Course : CSCI 4965/6965 - AI for ConservationInstructor: Professor Charles V StewartCourse: CSCI 1100 - Computer Science IInstructor: Professor Uzma Mushtaque

Course : CSCI 1100 - Computer Science IInstructor : Professor Uzma Mushtaque

Project : Imageomics (NSF OAC-2118240) | In Collaboration with Ohio State University | NSF FundedAdvisor : Professor Charles V StewartStatement of Work :We propose to accelerate the study of genetic relatedness and appearance pattern variations. We will focus on Grevy’s zebras but build tools that can be used for a variety of species. This involves several interrelated steps. First, we will train algorithms that identify the same individual across a long sequence of images, starting from the time it is a foal and continuing all the way through adulthood. This will be achieved with a hybrid of a deep learning algorithm training using an ArcFace loss and the classical SIFT based Hotspotter algorithm (and its verification algorithm cousin, VAMP). The second step will involve quantifying appearance variation between images of different animals. We will start with unsupervised methods derived from the Step 1 identification algorithms, looking at distance variations in embedding space and match score values. We will then proceed to refine these methods using supervision derived from genetic relatedness. The latter will be a refinement of the former. The final step will involve collaborating with the population biologists to analyze the relationship between appearance variation and genetic relatedness. Outcomes will include open-source code – integrated with the Wild Me repository where possible — and papers describing both the technical content and scientific results.

Course : CSCI 1100 - Computer Science IInstructors : Professor Uzma Mushtaque, Professor John Sturman

Project : Imageomics (NSF OAC-2118240)Advisor : Professor Charles V Stewart

Responsibilities- Test Automation using Cypress, Playwright- Managing Automation projects- Managing Jenkins environment

Responsibilities - Test Automation using Cypress- Security Testing using BurpSuite- Regression Testing for new product-versions- Validating production deployment changes- Providing Bug-reports

As an extension of my undergraduate thesis, my work in this lab is based on Sign Language Recognition (SLR). I have been working on Bangla Sign Language (BdSL) Recognition using depth information. Since my affiliation with this lab, I have published one paper on Bangla Sign Digits in an International Conference as the first-author and has one journal article under review. Recently, I, along with my thesis supervisor and co-supervisor have received a research grant for an ongoing project on generating a depth-dataset for Bangla Sign Alphabet.

Responsibilities - Testcase Writing and Basic Manual Testing- Test Automation using Selenium Protractor- Manual Testing on Product Functionalities- Writing optimized testcases- API Testing (using Apache Jmeter)- Security Testing (using Fiddler)