{"672115":{"#nid":"672115","#data":{"type":"news","title":"GTRI Develops Machine Learning Operations Platform to Streamline Data Management for the DoD ","body":[{"value":"\u003Cp\u003EMachine learning (ML) has transformed the digital landscape with its unprecedented ability to automate complex tasks and improve decision-making processes. However, many organizations, including the U.S. Department of Defense (DoD), still rely on time-consuming methods for developing and testing machine learning models, which can create strategic vulnerabilities in today\u2019s fast-changing environment.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe Georgia Tech Research Institute (GTRI) is addressing this challenge by developing a Machine Learning Operations (MLOps) platform that standardizes the development and testing of artificial intelligence (AI) and ML models to enhance the speed and efficiency with which these models are utilized during real-time decision-making situations.\u0026nbsp;\u003Cspan\u003E \u0026nbsp;\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cIt\u2019s been difficult for organizations to transition these models from a research environment and turn them into fully-functional products that can be used in real-time,\u201d said Austin Ruth, a GTRI research engineer who is leading this project. \u201cOur goal is to bring AI\/ML to the tactical edge where it could be used during active threat situations to heighten the survivability of our warfighters.\u201d\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ERather than treating ML development in isolation, GTRI\u2019s MLOps platform would bridge the gap between data scientists and field operations so that organizations can oversee the entire lifecycle of ML projects from development to deployment at the tactical edge.\u003Cspan\u003E\u0026nbsp;\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe tactical edge refers to the immediate operational space where decisions are made and actions take place. Bringing AI and ML capabilities closer to the point of action would enhance the speed, efficiency and effectiveness of decision-making processes and contribute to more agile and adaptive responses to threats.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cWe want to develop a system where fighter jets or warships don\u2019t have to do any data transfers but could train and label the data right where they are and have the AI\/ML models improve in real-time as they\u2019re actively going up against threats,\u201d said Ruth.\u003Cspan\u003E\u0026nbsp; \u0026nbsp;\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFor example, a model could monitor a plane\u2019s altitude and speed, immediately spot potential wing drag issues and alert the pilot about it. In an electronic warfare (EW) situation when facing enemy aircraft or missiles, the models could process vast amounts of incoming data to more quickly identify threats and recommend effective countermeasures in real time.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAI\/ML models need to be trained and tested to ensure their effectiveness in adapting to new, unseen data. However, without having a standardized process in place, training and testing is done in a fragmented manner, which poses several risks, such as overfitting, where the model performs well on the training data but fails to generalize unseen data and makes inaccurate predictions or decisions in real-world situations, security vulnerabilities where bad actors exploit weaknesses in the models, and a general lack of robustness and inefficient resource utilization.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cThroughout this project, we noticed that training and testing are often done in a piecemeal fashion and thus aren\u2019t repeatable,\u201d said Jovan Munroe, a GTRI senior research engineer who is also leading this project. \u201cOur MLOps platform makes the training and testing process more consistent and well-defined so that these models are better equipped to identify and address unknown variables in the battle space.\u201d\u003Cspan\u003E\u0026nbsp;\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis project has been supported by GTRI\u2019s Independent Research and Development (IRAD) Program, winning an IRAD of the Year award in fiscal year 2023. In fiscal year 2024, the project received funding from a U.S. government sponsor.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003EWriter: Anna Akins\u0026nbsp;\u003C\/span\u003E\u003Cbr \/\u003E\r\n\u003Cspan\u003EPhotos: Sean McNeil\u0026nbsp;\u003C\/span\u003E\u003Cbr \/\u003E\r\n\u003Cspan\u003EGTRI Communications\u003C\/span\u003E\u003Cbr \/\u003E\r\n\u003Cspan\u003EGeorgia Tech Research Institute\u003C\/span\u003E\u003Cbr \/\u003E\r\n\u003Cspan\u003EAtlanta, Georgia\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003EThe \u003C\/span\u003E\u003Ca href=\u0022https:\/\/gtri.gatech.edu\/\u0022 rel=\u0022noopener noreferrer\u0022 target=\u0022_blank\u0022\u003E\u003Cstrong\u003EGeorgia Tech Research Institute (GTRI)\u003C\/strong\u003E\u003C\/a\u003E\u003Cspan\u003E is the nonprofit, applied research division of the Georgia Institute of Technology (Georgia Tech).