Papers under preparation
  1. Yunzhe Xue and Usman Roshan, Why are 01 loss sign activation neural network ensembles hard to attack?

  2. Yunzhe Xue, Olanrewaju Eletta, Justin W Ady, Nell Maloney Patel, Advaith Bongu, and Usman Roshan, A mobile phone app to assess medical student performance in surgical knot tying simulation
Abstracts and posters
  1. Hu, A. Roshan U, Ady J, Muralidhar R, Getrajdman J, Cai J, Maloney-Patel N, Bongu A. AI Model Improvement of FLS PEG Transfer Competency After Video Annotation Optimization. Oral Presentation at ACS Surgeons and Engineers Conference 2024, Chicago, IL (3/13/2024).

  2. Eletta O, Hu A, Xue Y, Roshan U, Ady JW, Cai J, Getrajdman J, Maloney-Patel N, Bongu A. Machine Learning System For Performance Feedback Using Low Cost Surgical Simulator. American College of Surgeons Clinical Congress 2023, Boston MA. [oral presentation 10/25/2023]

  3. Meiyan Xie, Yunzhu Li, Yunzhe Xue, Lauren Huntress, William Beckerman, Saum A. Rahimi, Justin W. Ady, and Usman W. Roshan, Two-stage and dual-decoder convolutional U-Net ensembles for reliable vessel and plaque segmentation in carotid ultrasound images, accepted to The 49th Annual Symposium of the Society for Clinical Vascular Surgery, 2021

  4. Automated Vessel Lumen Identification in B-Mode Carotid Ultrasound Images Using Convolutional Neural Networks, Dr Lauren Huntress, MD; Meiyan Xie; William Beckerman, MD; Saum A. Rahimi, MD; Randy Shafritz, MD; Usman Roshan, PhD; Justin W. Ady, MD, accepted to The 48th Annual Symposium of the Society for Clinical Vascular Surgery, 2020 (Abstract on symposium site)
Publications (peer-reviewed)
  1. Yunzhe Xue, Andrew Hu, Rohit Muralidhar, Justin W. Ady, Advaith Bongu, and Usman Roshan, An AI system for evaluating pass fail in fundamentals of laparoscopic surgery from live video in realtime with performative feedback, accepted to The 6th Workshop in Artificial Intelligence Techniques for BioMedicine and Healthcare, IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2023 (local link to paper)

  2. Yunzhe Xue and Usman Roshan, Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble, accepted to 22nd IEEE International Conference on Machine Learning and Applications (ICMLA), 2023, (local link to paper)

  3. Yunzhe Xue and Usman Roshan, The accuracy of white-box and black-box adversarial attacks on 01 loss neural network models, accepted to ICLR Tiny Papers track, 2023 (OpenReview link, DBLP link)

  4. Yunzhe Xue, Olanrewaju Eletta, Justin W Ady, Nell Maloney Patel, Advaith Bongu, and Usman Roshan, A cascaded neural network system for rating student performance in surgical knot tying simulation, accepted to 11th IEEE International Conference on Healthcare Informatics (ICHI), 2023, (PDF, local link to paper)

  5. Yang, Yanan, Frank Y. Shih, and Usman Roshan. Defense Against Adversarial Attacks Based on Stochastic Descent Sign Activation Networks on Medical Images, International Journal of Pattern Recognition and Artificial Intelligence, vol 36 no 03, 2254005, 2022, (local link to paper)

  6. Meiyan Xie, Yunzhu Li, Yunzhe Xue, Lauren Huntress, William Beckerman, Saum A. Rahimi, Justin W. Ady, and Usman W. Roshan, Vessel lumen segmentation in carotid artery ultrasounds with the U-Net convolutional neural network, accepted to The 3rd Workshop in Artificial Intelligence Techniques for BioMedicine and Healthcare, IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020 (local link to paper)

  7. Abdulrhman Aljouie, Yunzhe Xue, Meiyan Xie, and Usman Roshan, Challenges in predicting glioma survival time in multi-modal deep networks. accepted to The 3rd Workshop in Artificial Intelligence Techniques for BioMedicine and Healthcare, IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020 (local link to paper)

