Sankhya Singh
Papers
1
Total Citations
1
H-Index
1
About
Dr. Sankhya Singh is a pioneering researcher at the intersection of machine learning and industrial optimization, with a primary focus on federated learning, meta-learning, and their applications in resource-intensive sectors like mining. Her most-cited work, "An Integrated Federated Learning and Meta-Learning Approach for Mining Operations" (2023), introduces a novel framework that enables decentralized model training across geographically dispersed mining sites while preserving data privacy and reducing communication overhead. This contribution addresses a critical challenge in heavy industries where data centralization is often impractical due to bandwidth or regulatory constraints. By combining meta-learning’s rapid adaptation capabilities with federated learning’s privacy-preserving architecture, Singh’s approach achieves faster convergence and improved predictive accuracy for equipment maintenance and resource estimation—a significant leap forward for operational efficiency. Though early in her career, her work has already garnered attention for its practical scalability, laying the groundwork for smarter, safer, and more sustainable industrial practices. Singh’s research is particularly vital for students and engineers seeking to bridge cutting-edge AI with real-world, high-stakes environments.
Research Focus
Key Achievements
Top Papers
- 1