Aditeya Pandey
PhD Student @ Northeastern University
Boston, MA, US
aditeyapandey@gmail.com
(857) 930--0481
CerebroVis is a novel network visualization tool which assists in diagnosis cerebrovascular abnormalities like stenosis and aneurysms. We found that CerebroVis improves the identification of cerebrovascular abnormalities in the brain over existing 3D MRA visualization.
In a crowdsourced experiment, we measured the effect of glyph design on an everyday task of categorization. We found that abstract glyphs are more accurate compared to anthropomorphic glyphs in a categorization experiment.
Multi-faceted data, such as a photo’s location, timestamp, and content, are difficult to navigate, particularly when a user has incomplete knowledge of the data, such as when the date of a photo is unknown. We present Picture Penguin, a novel personal photo navigation system that enables search and filtering through linked and combined views of temporal, geospatial, and photo content information. Picture Penguin scales to large photo collections andreduces complexity through clustering and data summarization techniques, and runs as both a mobile and a desktop application.
The Network Infrastructure of computer-based business is expanding every day. Consequently, monitoring and cyber-fencing of these massive networks is a growing concern within organizations. We developed a visualization tool which assists organizations to segment their network, write security policies and monitor network.
A data-fusion based visual analytics platform for navigating a data lake to derive insights. Our platform allows for rich interactive visualizations, querying and keyword-based search within and across datasets or models, as well as intuitive visual interfaces for value-imputation or model-based predictions.
A platform designed to explore multi-dimensional sensor data. Special focus on visualization of temporal sensor data using time-series visualization. Real-time time-series query visualization support, where the similar and frequent patterns can be queried using suitable machine learning algorithms.
Rules along with their exceptions have been used to explain large data sets in a comprehensible manner. In this work we present a novel hierarchical view of the rules and exceptions in a bubble layout.