  8. Zhibo Yang, Yanan Yang, Yunzhe Xue, Frank Y. Shih, Justin Ady, Usman Roshan, Accurate and adversarially robust classification of medical images and ECG time-series with gradient-free trained sign activation neural networks, accepted to The 4rd International Workshop on Deep Learning in Bioinformatics, Biomedicine, and Healthcare Informatics (DLB2H), Workshop at IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020 (local link to paper)

  9. Meiyan Xie, Yunzhu Li, Yunzhe Xue, Lauren Huntress, William Beckerman, Saum A. Rahimi, Justin W. Ady, and Usman W. Roshan, Two-stage and dual-decoder convolutional U-Net ensembles for reliable vessel and plaque segmentation in carotid ultrasound images, accepted to 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020 (local link to paper)

  10. Yunzhe Xue, Meiyan Xie, and Usman Roshan, Towards adversarially robust classification with 01 loss neural networks, accepted to 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020 (local link to paper, Supplementary Material)

  11. Yunzhe Xue, Meiyan Xie, and Usman Roshan, On the transferability of adversarial examples between convex and 01 loss models, accepted to 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020 (local link to paper , Supplementary Material)

  12. Yanan Yang, Fadi Farhat, Yunzhe Xue, Frank Y. Shih, Usman Roshan, Classifying histopathology images with random depthwise convolutional neural networks, accepted to ACM 7th International Conference on Bioinformatics Research and Applications (ICBRA), 2020 (local link to paper)

  13. Lauren Huntress, Meiyan Xie, Shih-Yau G. Huang, William Beckerman, Saum A. Rahimi, Usman Roshan, Justin W. Ady, An Ensemble-Based Confidence Score to Increase Accuracy of Carotid Ultrasound Vessel Lumen Segmentation by Convolutional Neural Networks, Journal of Vascular Surgery, Volume 72, Issue 1, E235-E236, 2020 (PDF)

  14. Yunzhe Xue, Yanan Yang, Fadi Farhat, Frank Y. Shih, Olga Boukrina, A. M. Barrett, Jeffrey R. Binder, William W. Graves, and Usman W. Roshan, Brain tumor classification with tumor segmentations and a dual path residual convolutional neural network from MRI and pathology images, accepted to Proceedings of the MICCAI Radiology-Pathology Challenge on Brain Tumor Classification (CPM-RadPath), 2019 (local link to paper)

  15. Yunzhe Xue, Meiyan Xie, Fadi Farhat, Olga Boukrina, A. M. Barrett, Jeffrey R. Binder, Usman W. Roshan, and William W. Graves, A multi-path decoder network for brain tumor segmentation, accepted to Proceedings of the MICCAI Multimodal Brain Tumor Segmentation Challenge (BraTS), 2019 (local link to paper)

  16. Yunzhe Xue, Fadi Farhat, Olga Boukrina, A. M. Barrett, Jeffrey R. Binder, Usman W. Roshan, William W. Graves, A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images, accepted to NeuroImage:Clinical, 2019 (PDF)

  17. Meiyan Xie, Yunzhu Li, Yunzhe Xue, Randy Shafritz, Saum A. Rahimi, Justin W. Ady, and Usman W. Roshan, Vessel lumen segmentation in internal carotid artery ultrasounds with deep convolutional neural networks, accepted to The 3rd International Workshop on Deep Learning in Bioinformatics, Biomedicine, and Healthcare Informatics (DLB2H), Workshop at IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2019 (local link to paper)

  18. Abdulrhman Aljouie and Usman W. Roshan, Multi-path convolutional neural network for glioblastoma survival group prediction with point mutations and demographic features, accepted to Machine Learning and Artificial Intelligence in Bioinformatics and Medical Informatics (MABM), Workshop at IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2019 (local link to paper)

  19. Yunzhe Xue, Meiyan Xie, Fadi Farhat, Olga Boukrina, A. M. Barrett, Jeffrey R. Binder, Usman W. Roshan, William W. Graves, A fully 3D multi-path convolutional neural network with feature fusion and feature weighting for automatic lesion identification in brain MRI images, extended abstract in ML4H: Machine Learning for Health, Workshop at NeurIPS, 2019 (ML4H electronic proceedings, ArXiv)

