Real-Time Advanced Eye Movements Analysis Pipeline (RAEMAP) is an advanced pipeline to analyze traditional positional gaze measurements as well as advanced eye gaze measurements. The implementation of RAEMAP includes real-time analysis of fixations, saccades, gaze transition entropy, ambient/focal viewing coefficient, and real-time measure of cognitive load. RAEMAP provides visualizations of generated advanced gaze measures in real-time.

Explored the relationship between joint visual attention and joint mental effort in collaborative learning environments by conducting a data analysis of eye tracking datasets from three studies in collaboration with Dr. Bertrand Schneider from Harvard University, Cambridge, MA. Analyzed joint visual attention and joint mental effort, and how they support collaboration in terms of collaboration quality and learning gains from previous experiments.

Re-designed and implemented the Low/High Index of Pupillary Activity (LHIPA), an eye-tracked measure of pupil diameter oscillation to function in real-time, in collaboration with Dr. Andrew Duchowski from Clemson University. The novel Real-time IPA (RIPA) is shown to discriminate cognitive load in re-streamed eye-tracking data from previous experiments.

Designed and developed a software to extract header information such as title, abstract, keywords, authors, affiliations, and full text from scholarly PDF documents in real-time and process extracted data. Goal was to populate LANL’s Review & Approval System, RASSTI’s forms with extracted data.

Designed a study to detect dynamic areas of interest using object detectors and filter eye movement data that falls within the polygonal boundaries of detected dynamic AOIs.

Conducted a pilot study to assess audiovisual Speech-In-Noise (SIN) performance of adolescents with ADHD compared to age-matched controls using eye-tracking measures. Found that some signal-to-noise ratios shifts noise to a point where processing of speech becomes less automatic and relies more on increased cognitive load.

Developed a feasibility study to confirm eye movement data as a predictor of a diagnosis of ADHD in adults. Tree-based classifiers performed with 91% accuracy.

Designed a study to determine the next set of crawl URLs using URL update frequencies from crawl history.

Developed a browser extension, utilizing article segmentation and extractive summarization to generate Wikipedia-style TOC for blog posts to serve both as an article summary, and as a shortcut to navigate to sections of interest.

Constructed a blockchain-based system for DMV where, drivers, vehicle owners, police departments, and car dealers can all benefit from the DMV’s online services, without a customer service representative.

Created ML models to predict which team would win at each possible game in the next season, as a probability. We trained and evaluated each model using the four feature-sets, and evaluated their performances in terms of classification accuracy, and log loss.

Designed and developed a SSE to explore SL across multiple websites by crawling a set of seed URLs. This SSE provides a collection of results about certain attractions in SL, by ranking the results, and avoiding promotional content such as tours & hotels.

A full-stack, event-driven, microservices framework for Java, with business modeling. It abstracts away the complexities of microservices architecture by providing interfaces to write business logic. The framework internally handles microservice lifecycle, data partitioning, and auto-scaling. It also facilitates generating boilerplate code from Business Process Models.

A competition hosted by DrivenData, to model the spread of Dengue using weather and geographical information. Built a machine learning model that ranked #1 in 2017.

Developed a program to automatically generate and update API documentation using the code base.

Designed and developed an Information System for a company. Mainly focused on Inventory Management, Employee Management and day to day transactions.

Designed and developed a mobile application to report accidents to the insurance company by the owner of the vehicle himself. The app supports sending pictures of the damage along with the insurance policy details.

Developed a web application to manage parallel activities of a congress. Mainly focused on providing feedback to the speaker and asking questions from the speakers.

Developed a program to automatically generate the Rapidoid framework’s syntax adhered server- side code for Swagger codegen.

Designed a Web and Mobile application to manage Medical Records of patients which allows authorized Doctors to view and edit.

A web platform to manage information of a medium sized music school. It supports classroom management, progress tracking, attendance, and payroll.