Principal Data Scientist

Dr. Beilei Xu serves as Principal Data Scientist at FLX and her research interests include image/video analytics, machine learning and statistical modeling.  She is currently working on applying machine learning in the quantitative finance space.   Prior to FLX she served as a senior research scientist at PARC, Conduent and Xerox, where she contributed and led a variety of projects ranging from data analytic research in managed print services, subsystem modeling of xerographic marking process, image rendering and image-based defect detection, to computer vision and machine learning research in healthcare and transportation.

Beilei holds a Ph.D. in Medical Physics from University of Chicago.  She is a certified Design for Lean Six Sigma Black Belt.  She has been a reviewer/referee for several journals and served on program committees and chaired sessions of conferences in the areas of image/video processing, healthcare, and transportation.  She has served on the review panel for the National Science Foundation grant review committees.  Beilei has published 39 papers, a book chapter and holds 120+ US patents with more pending applications.  She is a recipient of the Xerox Innovation Group President’s Award and the Xerox Anne Mulcahy Inventor Award for her contributions to Xerox intellectual property.

Publications

• S. Wshah, B. Xu, A. Cleveland, J. Bates, K. Morrissette, “Deep Fusion of Ultrasound Videos for Furosemide Classification,” International Symposium on Biomedical Imaging (ISBI), Mar. 2022. (Accepted)
• Z. Shangguan, L. Lin, W. Wu, B. Xu, “Neural Process for Black-Box Model Optimization Under Bayesian Framework,” AAAI 2021 Spring Symposium on Combining Artificial Intelligence and Machine Learning with Physics Sciences, Mar. 2021.
• W. Wu, B. Xu, E. Bernal, R. L. Hill, D. Desa, E. B. Brown, “Breast Cancer Tissue Sub-Region Classification from Second Harmonic Generation Imagery via Machine Learning,” Electronic Imaging, Jan. 2021.
• B. Xu, W. Wu, L. Lin, R. Melnyk, A. Ghazi, “Task Evoked Pupillary Response for Surgical Task Difficulty Prediction Multitask Learning,” Electronic Imaging, Jan. 2021.
• Lin, B. Xu, W. Wu, T. Richardson, E. A. Bernal, B. Martens, C. Thornton, C. Heatwole, “Deep Metric Learning with Triplet Networks: Application to Hand-grip Myotonia,” IEEE EMB Special Topic Conference on Healthcare Innovations and Point-of-Care Technologies, 2019
• Wu, B. Xu, E. A. Bernal, R. L. Hill, E. B. Brown, and D. Desa “Breast Cancer Tissue Sub-Type Classification from Second Harmonic Generation Images via Machine Learning,” IEEE EMB Special Topic Conference on Healthcare Innovations and Point-of-Care Technologies, 2019
• Cheng, B. Xu, W. Wu, L. Lin, T. Richardson, and E. A. Bernal, “An Unsupervised Machine Learning Framework for Parkinson’s Disease Progression Analysis and Subtyping,” IEEE EMB Special Topic Conference on Healthcare Innovations and Point-of-Care Technologies, 2019
• Shreve, R. Bala, W. Wu, B. Xu, P. Matts, A, Purwar, “Deep CNNs for Facial Skin Age Modeling,” accepted to International Conference on Machine Vision Applications, May 27–31 2019, Tokyo, Japan.
• Gavai, W. Wu, B. Xu, et. al., “Hybrid Image-based Defect Detection for Railroad Maintenance,” 2019 IS&T International Symposium on Electronic Imaging, Jan. 13-17, 2019, Burlingame, CA.
• Lei Lin, Beilei Xu, Wencheng Wu, Trevor W. Richardson, and Edgar A. Bernal.  “Medical Time Series Classification with Hierarchical Attention-based Temporal Convolutional Networks: A Case Study of Myotonic Dystrophy Diagnosis.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 83-86. 2019.
• Shangguan, L. Lin, W. Wu, B. Xu, “Neural Process for Black-Box Model Optimization Under Bayesian Framework,” AAAI-MLPS, Mar. 2021.
• Wu, B. Xu, E. Bernal, R. L. Hill, D. Desa, E. B. Brown, “Breast Cancer Tissue Sub-Region Classification from Second Harmonic Generation Imagery via Machine Learning,” Electronic Imaging, Jan. 2021.
• Xu, W. Wu, L. Lin, R. Melnyk, A. Ghazi, “Task Evoked Pupillary Response for Surgical Task Difficulty Prediction via Multitask Learning,” Electronic Imaging, Jan. 2021.
• Lin, W. Wu, S. Wshah, R. Elmoudi, B. Xu, “HPT-RL: Calibrating Power System Models based on Hierarchical Parameter Tuning and Reinforcement Learning,” IEEE International Conference on Machine Learning and Applications (ICMLA), Dec.14-17, 2020.
• Wu, L. Lin, S. Wshah, R. Elmoudi, B. Xu, “Generator Model Parameter Calibration Using Reinforcement Learning,” IEEE Green Energy and Smart Systems Conference (IGESSC), Nov. 2-3, 2020.
• Wshah, R. Shadid, Y. Wu, M. Matar, B. Xu, W. Wu, L. Lin, R. Elmoudi, “Deep Learning for Model Parameter Calibration in Power Systems,” IEEE International Conference on Power System Technology (POWERCON), Sept. 13-16, 2020.
• Richardson, E. Bernal, L. Lin, W. Wu, B. Xu, “MC Flow: Monte Carlo Flow Models for Data Imputation,” IEEE Conference on Computer Vision and Pattern Recognition, June 2020.

Conference Proceedings and Presentations

• B. Xu, Collaboration with URMC, Presented to the Board of RDSC, March 2019.
• L. Lin, B. Xu, W. Wu, T. Richardson, E. Bernal. Deep Metric Learning with Triplet Networks: Application to Myotonic Dystrophy Diagnosis. CEIS, April 2019.
• W. Wu, R. Hill, E. Brown, B. Xu, E. Bernal, E. Patak. Image-Based Biomarkers for Cancer Recurrence Prediction using SHG imaging, CEIS April 2019. (Best Poster Award)
• B.Xu, W. Wen, S. Wshah, R. Elmoudi, L. Lin.  Advanced Modeling of Power System Dynamics Using Machine Learning.  NYISO, Albany, August 2019.
• B. Xu, W. Wen, S. Wshah, R. Elmoudi. Advanced Modeling of Power System Dynamics Using Machine Learning.  NYSERDA, Albany, Nov 2018.