\u202fFounded in 1934 as the Engineering Experiment Station, GTRI has grown to more than 2,900 employees, supporting eight laboratories in over 20 locations around the country and performing more than $940\u003C\/span\u003E\u003Cstrong\u003E \u003C\/strong\u003E\u003Cspan\u003Emillion of problem-solving research annually for government and industry.\u202fGTRI\u0027s renowned researchers combine science, engineering, economics, policy, and technical expertise to solve complex problems for the U.S. federal government, state, and industry.\u003C\/span\u003E\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThe Georgia Tech Research Institute (GTRI) is developing a Machine Learning Operations (MLOps) platform that standardizes the development and testing of artificial intelligence (AI) and ML models to enhance the speed and efficiency with which these models are utilized during real-time active threat situations to heighten the survivability of our warfighters.\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"GTRI has developed a dashboard that aids in the DoD\u0027s development and testing of Artificial Intelligence and Machine Learning models that would be utilized during real-time decision-making situations."}],"uid":"35832","created_gmt":"2024-01-16 15:13:30","changed_gmt":"2024-02-09 16:37:44","author":"Michelle Gowdy","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2024-01-16T00:00:00-05:00","iso_date":"2024-01-16T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"672753":{"id":"672753","type":"image","title":"GTRI Machine Learning Project Leads","body":"\u003Cp\u003E\u003Cem\u003EGTRI has developed a dashboard that aids in the DoD\u0027s development and testing of AI and ML models that would be utilized during real-time decision-making situations. Pictured from L to R are the two project leads, GTRI Research Engineer Austin Ruth and GTRI Senior Research Engineer Jovan Munroe (Photo Credit: Sean McNeil, GTRI).\u003C\/em\u003E\u003C\/p\u003E\r\n","created":"1705417197","gmt_created":"2024-01-16 14:59:57","changed":"1705417566","gmt_changed":"2024-01-16 15:06:06","alt":"GTRI Machine Learning Project Leads","file":{"fid":"256049","name":"2023_1108_image_ELSYS_MLOps_Austin Ruth and Jovan Munroe_HQ_12.JPG","image_path":"\/sites\/default\/files\/2024\/01\/16\/2023_1108_image_ELSYS_MLOps_Austin%20Ruth%20and%20Jovan%20Munroe_HQ_12.JPG","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/01\/16\/2023_1108_image_ELSYS_MLOps_Austin%20Ruth%20and%20Jovan%20Munroe_HQ_12.JPG","mime":"image\/jpeg","size":1853239,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/01\/16\/2023_1108_image_ELSYS_MLOps_Austin%20Ruth%20and%20Jovan%20Munroe_HQ_12.JPG?itok=gUp3mXtD"}},"672752":{"id":"672752","type":"image","title":"GTRI MLOps team ","body":"\u003Cp\u003E\u003Cem\u003EThe MLOps team poses with GTRI Chief Technology Officer Mark Whorton (far left) and GTRI Director Jim Hudgens (second from left) after winning an IRAD of the Year award for their work on this project at GTRI\u0027s FY23 IRAD Extravaganza event (Photo Credit: Sean McNeil, GTRI).\u003C\/em\u003E\u003C\/p\u003E\r\n","created":"1705417067","gmt_created":"2024-01-16 14:57:47","changed":"1705417169","gmt_changed":"2024-01-16 14:59:29","alt":"GTRI MLOps team ","file":{"fid":"256048","name":"2023_0616_image_DO_IRAD 2023 Extravaganza_HQ_46.JPG","image_path":"\/sites\/default\/files\/2024\/01\/16\/2023_0616_image_DO_IRAD%202023%20Extravaganza_HQ_46.JPG","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/01\/16\/2023_0616_image_DO_IRAD%202023%20Extravaganza_HQ_46.JPG","mime":"image\/jpeg","size":2226382,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/01\/16\/2023_0616_image_DO_IRAD%202023%20Extravaganza_HQ_46.JPG?itok=G8qvL3-f"}}},"media_ids":["672753","672752"],"groups":[{"id":"1276","name":"Georgia Tech Research Institute (GTRI)"},{"id":"1188","name":"Research Horizons"}],"categories":[{"id":"129","name":"Institute and Campus"},{"id":"147","name":"Military Technology"},{"id":"135","name":"Research"}],"keywords":[{"id":"416","name":"GTRI"},{"id":"365","name":"Research"},{"id":"187915","name":"go-researchnews"},{"id":"166902","name":"science and technology"},{"id":"341","name":"innovation"},{"id":"9167","name":"machine learning"},{"id":"5901","name":"dod"},{"id":"8246","name":"Department of Defense"},{"id":"193417","name":"MLOps"},{"id":"193418","name":"protecting the warfighter"},{"id":"7141","name":"IRAD"},{"id":"192863","name":"go-ai"}],"core_research_areas":[{"id":"39481","name":"National Security"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E(Interim) Director of Communications\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003EMichelle Gowdy\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003EMichelle.Gowdy@gtri.gatech.edu\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E404-407-8060\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["michelle.gowdy@gtri.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}