivity, but its rapid expansion has raised significant security concerns related to data privacy, device integrity, and unauthorized access. This study explores a hybrid cryptographic approach leveraging blockchain technology and deep learning to enhance IoT security mechanisms. Blockchain provides a decentralized and immutable framework for securing data transactions, while deep learning algorithms can adaptively detect and neutralize attacks by analyzing large datasets. Our proposed method integrates smart contracts for enforcing access controls, ensuring only authorized devices interact within the network. Furthermore, advanced deep learning techniques enable real-time anomaly detection, identifying potential breaches and malicious activities effectively. The research addresses scalability challenges, computational efficiency, and energy consumption, offering tailored solutions suitable for resource-constrained IoT devices. By synthesizing blockchain and deep learning, this approach not only fortifies data integrity and confidentiality but also enhances user trust in IoT systems. Key findings indicate that employing this hybrid model can significantly reduce the incidence of cyberattacks and provide robust security solutions for diverse IoT applications, ranging from smart homes to healthcare and industrial automation. This study aims to establish a foundational framework for future research in secure IoT architectures, paving the way for broader implementation in real-world scenarios
- Open Access
- 31 March 2024
- Published by Seventh Sense Research Group Journals in International Journal of Electronics and Communication Engineering
- Vol. 11 (3)
Adaptive Fog Computing Framework (AFCF): Bridging IoT and Blockchain for Enhanced Data Processing and Security
This research introduces an Adaptive Fog Computing Framework (AFCF) aimed at enhancing the efficiency and scalability of IoT ecosystems through blockchain technology integration, addressing task allocation, resource management, and task offloading challenges within fog and cloud computing paradigms. Employing simulations, the study utilized task distribution strategies, blockchain stability assessment, and cloud server workload management, demonstrating the framework’s capacity to maintain performance across diverse IoT settings. Quantitative results revealed a cent percent success rate in task processing, with a balanced load distribution at 50% and an average task complexity of 6.47893 in arbitrary units. The system demonstrated a latency of 48.479 milliseconds and a throughput of 2.469697 tasks per timestep, showcasing high scalability (97.8%) and energy efficiency (15.774194 in arbitrary efficiency units), emphasizing the AFCF’s robustness in varied tasks and resource dynamics. The study concludes the AFCF’s potential for real-world IoT applications, highlighting its implications for future research and practical deployment, underscoring its contribution to fog and cloud computing literature and paving the way for further exploration into adaptive computing frameworks.
- 31 March 2024
- Published by Seventh Sense Research Group Journals in International Journal of Electronics and Communication Engineering
- Vol. 11 (3)
Open AccessAdaptive Fog Computing Framework (AFCF): Bridging IoT and Blockchain for Enhanced Data Processing and Security
This research introduces an Adaptive Fog Computing Framework (AFCF) aimed at enhancing the efficiency and scalability of IoT ecosystems through blockchain technology integration, addressing task allocation, resource management, and task offloading challenges within fog and cloud computing paradigms. Employing simulations, the study utilized task distribution strategies, blockchain stability assessment, and cloud server workload management, demonstrating the framework’s capacity to maintain performance across diverse IoT settings. Quantitative results revealed a cent percent success rate in task processing, with a balanced load distribution at 50% and an average task complexity of 6.47893 in arbitrary units. The system demonstrated a latency of 48.479 milliseconds and a throughput of 2.469697 tasks per timestep, showcasing high scalability (97.8%) and energy efficiency (15.774194 in arbitrary efficiency units), emphasizing the AFCF’s robustness in varied tasks and resource dynamics. The study concludes the AFCF’s potential for real-world IoT applications, highlighting its implications for future research and practical deployment, underscoring its contribution to fog and cloud computing literature and paving the way for further exploration into adaptive computing frameworks.
- Open Access
- 9 December 2022
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 10 (1s) , 265-273
Edge Computing and Blockchain in Smart Agriculture Systems
The advancement of Internet-based technologies has made huge progress toward improving the accessibility of "smart agriculture." With the advent of unmanned and automatic management, smart agriculture is now able to accomplish monitoring, supervision, and real-time picture monitoring. It is not possible to know for sure that the data in a smart agriculture system is complete and secure from intrusion. This article investigates and assesses the potential of edge computing and blockchain for use in smart agriculture. We combine the advantages of blockchain technology and the edge computing framework to create a smart agriculture framework system that is based on a very straightforward analysis of the evolution of smart agriculture. The study proposes a thorough method for emphasizing the significance of agriculture and edge computing, as well as the advantages of incorporating blockchain technology in this context. This paper also proposes an intelligent agricultural product traceability system design: edge computing with blockchain for smart agriculture. The study concludes with a discussion of outstanding problems and difficulties that can arise during the creation of a blockchain-based edge computing system for smart agriculture systems.
- 9 December 2022
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 10 (1s) , 265-273
Open AccessEdge Computing and Blockchain in Smart Agriculture Systems
The advancement of Internet-based technologies has made huge progress toward improving the accessibility of "smart agriculture." With the advent of unmanned and automatic management, smart agriculture is now able to accomplish monitoring, supervision, and real-time picture monitoring. It is not possible to know for sure that the data in a smart agriculture system is complete and secure from intrusion. This article investigates and assesses the potential of edge computing and blockchain for use in smart agriculture. We combine the advantages of blockchain technology and the edge computing framework to create a smart agriculture framework system that is based on a very straightforward analysis of the evolution of smart agriculture. The study proposes a thorough method for emphasizing the significance of agriculture and edge computing, as well as the advantages of incorporating blockchain technology in this context. This paper also proposes an intelligent agricultural product traceability system design: edge computing with blockchain for smart agriculture. The study concludes with a discussion of outstanding problems and difficulties that can arise during the creation of a blockchain-based edge computing system for smart agriculture systems.