AI,wireless sensor networks, computer Vision,Machine Learning,IoT and quantum computing
156
Scopus Publications
Scopus Publications
Fusion-ADiNet: a multi-level framework for enhanced diabetes and Alzheimer’s disease detection using chimp-whale fusion estimation Roobini MS, Mong-Fong Horng, Siva Shankar S, Nagarajan G Scientific Reports, 2026 Rising cases of diabetes and AD are the two biggest health-related issues world-wide; this greatly hampers the quality of life among the afflicted persons. Early identification of diabetes most especially correlated with neurodegenerative conditions such as Alzheimer's guarantees early intervention and hence proper management. However, the existing approaches for disease detection have been suffering from a series of limitations in poor diagnostic accuracy, high computational complexity, and the lack of an effective model that could properly handle the intricate correlations between diabetes and AD. Most of the existing methods for diabetes and AD detection rely on traditional machine-learning algorithms or heuristic optimization approaches, which are not capable of handling high dimensionality and complex clinical data. The models also find it extremely difficult to represent the subtle relationship between the two diseases, leading to unsatisfying performance in practical applications. It is therefore imminent to develop much more advanced methodologies with integration that could improve accuracy in prediction, enabling better decision-making in clinics. To overcome the limitations of existing methods, in this paper, we propose a new approach called Fusion-Alzheimer's Diabetes Network (Fusion-ADiNet) by introducing a multi-level fusion framework for disease detection. The main novelty in this method lies in the newly designed Chimp-Whale Fusion Estimator (CWFE) optimization algorithm. Furthermore, the Fusion-ADiNet framework is quite flexible, so extending it to other diseases or datasets in the future will be very easy. This work contributes much to the field of healthcare analytics and opens new perspectives toward more effective diagnostic tools for timely detection of diabetes and Alzheimer's disease.
Forward Selection for Time Series-Based Qubit Generation via Parameterized Quantum Gates Singaraju Srinivasulu, Nagarajan G International Journal of Advanced Computer Science and Applications, 2026 Quantum data processing requires classical data to be encoded into quantum states. Current noisy intermediate-scale quantum devices have a limited number of qubits that are stable only briefly. Encoding classical data into qubits is the initial step in Quantum Machine Learning (QML), and effective encoding is crucial for quantum processing. This algorithms for data processing are still emerging, and compact data representations are essential for their success. This research proposes a novel data encoding technique using uniformly controlled rotation gates, achieving high storage density by encoding real-valued time series data as qubit rotations. The model uses a binary representation for computations on time series data, reducing the number of quantum measurements needed. The research explores quantum forward propagation in simulations to improve prediction accuracy for time series signals using parameterized quantum circuits, handling trends, noise, and sinusoidal components. The efficiency of the encoding process depends on data volume and chosen encoding, with potential infinite loading time in the worst case. This study presents a Forward Selection Time Series Data Pro-cessing and Feature Extraction Model for Qubits generation with Parameterized Quantum Gates (FSDPFEM-PQG), demonstrating superior performance in quantum representations compared to existing models.
AI-driven energy-efficient cybersecurity frameworks for sustainable digital infrastructures Saravanan T R, Bhuvan Unhelkar, Siva Shankar, Nagarajan G Results in Engineering, 2025 • Traditional models focus on detection accuracy but lack energy efficiency, making them unsuitable for deployment in resource-constrained settings. • Introduction of a novel hybrid model: Dynamic Beetle Antennae Search–Mutated Adaptive Weighted Random Forest Tree (DynBAS-AWRF Tree). • Performs intelligent feature subset selection and hyperparameter tuning. • Uses labeled intrusion detection datasets with network flow and system behavior logs relevant to IoT/edge environments. • Preprocessing includes Min-Max normalization, one-hot encoding, and Linear Discriminant Analysis (LDA) for dimensionality reduction while preserving class separability. Cybersecurity in digital infrastructures faces energy limitations, especially in IoT systems. Traditional models emphasize accuracy but lack efficiency, making them unsuitable for edge deployment. Existing methods struggle to balance performance and energy use, particularly with high-dimensional, imbalanced data. The objective is to develop an energy-conscious, adaptive cybersecurity framework capable of delivering robust intrusion detection while minimizing computational overhead. A novel hybrid model named Dynamic Beetle Antennae Search–Mutated Adaptive Weighted Random Forest Tree (DynBAS-AWRF Tree) is introduced, integrating a dynamic feature selection and tuning mechanism with a highly adaptable, weighted ensemble classifier. The DynBAS component performs intelligent feature subset selection and hyperparameter tuning through directional sensing and mutation-enhanced search strategies. The AWRF Tree adapts its structure and weighting in response to class distribution and feature relevance, reducing complexity while improving sensitivity to minority attacks. Evaluation utilizes labeled intrusion detection datasets containing network flow and system behavior logs representative of smart IoT and edge environments. Min-max normalization and one-hot encoding are applied to standardize and structure the input data for optimal model ingestion. Linear Discriminant Analysis (LDA) reduces dimensionality while preserving class separability. DynBAS selects optimal feature sets and hyperparameters, while AWRF Tree dynamically adjusts node weights and tree depth, maintaining efficiency and adaptability. The hybrid model achieves competitive detection accuracy with significantly reduced feature usage by 45 % and increased energy efficiency from 50 % to 85 %. The DynBAS-AWRF Tree framework enables a scalable and sustainable cybersecurity solution suitable for deployment in constrained digital infrastructures.
