Publications

 On the asymptotic L1-PC of elliptical distributions, M. Dhanaraj and P. P. Markopoulos, IEEE Signal Processing Letters, vol. 29, pp. 2343-2347, Sept. 2022. [Link].

 Dynamic L1-norm Tucker tensor decomposition, D. G. Chachlakis, M. Dhanaraj, A. Prater-Bennette, and P. P. Markopoulos, IEEE Journal Selected Topics in Signal  Processing, vol. 15, no. 3, pp.  587-602, April 2021. [Link]

 YOLOrs: Object detection in multimodal remote sensing imagery, M. Sharma, M. Dhanaraj, S. Karnam, D. G. Chachlakis, R. Ptucha, P. P. Markopoulos, and E.  Saber, IEEE Journal Selected Topics in Applied Earth Obsereifjcbeciibfeivfdjgelbgcgvgbrbgbftntcnhibvations and Remote Sensing, vol. 14, pp. 1497-1508, November 2020. [Link]

 Adaptive L1-norm principal-component analysis with online outlier rejection, P. P. Markopoulos, M. Dhanaraj, and A. Savakis, IEEE Journal Selected Topics in  Signal Processing, vol. 12, no. 6, pp. 1-13, December 2018. [Link]

D. G. Chachlakis, M. Dhanaraj, P. P. Markopoulos, A. Prater-Bennette, and I. Tomeo, "D-L1-Tucker: Dynamic and Robust Analysis of Tensor Data Based on Absolute Projection Maximization," to appear in Handbook on Dynamic Data Driven Application Systems (Vol. II).

Robust stochastic principal component analysis via Barron loss. M. Dhanaraj and P. P. Markopoulos, in Proceedings IEEE Asilomar Conference on Signals, Systems, and Computers, pp 1286-1290, Oct. 2022 (also presenter). [Link]

Leveraging tensor methods in neural architecture search for the automatic development of lightweight convolutional neural networks, M. Dhanaraj, H. Do, D. Nair, C. Xu, in Proceedings SPIE, Big Data IV: Learning, Analytics, and Applications, Orlando, FL, April 2022 (also presenter). Paper received student travel grant. [Link]

 Vehicle detection from multi-modal aerial imagery using YOLOv3 with mid-level fusion, M. Dhanaraj, M. Sharma, T. Sarkar, S. Karnam, D. Chachlakis, R. Ptucha, P.  Markopoulos, and E. Saber, in Proceedings SPIE 11395, Big Data II: Learning, Analytics, and Applications, 1139506 , Anaheim, CA (online only), May 2020. [Link]

 Stochastic principal component analysis via mean absolute projection maximization, M. Dhanaraj and P. P. Markopoulos, in Proceedings IEEE Global  Conference on Signal and Information Processing (IEEE GlobalSIP 2019), Ottawa, Canada, November 2019. [Link] 

 Options for multimodal classification based on L1-Tucker decomposition, D. G. Chachlakis, M. Dhanaraj, P. P. Markopoulos, and A. Prater-Bennette, in 2019 SPIE  Defense and Commercial Sensing (SPIE DCS 2019) Baltimore, MD, April 2019.  [Link]

 Incremental complex L1-PCA for direction-of-arrival estimation, M. Dhanaraj, D. G. Chachlakis, and P. P. Markopoulos, in Proceedings IEEE Western New York  Signal and Image Processing Workshop (IEEE WNYSIPW 2018), Rochester, NY, October 2018.  [Link]

 Novel algorithm for incremental L1-norm principal-component analysis, M. Dhanaraj and P. P. Markopoulos, in Proceedings IEEE/EURASIP European Signal  Processing Conference (EUSIPCO 2018), Rome, Italy, September 2018.  [Link]

Dynamic Algorithms and Asymptotic Theory for Lp-norm Data Analysis. M. Dhanaraj, PhD Electrical and Computer Engineering, Kate Gleason College of Engineering, Rochester Institute of Technology, Rochester, NY, August 2022. [Link]

 Incremental and adaptive L1-norm principal component analysis: Novel algorithms and applications, M. Dhanaraj, MSEE thesis, Kate Gleason College of  Engineering, Rochester Institute of Technology, Rochester, NY, July 2018.  [Link]

Compressing neural networks towards edge artificial intelligence. M. Dhanaraj and  P. P. Markopoulos, Magazine of the Rochester Engineer, pp. 18-20, June 2022. [Link]