Panos Markopoulos Headshot

Panos Markopoulos

Associate Professor

Department of Electrical and Microelectronic Engineering
Kate Gleason College of Engineering
Program Faculty, School of Mathematical Sciences

585-475-7917
Office Location

Panos Markopoulos

Associate Professor

Department of Electrical and Microelectronic Engineering
Kate Gleason College of Engineering
Program Faculty, School of Mathematical Sciences

Education

Ph.D., Electrical Engineering, The State University of New York at Buffalo; MS, Electronic and Computer Engineering; Diploma of Engineering, Electronic and Computer Engineering, Technical University of Crete (Greece)

Bio

Dr. Panos P. Markopoulos is an Associate Professor of Electrical Engineering with the Rochester Institute of Technology, Rochester NY, USA, where he directs the Machine Learning Optimization and Signal Processing Lab (miloslab.org). In 2018 and 2020, he was a Summer Visiting Research Faculty at the U.S. Air Force Research Laboratory, Information Directorate, in Rome NY. He received a Ph.D. degree in Electrical Engineering from The State University of New York at Buffalo, in 2015.

His research expertise is in the areas of machine learning, data analysis, and communications, based on statistical signal processing and mathematical optimization. In these areas, he has co-authored more than 60 journal and conference articles. His current focus is on theory and algorithms for dynamic and robust tensor-data processing.

Dr. Markopoulos’s research has been supported with multiple grants from the U.S. National Science Foundation (NSF), the U.S. National Geo-Spatial Intelligence Agency (NGA), the U.S. Air Force Office of Scientific Research (AFOSR), U.S. Air Force Research Lab (AFRL), as well as industry partners such as L3Harris. He is a member of IEEE, SPIE, and SIAM, with high service activity including, the organization of the IEEE International Workshop on Machine Learning for Signal Processing (IEEE MLSP 2019).

Dr. Markopoulos has received multiple research, teaching, and service  awards, including the Best Paper Award in Physical-Layer Communications at the 2013 International Symposium on Wireless Communication Systems and the Exemplary Reviewer Award from the IEEE Communications Society in 2017. RIT KGCOE has recognized Dr. Markopoulos for his  "Exemplary Performance in Research" (2017, 2018) and his  "Exemplary Performance in Teaching" (2018). In 2020, Dr. Markopoulos received the prestigious AFOSR Young Investigator Award.

585-475-7917

Areas of Expertise

Select Scholarship

Book Chapter
Ahmad, Fauzia and Panos Markopoulos. "L1-norm Principal-component and Ddiscriminant Aanalyses of Micro-Doppler Signatures for Indoor Human Activity Recognition." Micro-Doppler Radar and its Applications. Ed. F. Fioranelli, et al. -, -: IET Press, 2020. -. Web.
Markopoulos, Panos, et al. "Outlier-resistant data processing with L1-norm principal component analysis." Advances in Principal Component Analysis: Research and Development. Ed. Ganesh R. Naik. -, -: Springer Singapore, 2018. -. Print.

Currently Teaching

IMGS-890
1 - 6 Credits
Doctoral-level research by the candidate on an appropriate topic as arranged between the candidate and the research advisor.
EEEE-484
3 Credits
Introduction to Communication Systems provides the basics of the formation, transmission and reception of information over communication channels. Spectral density and correlation descriptions for deterministic and stationary random signals. Amplitude and angle modulation methods (e.g. AM and FM) for continuous signals. Carrier detection and synchronization. Phase-locked loop and its application. Introduction to digital communication. Binary ASK, FSK and PSK. Noise effects. Optimum detection: matched filters, maximum-likelihood reception. Computer simulation.
EEEE-647
3 Credits
The course will start with the history of artificial intelligence and its development over the years. There have been many attempts to define and generate artificial intelligence. As a result of these attempts, many artificial intelligence techniques have been developed and applied to solve real life problems. This course will explore variety of artificial intelligence techniques, and their applications and limitations. Some of the AI techniques to be covered in this course are intelligent agents, problem-solving, knowledge and reasoning, uncertainty, decision making, learning (Neural networks and Bayesian networks), reinforcement learning, swarm intelligence, Genetic algorithms, particle swarm optimization, applications in robotics, controls, and communications. Students are expected to have any of the following programming skills listed above. Students will write an IEEE conference paper.
EEEE-547
3 Credits
The course will start with the history of artificial intelligence and its development over the years. There have been many attempts to define and generate artificial intelligence. As a result of these attempts, many artificial intelligence techniques have been developed and applied to solve real life problems. This course will explore variety of artificial intelligence techniques, and their applications and limitations. Some of the AI techniques to be covered in this course are intelligent agents, problem-solving, knowledge and reasoning, uncertainty, decision making, learning (Neural networks and Bayesian networks), reinforcement learning, swarm intelligence, Genetic algorithms, particle swarm optimization, applications in robotics, controls, and communications. Students are expected to have any of the following programming skills listed above. Students will write an IEEE conference paper.
EEEE-594
3 Credits
This course offers a broad overview of sensor-array processing, with a focus on wireless communications. It aims at providing g the students with essential and advanced theoretical and technical knowledge that finds direct application in modern wireless communication systems that employ multi-sensor arrays and/or apply user-multiplexing in the code domain (CDMA). Theory and practices covered in this course can be extended in fields such as radar, sonar, hyperspectral image processing, and biomedical signal processing. Topics covered: uniform linear antenna arrays (inter-element spacing and Nyquist sampling in space); linear beamforming, array beam patterns, array gain, and spatial diversity; interference suppression in the absence of noise (null-steering beamforming); optimal beamforming in AWGN (matched filter); optimal beamforming in the presence of colored interference; estimation of filters from finite measurements and adaptive beamforming (SMI and variants, RLS, LMS and variants, CMA, and AV); BPSK demodulation with antenna arrays (multiple users and AWGN); BPSK demodulation in CDMA (multiple users and AWGN); ML and subspace methods (MUSIC, root MUSIC, Minimum-norm, Linear Predictor, Pisarenko) for Direction-of-arrival estimation; BPSK demodulation with antenna arrays in CDMA systems (space-time processing).
EEEE-694
3 Credits
This course offers a broad overview of sensor-array processing, with a focus on wireless communications. It aims at providing the students with essential and advanced theoretical and technical knowledge that finds direct application in modern wireless communication systems that employ multi-sensor arrays and/or apply user-multiplexing in the code domain (CDMA). Theory and practices covered in this course can be extended in fields such as radar, sonar, hyperspectral image processing, and biomedical signal processing. Topics covered: uniform linear antenna arrays (inter-element spacing and Nyquist sampling in space); linear beamforming, array beam patterns, array gain, and spatial diversity; interference suppression in the absence of noise (null-steering beamforming); optimal beamforming in AWGN (matched filter); optimal beamforming in the presence of colored interference; estimation of filters from finite measurements and adaptive beamforming (SMI and variants, RLS, LMS and variants, CMA, and AV); BPSK demodulation with antenna arrays (multiple users and AWGN); BPSK demodulation in CDMA (multiple users and AWGN); ML and subspace methods (MUSIC, root MUSIC, Minimum-norm, Linear Predictor, Pisarenko) for Direction-of-arrival estimation; BPSK demodulation with antenna arrays in CDMA systems (space-time processing).

In the News