Internet of Things (IoT), edge computing, and cloud computing has transformed data-driven services across healthcare, transportation, manufacturing, finance, agriculture, and smart cities. These applications generate large volumes of sensitive distributed data, making traditional centralized machine learning unsuitable due to privacy, security, communication, and regulatory challenges. Federated Learning (FL) addresses these issues by enabling collaborative model training without transferring raw data, thereby preserving user privacy.This paper presents a privacy-preserving federated learning framework that integrates secure aggregation, differential privacy, encryption, adaptive communication, and federated optimization for large-scale heterogeneous environments. The framework incorporates edge computing, blockchain, Trusted Execution Environments (TEE), and Explainable AI (XAI) to improve security, transparency, and trust. A multi-layer architecture consisting of client devices, edge servers, federated coordinators, cloud services, and security modules is proposed. Adaptive client selection, weighted federated averaging, dynamic privacy allocation, and asynchronous synchronization are employed to improve learning under Non-IID data distributions. Experimental results demonstrate high model accuracy, reduced privacy leakage, lower communication overhead, faster convergence, enhanced scalability, and strong resilience against security attacks, making the proposed framework suitable for next-generation privacy-preserving smart applications.
Seshagiri N· International Journal of Mod...· 0 citations
Autonomous robotic systems are increasingly deployed in industrial automation, healthcare, logistics, agriculture, defense, and intelligent transportation, where they must make complex decisions in dynamic environments. Reinforcement Learning (RL) enables robots to learn optimal actions through interaction with their environment, but most deep RL models function as black boxes, limiting transparency and trust in safety-critical applications. This paper proposes an Explainable Reinforcement Learning for Autonomous Robotic Decision Making (XORL) framework that integrates reinforcement learning with Explainable AI (XAI) to improve decision interpretability. The framework combines multimodal sensor data, policy optimization, confidence estimation, reward decomposition, policy visualization, and decision traceability to generate understandable explanations for robotic actions. It evaluates performance using metrics such as navigation success, obstacle avoidance, learning stability, computational efficiency, explanation consistency, and reliability. Experimental results demonstrate that XORL enhances decision transparency, operator trust, safety awareness, and autonomous task performance while maintaining competitive learning efficiency, supporting the development of trustworthy and human-centric autonomous robotic systems.
Seshagiri N· International Journal of Int...· 0 citations
Predictive analytics is rapidly evolving through Artificial Intelligence (AI), particularly with the emergence of foundation models that enable scalable, transferable, and context-aware intelligence across multiple domains. Unlike traditional machine learning models, foundation models leverage large-scale multimodal pretraining and efficient task-specific adaptation, enabling superior reasoning, zero-shot learning, and cross-domain knowledge transfer. This paper proposes the Foundation Model-Based Predictive Analytics Framework for Multi-Domain Decision Intelligence (FMPA-MDI), an integrated architecture that combines heterogeneous data acquisition, multimodal preprocessing, semantic representation learning, transformer-based predictive reasoning, retrieval-augmented learning, knowledge graph integration, explainable AI (XAI), and intelligent decision optimization. The framework supports structured and unstructured data while incorporating transfer learning, attention mechanisms, semantic embeddings, and continuous feedback for adaptive decision-making. Mathematical formulations model feature representation, semantic similarity, predictive confidence, and optimization. The proposed framework enhances prediction accuracy, scalability, interpretability, and computational efficiency, providing a robust foundation for next-generation intelligent decision support across healthcare, finance, manufacturing, smart cities, and other enterprise domains.
Seshagiri N· International Journal of Mac...· 0 citations
The rapid growth of distributed computing paradigms such as cloud, edge computing, and large-scale data centers has significantly increased global energy consumption. As organizations increasingly rely on these systems for large-scale data processing, the need for energy-efficient methods has become critical due to rising operational costs and environmental concerns like carbon emissions. This paper analyzes energy-efficient data processing techniques in distributed environments, focusing on system-level optimization, algorithmic strategies, and resource management. It identifies major sources of energy consumption, including computation, data transfer, storage, and cooling, and highlights inefficiencies such as data redundancy, poor scheduling, network congestion, and underutilized resources. To address these challenges, the paper examines approaches such as energy-aware task scheduling, data locality optimization, dynamic voltage and frequency scaling (DVFS), virtualization, and workload consolidation. It also explores machine learning-based predictive models for adaptive resource allocation. A key contribution is the classification of these techniques across hardware, middleware, and application layers, along with a comparative analysis of their effectiveness. The proposed hybrid methodology integrates workload prediction, adaptive scheduling, and resource consolidation, demonstrating significant energy savings without compromising system performance. Overall, the study emphasizes the importance of coordinated, multi-layered strategies for achieving sustainable and energy-efficient distributed computing systems.
Seshagiri N· International Journal of Dat...· 0 citations
This study proposes a Federated Predictive Learning with Privacy-Aware Model Aggregation (FPL-PAMA) framework, suitable for applications including healthcare, IoT, smart manufacturing, transportation, and financial fraud detection, providing a secure and scalable solution for next-generation distributed intelligent systems.
Mahabala H.N, Seshagiri N· International Journal of Mac...· 0 citations