Summaries - Research
Back Big Data Meet ML and AI for Decision Superiority at the Tactical Edge – Algorithm Design, Demonstrate and Concept Model
|Division||Research & Sponsored Programs|
|Department||NPS Naval Research Program|
Boger, Dan C.
|Sponsor||NPS Naval Research Program (Navy)|
We will continue improving the tactical server demonstration by applying the state-of-the-art big data, deep analytics, machine learning (ML) and artificial intelligence (AI) methods and focus on the predictive capabilities that these methods might bring. The goal of this continuous effort is to demonstrate evolving and new concepts in a real-life event using live data in support of the the Common Tactical Picture (CTAP), Combat ID (CID), combat systems and kill chain applications. This project will continue demonstrating a logical, incremental introduction of the technologies towards improved engagement in doctrine, tracking and identification, meanwhile addressing more challenges and needs.
High level research questions for the big data, deep analytics, ML/AI that will address with the CTAP, combat systems and kill chain applications:
• What are the areas that predictive ML/AI methods are most suitable?
• How does big data meet ML/AI for example, how to better fuse and link heterogeneous data and tie all the data together to the objects in study (e.g., air tracks) and discover initial knowledge/rules that can jump start or further improve the precision of the ML/AL algorithms?
• What are the relationships of self-learning, meta-learning and reinforcement learning in complex decision making tasks and unknown environment?
Deliverables include a research report and presentation; demonstration of the live feed using the developed models at an exercise event and a publication to a journal or conference.
|Publications||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|