Milos Doroslovacki

Headshot of Milos Doroslovacki
Title:
Associate Professor
Office:
SEH 6620 | Office hours: By appointment
Phone:
202-994-6916
Email:
[email protected]

 

Professor Milos Doroslovacki conducts research in signal processing, communication signals and systems, discrete-time signal and system theory, and wavelets and their applications. Recent projects have been centered on adaptive wavelet-based  echo cancellation for voice transmission over digital networks, attitude rate estimation using GPS, techniques for automatic recognition of modulations, sparse system identification, distributed estimation, Bayesian learning, machine learning, and signal processing for hardware security.

 

  • B.S., University of Belgrade, 1979
  • M.S., University of Belgrade, 1984
  • Ph.D., University of Cincinnati, 1994
  • Signal and Image Processing
  • Signal and System Theory
  • Communications
  • Detection, Estimation, and Machine Learning
  • S. Wang, A. Etemadi, and M. Doroslovački, “ Adaptive cascaded delayed signal cancellation PLL for three-phase grid under unbalanced and distorted condition,” Electric Power Systems Research, Vol. 180, March 2020.
  • F. Yao, M. Doroslovački, and G. Venkataramani, “Covert timing channels exploiting cache coherence hardware: characterization and defense,” International Journal of Parallel Programming, Vol. 47, Issue 4, pp. 595-620, August 2019.
  • H. Fang, S. S. Dayapule, F. Yao, M. Doroslovački, and G. Venkataramani, “PrODACT: Prefetch obfuscator to defend against cache timing channels,” International Journal of Parallel Programming, Vol. 47, Issue 4, pp. 571-594, August 2019.
  • P. Radamacher and M. Doroslovački, “Bayesian learning for classification using a uniform Dirichlet prior,” IEEE Global Conference on Signal and Information Processing (GlobalSIP), Ottawa, Canada, November 2019.
  • P. Radamacher and M. Doroslovački, “Predictive distribution estimation for Bayesian machine learning using a Dirichlet process prior,” Fifty-Third Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, November 2019.
  • L. Li, M. Doroslovački, and M. Loew, “Loss functions forcing cluster separations for multi-class classification using deep neural networks,” Fifty-Third Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, November 2019.
  • F. Yao, H. Fang, M. Doroslovački, and G. Venkataramani, “Leveraging cache management hardware for practical defense against cache timing channel attacks,” IEEE Micro, Vol. 39, Issue 4, pp. 8-16, July 2019.
  • F. Yao, H. Fang, M. Doroslovački, and G. Venkataramani, “COTSknight: practical defense against cache timing channel attacks using cache monitoring and partitioning technologies,” IEEE International Symposium on Hardware Oriented Security and Trust, 10 pages, Tyson Corner, VA, May 2019.
  • H. Fang, M. Doroslovački, and G. Venkataramani, “EraseMe: a defense mechanism against information leakage exploiting GPU memory,” Twenty-Nineth ACM Great Lakes Symposium on VLSI , 4 pages, Washington, DC, May 2019.
  • H. Fang, F. Yao, M. Doroslovački, and G. Venkataramani, “Negative correlation, non-linear filtering, and discovering of repetitiveness for cache timing channel detection,” IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 2522-2526, Brighton, United Kingdom, May 2019.
  • L. Li, M. Doroslovački, and M. Loew, “Discriminant analysis deep neural networks,” Fifty-Third Annual Conference on Information Sciences and Systems, 6 pages, JHU, Baltimore, MD, March 2019.
  • M. Bari, A. Ambaw, and M. Doroslovački, “Comparison of machine learning algorithms for raw handwritten digits recognition,” Fifty-Second Asilomar Conference on Signals, Systems and Computers, pp. 1512-1516, Pacific Grove, CA, Oct. 2018.
