Illumination Works (ILW) is proud to announce the award of an Army Small Business Innovative Research (SBIR) Phase I contract to offer artificial intelligence (AI) automation to transform data labeling and curation for the Intelligence Community through machine learning (ML), computer vision, natural language processing (NLP), and human-machine-teaming.
AI-Driven Data Labeling & Curation
At present, Army intelligence analysts sift through volumes of data to locate relevant information and identify patterns. This community seeks an AI-based automated and reliable data labeling and curation system that allows users to quickly search, filter, and select datasets for further downstream analysis. Labeling data manually, whether individual records or whole datasets, requires extensive use of subject matter experts, which is cost prohibitive. Additionally, the challenge of trying to label at the pace of data collection requires large teams of analysts churning out annotations, which can cause burn out and high analyst turnover rates. Through this Phase I SBIR, ILW will prove the feasibility of our AI-driven solution for automated data labeling and curation, called Theia. ILW’s AI-driven approach is designed to speed downstream analytic tasks by saving countless hours in manual data tagging and filtering.
Solution Capabilities & Components
ILW’s automated data labeling and curation solution, Theia, is flexible and agnostic of data format (e.g., tabular, text, image, audio, video) and data source (e.g., structured data, text documents, full motion video, synthetic aperture radar, lidar, sensor information), and can meet the needs of the various types of intelligence community datasets. Theia uses AI to automatically tag datasets with informative metadata based on meaningful labels. These labels identify key elements/entities of interest and annotations to enable efficient dataset and entity filtering to help intelligence analysts select relevant data to speed downstream analytics.
“The cutting edge of data labeling and curation is automation through AI. We also understand that to solve these data-by-firehose problems, queries must return comprehensive knowledge, rather than just lists of results. ILW is at the forefront of automated knowledge generation through AI and the Army will be the first major benefactor of that innovation”
Learn more about our Data Science & Analytics services
Theia comprises three key components. The first is the AI Processing Engine, which applies AI/ML techniques from computer vision and NLP to identify and segment key entities, which are then curated into enhanced metadata packages that include higher-order categorical summaries, entity labels, and entity segment extraction parameters. The second component is the Knowledge Store, which houses entity labels and topics/classes identified and further enriches data with relevance scoring, providing improved curation and automated label validation. The third component is the User Interface, which provides human-machine teaming, giving users an interface to query and locate relevant data.
Solution Journey ― From TRL Level 3 to Commercialization
In Phase I, ILW will bring Theia to a Technical Readiness Level (TRL) 3 by validating the feasibility of the Theia AI Processing Engine to automatically label documents and images with meaningful metadata/classes. For this effort, ILW will also demonstrate the storage and retrieval of this information in the Knowledge Store and prototype the User Interface via wireframes showing how users will query and locate datasets relevant for downstream analytics.
Theia outcomes and insights expected to be proven in the feasibility study include:
- Automatically label data with knowledge
- Speed time to identify data of relevance
- Improve downstream AI/ML with curated, pre-labeled data
- Filter out data noise so analysts can focus on informative data to answer the question at hand
In follow-on efforts, ILW plans to mature Theia to accommodate automatic labeling and curation of the full swath of Army intelligence community data sources and productionalize the capability for Army use. The commercialization potential of Theia is excellent as many industries including security, medical, and aerospace require labeled data to speed downstream AI/analytic tasks and Theia’s AI-driven automation can save countless hours in manual data tagging and filtering for any of these industries.
For more information, contact Jan Turkelson, Vice President, Government Division.
About Illumination Works
Illumination Works is a trusted technology partner in user-centric digital transformation, delivering impactful business results to clients through a wide range of services including big data information frameworks, data science, data visualization, and application/cloud development, all while focusing the approach on the end-user perspective.
Established in 2006, ILW has primary offices in Dayton and Cincinnati, Ohio, as well as physical operations in Utah and the National Capital Region. In 2020, Illumination Works adopted a hybrid work model and currently has employees in 14 states and is actively recruiting.
