Kursat R. Mestav is a Machine Learning researcher in the Mathematics & Algorithms Research Group at Bell Labs. His research interests are in the areas of machine learning and statistical signal processing. He is particularly interested in problems related to generative models and anomaly detection.
Prior to Bell Labs, he was a Senior Machine Learning Systems Researcher at Qualcomm in San Diego, California.
Ph.D. degree in Electrical and Computer Engineering, Cornell University - Ithaca, NY
M.S. degree in Electrical and Computer Engineering, Cornell University - Ithaca, NY
B.S. degree in Electrical and Electronics Engineering, Bilkent University - Ankara, Turkey
Selected articles and publications
A Deep Learning Approach to Anomaly Sequence Detection for High-Resolution Monitoring of Power Systems
K. R. Mestav, X. Wang, and L. Tong, IEEE Transactions on Power Systems, Early Access Article, Apr 2022.
Universal Data Anomaly Detection via Inverse Generative Adversary Network
K. R. Mestav, and L. Tong, IEEE Signal Processing Letters, vol. 27, pp. 511-515, 2020.
Bayesian State Estimation for Unobservable Distribution Systems via Deep Learning
K. R. Mestav, J. Luengo-Rozas, and L. Tong, IEEE Transactions on Power Systems, vol. 34, no. 6, pp. 4910–4920, Nov 2019.
Learning the Unobservable: High-Resolution State Estimation via Deep Learning
K. R. Mestav, and L. Tong 57th Annual Allerton Conference on Communication, Control, and Computing, December 2019.
State Estimation in Smart Distribution Systems with Deep Generative Adversary Networks
K. R. Mestav, and L. Tong IEEE SmartGridComm, November 2019.
State Estimation for Unobservable Distribution Systems via Deep Neural Networks
K. R. Mestav, J. Luengo-Rozas, and L. Tong IEEE Power Energy Society General Meeting, July 2018.