Designed and implemented a real-time multi-language translation app that can detect objects and texts captured from webcam and translate them into more than 90 languages with Text-to-Speech feature by leveraging deep learning models.
|
AllergyGenDB: Comprehensive Genetic, Pathway and Network Database for Allergy
AllergyGenDB is another bioinformatics tool I developed at Cincinnati Childrens. It is a literature-based gene database for the major allergic diseases. By using text mining techniques, AllergyGenDB retrieves previous research findings from literature as well as curated databases, and extracts a list of genes that might be related to the given diseases.
Explore the website
|
MI-MAAP: Marker Informativeness for Multi-Ancestry Admixed Populations
At Cincinnati Childrens, I independently developed this Django based web application that ranks and identifies ancestry informative markers (AIMs) from large-scale public genome databases by using feature selection algorithms. AIMs are genetic variants that exhibits substantially different frequencies between different populations. They have a number of applications in genetic research. For exmaple, a set of AMIs can be used to estimate the geographical origins of the ancestors of an individual; they can also be used for detecting disease risk factors.
Explore the website
As part of my thesis, I am developing algorithms for finding communities in large-scale directed networks. This is a problem from the domain of big data analytics and I am developing the algorithms for the Hadoop environment in MapReduce programming paradigm.
ADHD Treatment Using Real-Time Brainwave Biofeedback
ADHD is the most common childhood disorder with nearly 11% of school age children having been diagnosed. Our project leverages the Muse Headband to detect levels of gamma brain-wave activity, and creates a graphical display that allows ADHD patients to learn how to control their thought patterns through biofeedback.
See the description
Professor Jeffrey Shaffer released data he has collected on trick-or-treat visits to his house between 6:00pm - 8:15pm since 2008. See what patterns can you find in this data!
This visualization is based upon FEMA (the Federal Emergency Management Agency) Disaster Declarations by various counties in the US from 1987 to 2017. By clicking the icons of different disasters, statistical summary of the given disaster will be displayed correspondingly.
This project is based on World Greenhouse Emissions data for the Year 200-2012.
