Reframing Value Through Narrative Strategy for Economic Transformation in Entrepreneurial Ecosystems: Narrative-Driven Economic Change M. P. Rajakumar, R. Vinston Raja, M. Balasubramani, B. Nagalakshmi, J. Tharun, M. Robinson Joel Co Constructing Economic Transformation Through Enterprise Narrative and Systemic Design, 2026 Reframing Value Narrative Strategy as a Catalyst for Economic Transformation in Entrepreneurial Ecosystems for the upcoming book Co-Constructing Economic Transformation Through Enterprise Narrative and Systemic Design examines how strategic storytelling redefines and operationalizes value within entrepreneurial contexts. Drawing on narrative theory, institutional logics, and systems thinking, the authors develop a conceptual model showing how narratives frame opportunities, mobilize resources, and align stakeholder priorities. Empirical case studies illustrate how targeted narrative interventions in policy campaigns and grassroots initiatives can disrupt entrenched growth paradigms and foster inclusive, sustainable innovation. The chapter outlines hybrid methods for assessing narrative impact using computational discourse analysis and participatory evaluation and identifies future research avenues on cross-cultural storytelling, crisis-driven narratives, and narrative infrastructure design. Recommendations for embedding narrative capacity within governance structures.
Bridging Text and Video Generation: A Survey G. Maragatham, Nilay Kumar, Priyansh Bhandari, Vinston Raja, Robinson Joel M Fusion of Multimodal Generative AI and Blockchain Technology in Digital Media, 2025 While text-to-image synthesis extends to dynamic visual contents, text-to-video synthesis creates coherent videos from the provided text-based description. A technique of this nature can make a revolutionary impact on industries such as education, accessibility, marketing, and entertainment. However, the T2V technique comes with a set of challenges that pertain to temporal coherence, exact alignment between text and video, high computational demands, and limited high-quality datasets. This survey summarizes the latest developments in T2V technologies, beginning with early adaptations of text-to-image models and progressing to recent studies involving large-scale pre-training integrated with diffusion methods. The chapter then provides a comprehensive comparison of these models based on their performance metrics against benchmarking datasets, examining the strengths and limitations of each, along with practical applications.
Metrics and techniques for evaluating machine learning models and optimization algorithms R. Vinston Raja, J. Jayashankari, S. Sheela, S. Jancy Sickory Daisy, G. G. Gokilam, M. Robinson Joel AI Model Design and Data Management for Disease Prediction, 2025 Assessing optimization algorithms and machine learning models is crucial to ensure their reliability, scalability, and effectiveness across applications. This review provides a comprehensive analysis of evaluation metrics and methods. For supervised learning, classification metrics like accuracy, precision, recall, and regression metrics like MSE, RMSE, and R2 are emphasized. Unsupervised learning is assessed using metrics such as silhouette score, Davies-Bouldin index, and reconstruction error. Techniques like stratified k-fold, k-fold cross-validation, and leave-one-out validation ensure robust evaluations. Optimization algorithms are evaluated using metrics like convergence speed, solution accuracy, noise resilience, scalability, and computational efficiency, with advanced tools like sensitivity analysis, ablation studies, and comparative testing enhancing assessments. Visualization tools, including heatmaps, Pareto fronts, and convergence charts, aid in understanding model behavior.
Securing healthcare data: A federated learning framework with hybrid encryption in cluster environments C Srivenkateswaran, A Jaya Mabel Rani, R Senthil Kumaran, R Vinston Raja Technology and Health Care, 2025 The study's novel contribution is the development and evaluation of a hybrid encryption scheme combining Elliptic Curve Cryptography (ECC) with the Serpent symmetric encryption algorithm, demonstrating enhanced security and performance for safeguarding healthcare data in cluster environments while ensuring scalability, interoperability, and compliance with HIPAA regulations. The primary objectives include assessing the suitability of the ECC-Serpent hybrid encryption for safeguarding healthcare data, ensuring the scalability and interoperability of this encryption solution with existing healthcare systems, and implementing secure communication channels within cluster environments. The combination of Elliptic Curve Cryptography (ECC) and the Serpent algorithm leverages ECC's efficient key management and Serpent's robust symmetric encryption to provide enhanced security and performance, ensuring scalable and resilient data protection in cluster environments. This hybrid approach addresses both key distribution efficiency and high encryption strength, which are critical for securing sensitive healthcare data. This hybrid approach addresses key distribution efficiency and high encryption strength, which are critical for securing sensitive healthcare data. The study employs a hierarchical key management strategy, utilizing ECC for secure key exchange and distribution, paired with regular key rotation and storage practices to maintain compliance with HIPAA regulations and ensure the ongoing protection of sensitive healthcare data. Overall, the research underscores the critical need for healthcare organizations to adhere to HIPAA regulations and implement robust encryption measures to protect patient privacy and secure sensitive medical information. The study concludes that the ECC-Serpent hybrid encryption scheme is a viable and effective solution for enhancing healthcare data security in cluster environments, ensuring both data integrity and regulatory compliance. The implemented Python framework yielded promising results, the key finding is that the ECC-Serpent hybrid encryption scheme is a viable and effective solution for enhancing healthcare data security in cluster environments, achieving an accuracy rate of 97.5% in safeguarding patient data.