Designing low-power encryption algorithms for end-to-end vehicular data protection in sustainable IoT networks D. Sudha, Bhuvan Unhelkar, Siva Shankar, G. Nagarajan Results in Engineering, 2025 • Energy-Efficient Data Security: Create a low-power SACO-PRESENT encryption technique for end-to-end vehicular data protection. • Intelligent Path Selection: Achieve energy-efficient and reliable communications between vehicles, optimize the formation of cluster and the selection of routes by using an enhanced SACO implemented within an enhanced AODV protocol. • Secure Identity Management: Incorporate lightweight symmetric lightweight encryption in conjunction with anonymous trust-based authentication to protect user identity and privacy. • Intelligent vehicular networks need lightweight, energy-efficient encryption since traditional methods are too resource-heavy. • The proposed SACO-PRESENT with optimized routing ensures secure, scalable, and power-efficient end-to-end communication in high-mobility IoV. The rapid proliferation of the Internet of Things (IoT) in intelligent transportation systems has revolutionized vehicular communication by enabling real-time data exchange between vehicles, infrastructure, and cloud services. However, high mobility and dynamic network topologies result in increased energy consumption and heightened vulnerability to data breaches. To address these challenges, this research proposes an efficient low-power encryption framework for cluster-based Internet of Vehicles (IoV), designed to ensure end-to-end vehicular data protection while minimizing energy usage within sustainable IoT networks. The proposed model introduces a block cipher–based Scalable Ant Colony Optimized PRESENT (SACO-PRESENT) encryption scheme for secure data communication and energy-efficient path optimization. A Scalable Ant Colony Optimization (SACO) algorithm is employed to optimize clustering and adaptive link selection within an enhanced AODV routing protocol. This optimization enables the selection of energy-efficient communication paths based on residual energy, node mobility, and signal strength, thereby extending network lifetime. To ensure user privacy and identity authentication, the system incorporates lightweight symmetric encryption and anonymous trust authentication protocols, providing strong security without compromising the performance of resource-constrained devices. Simulation results demonstrate that the proposed model significantly improves key performance metrics achieving a higher packet delivery ratio (93.88 %), reduced end-to-end delay, lower energy consumption, and an overall extension of network lifetime. Overall, the proposed framework delivers a scalable, low-power, and secure solution for vehicular communication, contributing to the advancement of resilient and sustainable IoT-based intelligent transportation systems.
ADVANCED MACHINE LEARNING FRAMEWORKS FOR AUTOMATED IDENTIFICATION AND ANALYSIS OF CRITICAL PARAMETERS IN VLSI CIRCUIT PERFORMANCE AND RELIABILITY Journal of Theoretical and Applied Information Technology, 2025
Object Detection in Images using Machine Learning G. Nagarajan, Abhiram Piratla, Karthikeya Golla 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things Idciot 2025, 2025
Detection of Skin Cancer using CNN A. Ronald Doni, Mahanthi Varun, Mannepalli Manoj Kumar, G. Nagarajan Proceedings of 8th International Conference on Trends in Electronics and Informatics Icoei 2025, 2025
Crypto Currency Using Blockchain G. Nagarajan, Meka Sesha Sai, R. Karanam Giridhar Venkata Srinivas Rao, A. Ronald Doni Aip Conference Proceedings, 2024
Envisaging the patterns in Blockchain G Nagarajan, Sukeerth Atmakuri, Sri Satyendra Nalamati, R I Minu Proceedings of International Conference on Circuit Power and Computing Technologies Iccpct 2024, 2024
Fuzzy rule based ontology reasoning Minu Rajasekaran Indra, Nagarajan Govindan, Ravi Kumar Divakarla Naga Satya, Sundarsingh Jebaseelan Somasundram David Thanasingh Journal of Ambient Intelligence and Humanized Computing, 2021
Digital Art Using Machine Learning Karri Yaswanth Teja Reddy, Karnati Madhava Sai Kumar, A. Pravin, T. Prem Jacob, G. Nagarajan Lecture Notes in Electrical Engineering, 2021
Design of interleaved flyback converter D. Ramya, A. Santhi Mary Antony, D. Godwin Immanuel, G. Nagarajan International Journal of Intelligent Enterprise, 2019
Decision based detail preserving algorithm for the removal of equal and unequal probability salt and pepper noise in images and videos International Arab Journal of Information Technology, 2018
CIMTEL- mining algorithm for big data in telecommunication International Journal of Engineering and Technology, 2015
Hybrid solar inverter for grid synchronization M. Jyothi Monisha, S. D. SundarSingh Jebaseelan, G. Nagarajan IEEE International Conference on Circuit Power and Computing Technologies Iccpct 2015, 2015
Implementation of Non-Isolated High Voltage Gain Input-Parallel Output-Series Dc/Dc Converter with Switched Capacitor International Journal of Control Theory and Applications, 2015
FLC based fault tolerant technique in Dc-Dc converters for pv System International Journal of Control Theory and Applications, 2015
Photovoltaic smart battery charging system using fuzzy controlled burp-pulse charge technique International Journal of Applied Engineering Research, 2015
Rule-based semantic content extraction in image using fuzzy ontology International Review on Computers and Software, 2014
Fuzzy ontology creation for semantic sports event image description International Journal of Applied Engineering Research, 2014
Novel pid like fussy logic speed driving of switched reluctance motor International Journal of Applied Engineering Research, 2014
Power quality improvement for thirty bus system using UPFC and TCSC Indian Journal of Science and Technology, 2014
Performance analysis of voltage profile, power, angle of injection using combined facts device International Journal of Applied Engineering Research, 2014
