MSM. Jeyalakshmi Saravanakumar

M. Jeyalakshmi Saravanakumar

*This is an algorithmically generated author record based on publicly available information.

M. Jeyalakshmi Saravanakumar has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Data‑Driven Spatio‑Temporal Expert System for Electric Vehicle Charging Demand Profiling: The Complex T‑Spherical Fuzzy C‑Means Clustering Algorithm

    by Subramanian Petchimuthu, M. Jeyalakshmi Saravanakumar, Fathima Banu M, Meena Somasundaram, Dragan Pamucar

    Optimizing Electric Vehicle (EV) charging infrastructure is a critical urban planning challenge characterized by high-dimensional uncertainty and periodic traffic flows. Traditional decision models often suffer from "temporal blindness," failing to recognize the cyclical nature of urban movement (e.g., the proximity of late-night and early-morning hours). This paper introduces the Complex T-Spherical Fuzzy C-Means (CTSF-CM) expert system, a novel unsupervised machine learning framework designed for spatio-temporal demand profiling. The system utilizes a complex phase term to mathematically represent temporal periodicity and a T-spherical fuzzy structure to filter environmental noise from meteorological sensors. Validated on 2,747 hourly instances from the I-94 Interstate Highway, the CTSF-CM system achieves a Peak Separation Accuracy of 87.21%, significantly outperforming standard K-Means and Intuitionistic Fuzzy models. Beyond numerical precision, the system provides geometrically interpretable decision boundaries that allow urban planners to distinguish between morning and evening service zones, ensuring grid stability and infrastructure efficiency in smart city environments.

  • Open Access

    A Social Network-Driven Large-Scale Group Decision Making Framework for Resilient Green Hydrogen Supply Chain Design under Complex Periodicity

    by Subramanian Petchimuthu, M. Jeyalakshmi Saravanakumar, Fathima Banu M, Hüseyin Kamacı

    To create a robust green hydrogen economy, it is important to reconcile the technical intermittency of renewable energy and the competing interests of various stakeholders. Current multi-criteria models fail because they are ``phase-blind'' to seasonal production cycles and ``socially-blind'' to the complex dynamics of trust in large-scale groups. This paper suggests a smart expert system based on complex T-spherical fuzzy sets to fill such gaps. Our model proposes three structural novelties: (1) a phase-aware modeling system that uses complex-valued membership to represent the temporal dependability of the supply chain expressly; (2) a social network analysis component that extracts objective expert weights using PageRank centrality and Fuzzy C-means clustering to resolve cognitive conflict; and (3) an iterative consensus-reaching process with an automated feedback scheme to coordinate the viewpoints of the stakeholders. To fit the psychological truth of energy investors, we incorporate regret theory into a multiple aggregation scheme based on double normalization. The framework was tested using a real-world case study of the National Green Hydrogen Mission in India involving 20 diverse experts. A comparative analysis shows that our system finds resilient hybrid configurations that traditional models do not. These findings offer strategic paths to infrastructure planning in places where the environment is exposed to frequent stresses, and give a more reliable direction for the world going through the energy transition.