Insight Data Science Fellow2019 - 2020Insight Data Science Program
Technologies: Python, Scikit-learn, NLTK, SQL, OpenCV, Pandas, Matplotlib, Jupyter Notebook, Git, Flask, AWS, Bash
- Developed a machine learning algorithm that automatically identifies the best photo in a burst.
- Implemented and trained a pair-wise SVM ranker that uses general image quality features (blurriness, contrast, and more) and content-quality features (OpenCV for face detection, eyes open, and so on).
- Achieved 74% accuracy, measured using normalized discounted cumulative gain (NDCG).
- Deployed an interactive web app on AWS using Python, Flask, HTML, and CSS.
- Developed a multi-label text-classification algorithm to automatically tag research papers.
- Implemented a feature-extraction algorithm for NLP that uses TF-IDF of word n-grams, the appearance of words in a title, and more.
- Compared several problem transformation methods used in multi-label classification, including binary relevance, classifier chains, and label powerset.
Senior Postdoctoral Fellow2014 - 2018University of Washington
Technologies: Python, MATLAB, C, Scikit-learn, Pandas, Matplotlib, Jupyter Notebook, Git, SQL, Bash, OpenGL
- Explored the possibility of using neural activity from a single brain hemisphere to control both sides of the body in a brain-computer interface paradigm.
- Analyzed terabytes of neural activity data to provide insight into the brain’s function.
- Applied advanced statistical modeling, including transfer entropy and Gaussian process factor analysis (GPFA) to assess brain connectivity.
- Published two peer-reviewed publications, four oral presentations, and two conference papers.
- Independently led a research project to allow retraining of proprioceptive sensory pathways in stroke and spinal cord injury patients.
- Built haptic devices to explore alternative methods of communicating arm position in space.
- Wrote a grant proposal incorporating my findings from this study which was awarded $90,000 by the Bayley Family Foundation.
Research Associate2007 - 2013University of Belgrade School of Electrical Engineering
Technologies: MATLAB, Simulink, C
- Analyzed the walking deficits in patients with stroke and Parkinson’s disease.
- Developed a method for quantifying pathological walking patterns in stroke patients.
- Demonstrated that principal component analysis (PCA) provides better insight into the specific differences between acute and chronic patients compared to clinically-used assessment metrics.
- Detected walking disturbances in Parkinson’s disease patients by combining a neural network and rule-based classification, achieving 84% accuracy.