  20. Meiyan Xie, Yunzhe Xue, and Usman Roshan, Stochastic coordinate descent for 0/1 loss and its sensitivity to adversarial attacks, accepted to the 18th IEEE International Conference on Machine Learning and Applications (ICMLA), 2019 (PDF, local link to paper)

  21. Abdulrhman Aljouie, Michael Schatz, and Usman Roshan, Machine learning based prediction of gliomas with germline mutations obtained from whole exome sequences from TCGA and 1000 Genomes Project, accepted to The Third IEEE International Conference on Intelligent Computing in Data Sciences (ICDS), 2019 (PDF, local link to paper)

  22. Yunzhe Xue and Usman Roshan, Image classification and retrieval with random depthwise signed convolutional neural networks, Proceedings of the 15th International Work-Conference on Artificial Neural Networks (IWANN), Rojas I., Joya G., Catala A. (eds) Advances in Computational Intelligence. Lecture Notes in Computer Science, vol 11506, pp 492-506, 2019 (PDF, ArXiv)

  23. Meiyan Xie and Usman Roshan, Exploring classification, clustering, and its limits in a compressed hidden space of a single layer neural network with random weights, Proceedings of the 15th International Work-Conference on Artificial Neural Networks (IWANN), Rojas I., Joya G., Catala A. (eds) Advances in Computational Intelligence. Lecture Notes in Computer Science, vol 11506, pp 507-516, 2019 (PDF, local link to paper)

  24. Xin Yin, Vincenzo Musco, Iulian Neamtiu, and Usman Roshan, Statistically Rigorous Testing of Clustering Implementations, Proceedings of IEEE International Conference on AI Testing (AITest), Newark, CA, USA, pp 91-98, 2019 (PDF, local link to paper)

  25. Abdulrhman Aljouie, Ling Zhong, and Usman Roshan, High scoring segment selection for pairwise whole genome sequence alignment with the maximum scoring subsequence and GPUs, accepted and presented at the International Conference on Intelligent Biology and Medicine (ICIBM) 2018, to be published in International Journal of Computational Biology and Drug Design, 2018 (PDF, local link to paper)

  26. Abdulrhman Aljouie, Nihir Patel, and Usman Roshan, Cross-validation and cross-study validation of kidney cancer with machine learning and whole exome sequences from the National Cancer Institute, Proceedings of the IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), St. Louis, MO, USA, pp 1-6, 2018 (PDF, local link to paper)

  27. Paul Melman and Usman Roshan, A k-means based feature learning method for protein sequence classification, Proceedings of the ISCA International Conference on Bioinformatics and Computational Biology (BICOB), pp 99-104, 2018 (Proceedings, local link to paper)

  28. Abdulrhman Aljouie, Nihir Patel, and Usman Roshan, Cross-validation and cross-study validation of chronic lymphocytic leukemia with exome sequences and machine learning, International Journal of Data Mining and Bioinformatics, 2016 (PDF, local link to paper)

  29. Nihir Patel, Abdulrhman Aljouie, Bharati Jhadav, and Usman Roshan, Cross-validation and cross-study validation of chronic lymphocytic leukemia with exome sequences and machine learning, Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2015 (PDF, local link to paper)

  30. Abdulrhman Aljouie and Usman Roshan, Prediction of continous phenotypes in mouse, fly, and rice genome wide association studies with support vector regression SNPs and ridge regression classifier, Proceedings of the 14th IEEE International Conference on Machine Learning and Applications (ICMLA), 2015 (PDF, local link to paper)

  31. Abdulrhman Aljoiue, Mohammedreza Esfandiari, Srividya Ramakrishnan, and Usman Roshan, Chi8: a GPU program for detecting significant interacting SNPs with the chi-square 8-df test, BMC Research Notes, 8:436, 2015 (PDF) (Source code)

  32. Turki Turki and Usman Roshan, MaxSSmap: A GPU program for mapping divergent short reads to genomes with the maximum scoring subsequence, BMC Genomics, 15(1)1:969, 2014 (PDF) (Source code)

  33. Turki Turki, Muhammad Amimul Ihsan, Nouf Turki, Jie Zhang, Usman Roshan, and Zhi Wei, Top-k parameterized boost, Proceedings of the Second International Conference on Mining Intelligence and Knowledge Exploration, University College Cork, Ireland, 2014 (Springer link) (PDF)