AI-driven innovation powering economic growth in Industry 4.0 Vinston Raja R., P. Jose, Ashwin Prabhu G., Joel Jacson, R. Devi, Robinson Joel M. Driving Socio Economic Growth with AI and Blockchain, 2025 The Fourth Industrial Revolution, or Industry 4.0, is transforming economies through advanced technologies like AI, IoT, blockchain, and big data. AI-driven innovation enhances productivity, automates tasks, and personalizes services, revolutionizing sectors like healthcare, manufacturing, retail, and finance. Applications such as predictive maintenance, personalized customer experiences, and AI-based diagnostics boost efficiency and drive economic growth. Despite its benefits, AI adoption poses challenges like ethical concerns, algorithmic bias, data privacy, and workforce displacement. Transparent AI systems, regulatory frameworks, and reskilling initiatives are vital to address these issues. Public-private partnerships and inclusive policies can promote equitable economic growth. AI also supports sustainability, optimizing resources and advancing renewable energy and environmental conservation. This chapter emphasizes balancing innovation with ethics and inclusivity to harness AI's full potential for a resilient and sustainable economic future.
Precision Forecasting of Stock Prices: Leveraging XGBoost and Technical Indicator for Advanced Predictive Modeling Yuvaraj. S, Chenni Kumaran. J, Vinston Raja. R International Conference on Intelligent Systems and Computational Networks Iciscn 2025, 2025 The investigation aims to evaluate the performance of machine learning techniques, particularly the XGBoost regression method, for stock price prediction with the help of technical indicators. The research targets the adjusted closing price to reduce the autocorrelation problem in time series. The Five Days and Ten Days Exponential Moving Averages (EMA_5 and EMA_10) are involved in refining feature selection. The performance of the model was evaluated using different error metrics, namely, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2). The results indicate that the XGBoost model, combined with EMA_5 and EMA_10, achieves high predictive performance, obtaining an r2 value of 0.98. It implies that incorporating short-term EMAs into advanced machine learning techniques drastically improves stock price forecasting.
Stock Price Prediction Using Gradient Boosting Machine with Technical Indicators Yuvaraj. S, Chenni Kumaran. J, Vinston Raja. R, Jayanthi. G Proceedings of the 3rd International Conference on Intelligent and Innovative Technologies in Computing Electrical and Electronics Iitcee 2025, 2025 This research endeavors to design a predictive model to forecast stock prices using a Gradient Boosting Machine (GBM) regressor, specifically emphasizing the adjusted closing price to mitigate the autocorrelation issues intrinsic to time series data. The investigation encompasses a 12-month duration of historical stock data, integrating two technical indicators, namely Exponential Moving Averages (EMA_5 and EMA_10), to augment predictive precision. Gradient Boosting, recognized for its proficiency in managing intricate and non-linear data patterns, was employed to forecast forthcoming stock prices. Critical performance indicators, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R2), played a role in evaluating model accuracy, attaining an R2 score of 0.99, thereby signifying an almost perfect correlation between actual and predicted prices. Beyond numerical assessments, visual examinations through scatter plots, residual plots, and prediction error distribution further elucidated the model’s efficiency. The findings reveal that the amalgamation of Gradient Boosting with Technical Indicators such as EMA_5 and EMA_10, coupled with an emphasis on the adjusted closing price, proves exceptionally effective for stock price forecasting. This methodology achieved an accuracy rate nearing 99%, illustrating its substantial promise for stock market prediction and its proficiency in alleviating autocorrelation challenges within time series datasets.
Leveraging AI to Promote Sustainable Energy Distribution Raja R. Vinston, K. Fouzia Sulthana, Subha Priyadharshini A, R. Kotteeswaran, G. Manikandan, Joel M. Robinson Achieving Sustainability in Multi Industry Settings with AI, 2025
Reinforcement Learning for Autonomous Systems Vinston Raja R, C. Mary Subitha Jenefer, S. Rukmani Devi, Tatiraju.V. Rajanikanth, J. Bhavana, K Karthik Proceedings of 2025 10th International Conference on Science Technology Engineering and Mathematics Iconstem 2025, 2025
Automatic Identification of Hurricane Damage Using a Transfer Learning Approach with Satellite Images International Journal of Intelligent Systems and Applications in Engineering, 2024
INNOVATIVE TIME SERIES-BASED ECG FEATURE EXTRACTION FOR HEART DISEASE RISK ASSESSMENT Journal of Theoretical and Applied Information Technology, 2023
COMPARATIVE EVALUATION OF CARDIOVASCULAR DISEASE USING MLR AND RF ALGORITHM WITH SEMANTIC EQUIVALENCE Journal of Theoretical and Applied Information Technology, 2023
Study of ECG Analysis based Cardiac Disease Prediction using Deep Learning Techniques International Journal of Intelligent Systems and Applications in Engineering, 2023
Identification of Underwater Species Using Condition-Based Ensemble Supervised Learning Classification International Journal of Intelligent Systems and Applications in Engineering, 2023
ANALYTIC APPROACH OF PREDICTING EMPLOYEE ATTRITION USING DATA SCIENCE TECHNIQUES Journal of Theoretical and Applied Information Technology, 2023
SIMILARITY-BASED GENE DUPLICATION PREDICTION IN PROTEIN-PROTEIN INTERACTION USING DEEP ARTIFICIAL ECOSYSTEM NETWORK Journal of Theoretical and Applied Information Technology, 2022