  • H. Fang, S. S. Dayapule, F. Yao, M. Doroslovački, and G. Venkataramani, “A noise-resilient detection method against advanced cache timing channel attack,” Fifty-Second Asilomar Conference on Signals, Systems and Computers, pp. 237-241, Pacific Grove, CA, Oct. 2018.
  • F. Yao, H. Fang, M. Doroslovački, and G. Venkataramani, “WiP: Towards a stronger indicator for detecting cache timing channel,” Hardware and Architectural Support for Security and Privacy (HASP), 4 pages, Los Angeles, CA, June 2018.
  • H. Fang, S. S. Dayapule, F. Yao, M. Doroslovački, and G. Venkataramani, “Prefetch-guard: Leveraging hardware prefetchers to defend against cache timing channels,” IEEE International Symposium on Hardware Oriented Security and Trust (HOST), Washington, DC, May 2018.
  • F. Yao, M. Doroslovački, and G. Venkataramani, “Are coherent protocol states vulnerable to information leakage?,” 24th IEEE International Symposium on High-Performance Computer Architecture, Vienna, Austria, Feb. 24-28, 2018.
  • Ambaw and M. Doroslovački, “Feature based order recognition of continuous-phase FSK using principal component analysis,” 51st Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, Oct.-Nov. 2017.
  • M. Alagappan, J. Rajendran, M. Doroslovački, and G. Venkataramani, “DSF covert channels on multicore platforms,” IFIP/IEEE VLSI-SoC 2017, Abu Dhabi, UAE, Oct. 2017.
  • F. Yao, G. Venkataramani, and M. Doroslovački, “Covert timing channels exploiting non-uniform memory access based architectures,” The 27th ACM Great Lakes Symposium on VLSI, Banff, Alberta, Canada, pp. 155-160, May 10-12, 2017.
  • K. T. Wagner and M. I. Doroslovački, “Distributed linear prediction in the presence of noise and multipath,” 51st Annual Conference on Information Sciences and Systems, paper 4068, Baltimore, MD, March 22-24, 2017.
  • Ambaw, M. Bari, and M. I. Doroslovački, “A case for stacked autoencoder based order recognition of continuous-phase FSK,” 51st Annual Conference on Information Sciences and Systems, paper 4126, Baltimore, MD, March 22-24, 2017.
  • M. Bari, H. Taher, S. Saad Sherazi, and M. Doroslovački, “Supervised machine learning for signals having RRC shaped pulses,” Fiftieth Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, pp. x+1- x+5, November 2016.
  • K. T. Wagner and M. I. Doroslovački, “Distributed linear prediction of a single source,” Fiftieth Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, pp. x+1- x+5, November 2016.
  • G. Venkataramani, J. Chen,  M. Doroslovački, "Detecting Hardware Covert Timing Channels," IEEE Micro, pp. 17-27, 2016.
  • M. Bari, M. Doroslovački, "Distinguishing CPFSK From QAM and PSK Modulations," Circuits, Systems, Signal Processing, vol. 35, no. 4, pp. 1355-1375,  2016.
  • K. T. Wagner, M. I. Doroslovački, "Distributed LMS Estimation of Scaled and Delayed Impulse Responses," 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing, Shanghai,China, pp. 4154-4158, 2016.
  • K. Wagner, M. Doroslovački, “Proportionate-type Normalized Least Mean Square Algorithms,” Wiley-ISTE, 2013.
  • H. Asfour, L. M. Swift, N. Sarvazyan, M. Doroslovački, M. W. Kay, "Signal Decomposition of Transmembrane Voltage-Sensitive Dye Fluorescence Using a Multi-Resolution Wavelet Analysis," IEEE Transactions on Biomedical Engineering, vol. 58, no. 7, pp. 2083-2093, 2011
  • K. Wagner and M. Doroslovački, "Probability density of weight deviations given preceding weight deviations for proportionate-type LMS adaptive algorithms," IEEE Signal Processing Letters, Vol. 18, No. 11, pp. 667-670, November 2011.
