K. Prakasha

Implementation and experimental evaluation of mint for workload-aware approximate nearest neighbor index tuning in multi-vector databases

Approximate nearest neighbor (ANN) search is an integral part of contemporary vector databases; however, the performance of this algorithm highly depends on the specifics of data, recall requirements, storage capabilities, and query workload. All these factors complicate ANN even further in multi-vector databases, wher...

Adaptive primal–dual Q-learning for electric vehicle route optimization on real-world charging networks

A novel Dual Q–Adaptive Weighting model that balances reward and cost through a primal–dual learning mechanism is proposed and achieves the highest route accuracy of 78.66%, outperforming Double Q-Learning, Q-Learning, and traditional A* and Dijkstra algorithms.

Explainable AI for Smart Grid Intelligence: A Comprehensive Review of Techniques, Applications and Future Directions