  34. Turki Turki and Usman Roshan, Weighted maximum variance dimensionality reduction, Proceedings of the 6th Mexican Conference on Pattern Recognition, Cancun, Mexico, 2014 (Springer link) (PDF) (Source code)

  35. U. Roshan (corresponding author), S. Chikkagoudar, Z. Wei, K. Wang, and H. Hakonarson, Ranking causal SNPs and disease associated regions in genome wide association studies by the support vector machine and random forest, Nucleic Acids Research, 2011 (PDF)

  36. S. Chikkagoudar , D. R. Livesay, and U. Roshan (corresponding author) PLAST-ncRNA: Partition function Local Alignment Search Tool for non-coding RNA sequences, Nucleic Acids Research, 2010 (PDF) (webserver)

  37. U. Roshan (corresponding author), S. Chikkagoudar, and D. R. Livesay, Searching for RNA homologs within large genomic sequences using partition function posterior probabilities, BMC Bioinformatics, 9:61, 2008 (PDF)

  38. D. R. Livesay, P. D. Kidd, S. Eskandari, and U. Roshan, Assessing the ability of sequence-based methods to provide functional insight within membrane integral proteins: a case study analyzing the neurotransmitter/Na+ symporter family BMC Bioinformatics, 8:397, 2007 (PDF)

  39. S. Chikkagoudar, U. Roshan (corresponding author) and D. R. Livesay, eProbalign: generation and manipulation of multiple sequence alignments using partition function posterior probabilities, Nucleic Acids Research, Vol 35, 2007, W675-W677 PDF (webserver)

  40. U. Roshan (corresponding author) and D. R. Livesay, Probalign: multiple sequence alignment using partition function posterior probabilities, Bioinformatics, 22(22), 2006, 2715-21 (PDF)

  41. C. Coarfa, Y. Dotsenko, J. Mellor-Crummey, L. Nakhleh, and U. Roshan, PRec-I-DCM3: A Parallel Framework for Fast and Accurate Large Scale Phylogeny Reconstruction, International Journal on Bioinformatics Research and Applications, 2(4), 2006, 407-419 (PDF)

  42. U. Roshan, D. R. Livesay, and S. Chikkagoudar, Improving progressive alignment for phylogeny reconstruction using parsimonious guide-trees, Proceedings of The IEEE 6th Symposium on Bioinformatics and Bioengineering (BIBE06) Washington D.C., USA, 2006 (PDF)

  43. Z. Du, F. Lin, and U. Roshan, Reconstruction of large phylogenetic trees: a parallel approach, Computational Biology and Chemistry, 29(4), 2005, 273-280 (PDF)

  44. U. Roshan, D. R. Livesay, D. La, Improved phylogenetic motif detection using parsimony, Proceedings of The IEEE 5th Symposium on Bioinformatics and Bioengineering (BIBE05) Minneapolis, Minnesota, USA, 2005 (PDF)

  45. Z. Du, A. Stamatakis, F. Lin, U. Roshan, L. Nakhleh, Parallel divide-and-conquer phylogeny reconstruction by maximum likelihood, Proceedings of The 2005 International Conference on High Performance Computing and Communications (HPCC05) 2005, Naples, Italy, 2005 (PDF)

  46. C. Coarfa, Y. Dotsenko, J. Mellor-Crummey, L. Nakhleh, and U. Roshan, PRec-I-DCM3: A Parallel Framework for Fast and Accurate Large Scale Phylogeny Reconstruction, Proceedings of The First IEEE Workshop on High Performance Computing in Medicine and Biology (HiPCoMB 2005), Fukuoka, Japan, 2005 (PDF)

  47. U. Roshan, B. M. E. Moret, T. L. Williams, T. Warnow, Rec-I-DCM3: A Fast Algorithmic Technique for Reconstructing Large Phylogenetic Trees, Proceedings of the IEEE Computational Systems Bioinformatics (CSB04) Stanford (CA), USA, 2004 (PDF)

  48. I. S. Dhillon, E. M. Marcotte, U. Roshan (corresponding author), Diametrical Clustering for identifying anti- correlated gene clusters, Bioinformatics, 19, 2003, 1612-1619 (PDF)