  • H. Assfur, L. M. Swift, N. Sarvazyan, M. Doroslovački, M. W. Kay, "Signal decomposition of transmembrane voltage-sensitive dye fluorescence using a multi-resolution wavelet analysis," IEEE Transactions on Biomedical Engineering, Vol. 58, No. 7, pp. 2083-2093, July 2011.
  • K. Wagner and M. Doroslovački, "Proportionate-type normalized least mean square algorithms with gain allocation motivated by mean-square-error minimization for white input," IEEE Transaction on Signal Processing, Vol. 59, No. 5, pp. 2410-2415, May 2011.
  • K. Wagner and M. Doroslovački, "On proportionate-type NLMS algorithms for fast decay of output error at all times," Proc. 43th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 1 - 4, 2009.
  • X. (S.) Lin, A. W. H. Khong, M. Doroslovački, and P. A. Naylor, "Frequency-domain adaptive algorithm for network echo cancellation in VoIP," EURASIP Journal on Audio, Speech, and Music Processing, Vol. 2008, Article ID 156960, 9 pages, doi:10.1155/2008/156960, May 18, 2008.
  • H. Mustafa and M. Doroslovački, "Expansion of cumulant-based classifier to frequency shift keying modulations and to the use of support vector machines," European Transactions on Telecommunications, Vol. 19, No. 1, pp. 23-28, January - February 2008, published online April 23, 2007, doi: 10.1002/ett.1220.
  • W. Wasylkiwskyj, I. Kopriva, and M. Doroslovački, "Image frequency suppression in frequency-scanned direction-of-arrival estimation systems," IET Proc. - Radar Sonar Navig., Vol. 1, No. 3, pp. 191-197, June 2007.
  • W. Wasylkiwskyj, I. Kopriva, M. Doroslovački, and A. Zaghloul, "A new root-based direction finding algorithm," Radio Science, Vol. 42, No. 2, RS2S90, doi:10.1029/2004RS003147, April 2007.
  • H. Deng and M. Doroslovački, "Wavelet-based MPNLMS adaptive algorithm for network echo cancellation," EURASIP Journal on Audio, Speech, & Music Processing: Special Issue on Adaptive Partial-Update and Sparse System Identification, Vol. 2007, article ID 96101, 5 pages, doi: 10.1155/2007/96101, March 2007.
  • H. Deng and M. Doroslovački, "Proportionate adaptive algorithms for network echo cancellation," IEEE Trans. Signal Processing, Vol. 54, No. 5, pp. 1794-1803, May 2006.
  • M. Doroslovački and H. Deng, "On convergence of proportionate-type NLMS adaptive algorithms," Proc. of the 2006 IEEE International Conference on Acoustics, Speech & Signal Processing, Vol. 3, pp. 105-108, Toulouse, France, May 14 - 19, 2006.
  • M. I. Doroslovački and E. G. Larsson, "Nonuniform linear antenna arrays minimizing Cramer-Rao bounds for joint estimation of single source range and direction of arrival," IEE Proc. - Radar Sonar Navig., Vol. 152, No. 4, pp. 225-231, August 2005.
  • H. Deng and M. Doroslovački, "Improving convergence of the PNLMS algorithm for sparse impulse response identification," IEEE Signal Processing Letters, pp. 181-184, Vol. 12, No. 3, March 2005.
  • The Silver Anniversary Faculty Award, The George Washington University, May 2020.
  • American Men and Women of Science, Gale Cengage Learning, September 2015.
  • Individual of Outstanding Thought Leadership, Research Institute, August 2015.
  • Reviewer for NSF
  • General Chair, Asilomar Conference on Signals, Systems, and Computers, 2012
  • Technical Program Chair, Asilomar Conference on Signals, Systems, and Computers, 2010
  • Consultant for Aker Kvaerner Subsea Limited, Aberdeen, UK; Texas Instruments.
  • Reviewer for many professional journals (including several IEEE transactions)
  • Reviewer for many professional conferences (including several IEEE and EURASIP ones)