STEM RESOURCES LLC — National Aeronautics and Space Administration STTR Phase I: T11

Description

Scientificnbsp;discoverynbsp;todaynbsp;dependsnbsp;asnbsp;nevernbsp;beforenbsp;uponnbsp;easenbsp;ofnbsp;accessnbsp;tonbsp;data,nbsp;associatednbsp;sophisticatednbsp;toolsnbsp;andnbsp;applications,nbsp;tonbsp;enablenbsp;research, education.nbsp;Researchersnbsp;whonbsp;oncenbsp;worked in local, isolated laboratories now collaborate routinely and on a globalnbsp;scale.nbsp;Specializednbsp;instrumentsnbsp;thatnbsp;werespreadnbsp;acrossnbsp;multiplenbsp;locationsnbsp;cannbsp;nownbsp;fitnbsp;intonbsp;anbsp;singlenbsp;lab connected via cyberinfrastructure resources and residing in big data.nbsp;However, the sheer volume and heterogeneity of data bring a multitude of problems.nbsp;nbsp;The primary intellectual merit of the proposed project comes from its vision of providing an augmented intelligence and cognitive support ecosystem (AICSE) assistants that enhances the capability of scholars and researcher in examining research topics, data and assists the user in understand its relevance to their goals.nbsp;The expected result of this feasibility study will be a new resilient architecture for an agent-drivennbsp;tool that is capable of ingesting any structured or unstructured data provided by the NASA and providing actionable insights. The project will produce anbsp;software design documentnbsp;or specification document that is composed of several layers that compass NASA-domain specific research areasnbsp;. In particular the design will include, (1) a cross-platform user interface or agents, (2) natural language understanding functionality that maps tokens or words, sentences, paragraphs or documents to their respective meaning. As well as, produce document-specific sentiment, tone and intent information based on document corpuses. (3) Several open-source NLP models that can produce document-level or corpus themes, identifies relationships among themes and aggregatenbsp; analysis.nbsp;nbsp;Also, the proof of concept, phase I effort will be limited to Google Scholar, because of its diverse research publication types, as well as the restricted timeframe of the project.nbsp;