S
Sheetal Kalyani
Researcher at Indian Institute of Technology Madras
Publications - 149
Citations - 1526
Sheetal Kalyani is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Fading & Computer science. The author has an hindex of 16, co-authored 134 publications receiving 1053 citations. Previous affiliations of Sheetal Kalyani include Motorola & Indian Institutes of Technology.
Papers
More filters
Journal ArticleDOI
Backpropagating Through the Air: Deep Learning at Physical Layer Without Channel Models
Vishnu Raj,Sheetal Kalyani +1 more
TL;DR: By utilizing stochastic perturbation techniques, it is shown that the proposed method can train a deep learning-based communication system in real channel without any assumption on channel models.
Journal ArticleDOI
Spectrum Access In Cognitive Radio Using a Two-Stage Reinforcement Learning Approach
TL;DR: The number of sensing operations is minimized with negligible increase in primary user interference; this implies that less energy is spent by the secondary user in sensing, and also higher throughput is achieved by saving the time spent on sensing.
Journal ArticleDOI
Outlier analysis for defect detection using sparse sampling in guided wave structural health monitoring
Jagadeeshwar L. Tabjula,Srijith Kanakambaran,Sheetal Kalyani,Prabhu Rajagopal,Balaji Srinivasan +4 more
TL;DR: The feasibility of detection of delamination is experimentally demonstrated, whose size is comparable to the ultrasonic wavelength with probability of detection better than 90% using <1% of the total number of samples required for conventional imaging, even under conditions wherein the SNR is as low as 5 dB.
Journal ArticleDOI
Statistics-based baseline-free approach for rapid inspection of delamination in composite structures using ultrasonic guided waves
TL;DR: In this article , a baseline-free statistical approach for the identification and localization of delamination using sparse sampling and density-based spatial clustering of applications with noise (DBSCAN) technique is proposed.
Posted Content
Taming Non-stationary Bandits: A Bayesian Approach
Vishnu Raj,Sheetal Kalyani +1 more
TL;DR: This work proposes a variant of Thompson Sampling which can be used in both rested and restless bandit scenarios and derives the exact expression for the probability of picking sub-optimal arms from the parameters of prior distribution.