  49. B. M. E. Moret, U. Roshan, T. Warnow, "Sequence length requirements for phylogenetic methods", Proc. 2nd Int'l Workshop on Algorithms in Bioinformatics (WABI02) Rome, Italy, 2002 Lecture Notes in Computer Science 2452, 343-356, Springer Verlag, Roderic Guido and Dan Gusfield, eds (PDF)

  50. L. Nakhleh, U. Roshan, L. Vawter, and T. Warnow, "Estimating the deviation from a molecular clock", Proc. 2nd Int'l Workshop on Algorithms in Bioinformatics (WABI02) Rome, Italy, 2002 Lecture Notes in Computer Science 2452, 287-299, Springer Verlag, R. Guido and D. Gusfield, eds (PDF)

  51. L. Nakhleh, B. M. E. Moret, U. Roshan, K. St. John, J. Sun, T. Warnow, "The accuracy of fast phylogenetic methods for large datasets", Proc. 7th Pacific Symposium on BioComputing (PSB02) Kauai, USA, 2002, World Scientific Pub, 211-222 (PDF)

  52. L. Nakhleh, U. Roshan (corresponding author), K. St. John, J. Sun, T. Warnow, Designing fast converging phylogenetic methods", Bioinformatics, 17, 2001, S190-S198 (PDF)

  53. L. Nakhleh, U. Roshan, K. St. John, J. Sun, T. Warnow, "The performance of phylogenetic methods on trees of bounded diameter", Proc. 1st Workshop on Algorithms in Bioinformatics (WABI01) Aarhus, Denmark, 2001, Lecture Notes in Computer Science 2149, 189-203, Springer Verlag, Olivier Gascuel and B. M. E. Moret, eds (PDF)

  54. L. Nakhleh, U. Roshan (corresponding author), K. St. John, J. Sun, T. Warnow, Designing fast converging phylogenetic methods", Proceedings of The 9th Int'l Conference on Intelligent Systems on Molecular Biology (ISMB01) Copenhagen, Denmark, 2001 (PDF)
Book Chapters
  1. U. Roshan, Multiple sequence alignment using Probcons and Probalign, in "Methods in Molecular Biology: Multiple Sequence Alignment Methods", ed. David J. Russell, Humana Press (Springer), 2013, 147-155 (PDF, Springer link to book)

  2. K. M. Kjer, U. Roshan, and J. J. Gillespie, Structural and evolutionary considerations for multiple sequence alignment of RNA, and the challenges for algorithms that ignore them, in "Perspectives on Biological Sequence Alignment: Where, How, and Why It Matters", ed. Michael Rosenberg, University of California Press, USA, 2009, 105-151 (PDF)

  3. D. Bader, U. Roshan, and A. Stamatakis, Computational grand challenges in assembling the Tree of Life: problems and solutions, in "Advances in Computers, Computational Biology and Bioinformatics", ed. Marvin Zelkowitz and Chau-wen Tseng, Elsevier, 2006, 128-178 (PDF)

  4. U. Roshan, B. M. E. Moret, T. L. Williams, T. Warnow, Performance of supertree methods on various dataset decompositions in "Phylogenetic Supertrees: Combining Information to Reveal the Tree of Life", ed. O.R.P. Bininda Emonds, Springer, 2004, 301-329 (PDF)
Tutorials
  1. D. Bader, A. Stamatakis, and U. Roshan, Computational challenges in assembling the Tree of Life, peer reviewed tutorial presented at Supercomputing 2005 (SC05), Seattle, WA, USA
Unpublished
  1. Mohammedreza Esfandiari and Usman Roshan, EZPlanes: Ensemble of 0/1 loss local minima hyperplanes for classification (PDF)

  2. Pranitha Surya Andalam and Usman Roshan, Semi-Supervised Weighted Maximum Variance Dimensionality Reduction (PDF)

  3. Paras Garg and Usman Roshan, A study of multiple kernel learning for predicting type-1 diabetes from WTCCC genome wide association studies (PDF)

  4. U. Roshan, Fast and accurate population structure prediction using a greedy support vector machine clustering algorithm (PDF)

  5. U. Roshan, Semi-supervised feature extraction for population structure iden- tification using the Laplacian linear discriminant (PDF)