Data Science

  • Expert in persistent homology, a method of feature extraction. 
    • Developing methods for converting multiparameter persistent homology output into feature vectors so it can be used for machine learning or otherwise analyzed statistically. 
    • Developing associated stability theorems to assure statistical analysis of persistent homology feature vectors is valid.
    • Major project: adjusting persistent homology analysis of point clouds to be stable to outliers. 
    • Major project: using persistent homology to aid in parameter selection for statistical inference. 
    • Related project: using persistent homology to aid in finding "optimal" number of clusters for high-dimensional data. 
    • Major project: "Saltation" in fruit flies uses persistent homology for feature extraction and PCA to analyze persistent homology output. 
  • Robotics work in GRASP Lab at Penn included using video, ultrasound, and binaural microphone data for vision and localization systems on humanoid robot. 
    • Implemented a variation of a low-pass filter on ultrasound data for object detection. 
    • Used video, and specifically images segmented by learned color rules, for object detection. 
    • Used binaural microphone data to find direction to robot producing audible communication signal; directional information used for localization system. 
    • regularly trained vision system to learn colors in different lighting environments. 
  • Mentored 1.5 year undergraduate project on approximating biological data (Surabhi Beriwal, "Saltation" in fruit flies project, Surabhi awarded Duke Mathematics Prize for Excellence in Research 2018).
  • Mentored 6 short-term undergraduate projects exploring data through mathematical methods (17 students).


  • Significant past experience with: Matlab, C++,  C, Lua
  • Contributions to large, existing code bases:
    • Maintained and contributed to cross-platform humanoid robotics code base while part of the GRASP Lab at Penn. Most involved in with computer vision, localization, and object detection systems. Code for robots written in Lua; debugging code written in Matlab. 
    • Developed algorithms for HD video encoder during R&D internship at Immedia Semiconductor. Also independently wrote stand-alone data visualizer to help with algorithm development and debugging. Written in C++. 
  • Recent independent development:
    • Developed data visualizer for "Saltation" in fruit flies project. Includes preliminary computations of persistent homology. Matlab. 
  • Mentoring longterm undergraduate project in approximating Bezier curves with piecewise linear curves for "Saltation" in fruit flies project. Strong focus on software best practices. Matlab. 

Team Leadership, Mentoring, and Interfacing with Non-Experts

  • Mentored a 1.5 year undergraduate project as part of "Saltation" in fruit flies. Includes mathematical work and coding. 
  • Led year-long reading course with lower-level graduate student mentee. 
  • Mentored 7 groups of undergraduates and high school students (19 students total) in short-term projects studying advanced topics in applied math. 
  • Awarded L.P. and Barbara Smith Award for Excellence in Teaching for 
    • "Consistent level of excellence" as primary instructor for Calculus 1 (Math 111L) at Duke over two semesters.
    • Significant organizing and outreach work for Southeastern Conference for Undergraduate Women in Math, 2015, 2016.
  • Significant experience presenting information to non-expert audiences:
    • Presented biological information to mathematical audience for math-bio colloquium series (3 presentations, 20 minutes each).
    • Presented on advanced mathematical topics to undergrads (3 presentations, 20 minutes each).
    • Short course on advanced mathematical topics to high school students (5 hours of lectures). 
    • Over 20 outreach presentations for GRASP Lab, a robotics lab at Penn. 
  • Team leader for undergraduates contributing to cross-platform humanoid robot code base.  Maintained code base, assigned projects, assisted in development where needed. 


  • Project "Saltation" in fruit flies explores causes of discrete phenotypic changes between parents and offspring in structure of drosophila melanogaster wing veins.
  • 2 years of funding from an NSF Research Training Grant (RTG) in mathematical biology.
  • 2 years of constant exposure to mathematical biology research as participant in weekly RTG math-bio colloquium and seminar series. Participants read seminar-speaker-provided background material and then presented and discussed that material at a colloquium. The seminar, followed by lunch with the speaker, was later in the week. 
  • Mentored 3 short-term undergraduate group projects in mathematical biology. Topics include
    • Exploring the space of all evolutionary trees. In particular, how can we find an "average" for trees?
    • How to construct evolutionary trees given gene sequences. 
    • Exploring persistent homology and its applications, including to analyzing fly wings and brain arteries.