Sort
48,453 grants matching “machine learning”
Machine Learning Team
$650,003Francisco Pereira · National Institute Of Mental Health · ZIC · FY2018 · MH
Integrating Data Science and Hands-on Experience into the Community College Biotechnology Classroom with Applications to Antibody Engineering
$650,000Dylan A Bulseco · Institute For Future Intelligence, Inc. · · FY2023 · EDU
NSF Convergence Accelerator Track L: Engineered microbial sensors for assessing water quality
$650,000Virginia W Cornish · Columbia University · · FY2024 · TIP
NSF Convergence Accelerator Track L: Accelerating VOC Sensor Advances and Translation by Machine Learning and Bioinspiration
$650,000Qingshan Wei · North Carolina State University · · FY2024 · TIP
NSF Convergence Accelerator Track K: Remote Sensing Tools for Catalyzing Equitable Water Outcomes
$650,000Emily M Elliott · University Of Pittsburgh · · FY2024 · TIP
ASCENT: Collaborative Research: Scaling Distributed AI Systems based on Universal Optical I/O
$650,000Vladimir M Stojanovic · University Of California-Berkeley · · FY2020 · ENG
CAREER: Composable Optimization for Robot Simulation and Control
$650,000Zachary Manchester · Carnegie Mellon University · · FY2025 · ENG
CI-ADDO-EN: Flexible Machine Learning for Natural Language in the MALLET Toolkit
$650,000Andrew K McCallum · University Of Massachusetts Amherst · · FY2010 · CSE
Collaborative Research: URoL:ASC: Using the Rules of Antibiotic Resistance Development to Inform Wastewater Mitigation Strategies
$650,000Liqing Zhang · Virginia Polytechnic Institute And State University · · FY2023 · BIO
**AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** THE RESEARCH OBJECTIVE IS DESIGN, DEVELOPMENT, AND FIELD-TESTING OF AN ARTIFICIALLY INTELLIGENT METHOD TO PREDICT THE YIELD AND OIL CONTENT OF FLAX FROM A NUMBER OF MORPHOLOGICAL TRAITS BEFORE HARVESTING. SUCCESS IN THIS PROJECT WILL RESULT IN A QUANTUM LEAP FOR FLAX BREEDING PROGRAMS BY BRINGING IN A SYSTEMATIC DATA-DRIVEN AUTONOMOUS APPROACH, IN LIEU OF CONVENTIONAL HEURISTIC-BASED DECISION MAKING. NDSU HOSTS THE ONLY FLAX BREEDING PROGRAM IN THE US AND NORTH DAKOTA IS THE LARGEST PRODUCER OF FLAX (91% OF US PRODUCTION), WHICH WILL BE USED AS THE TESTBED IN THIS PROJECT. THE PROJECT REQUIRES PRECISION DATA COLLECTION ON MORPHOLOGICAL TRAITS THROUGHOUT THE ENTIRE LIFE CYCLE OF THE CROP. A COOPERATIVE TEAM OF UNMANNED AERIAL SYSTEMS (UASS) AND UNMANNED GROUND VEHICLES (UGVS) WILL BE EMPLOYED. THE UGVS WILL ALSO BE LOADED WITH A HYPERSPECTRAL CAMERA TO PREDICT THE OIL CONTENT EVEN BEFORE HARVESTING. THE SCHEDULING AND OPERATION OF THE UAS-UGV TEAM WILL BE DICTATED BY A DATA ANALYTICS ENGINE. THE VIDEOS COLLECTED BY THE UAS/UGV WILL BE PROCESSED TO EXTRACT VARIOUS MORPHOLOGICAL TRAITS AND TO PREDICT THE FINAL YIELD OF THE CROP THROUGH AN INTEGRATED MACHINE LEARNING MODEL. HYPERSPECTRAL IMAGES WILL BE ANALYZED USING MACHINE LEARNING TO PREDICT THE OIL CONTENT OF EACH PLOT. IF SUCCESSFUL, THIS PREDICTIVE MODEL FOR YIELD AND OIL CONTENT WILL ALLOW A BREEDER TO SUBSTANTIALLY LOWER THE COSTS OF THE BREEDING PROGRAM, AND HEREBY IMPROVE THE QUALITY OF THE NEW CROP VARIETY. IN COLLABORATION WITH AMERIFLAX, THIS FRAMEWORK WILL BE TESTED IN REAL-WORLD SETTINGS.
$650,000University Of California, Los Angeles · · FY2022 · National Institute of Food and Agriculture
TAIL BITING CAUSES SIGNIFICANT WELFARE ISSUES FOR PIGS AND ECONOMIC LOSSES FOR PORK PRODUCERS. THIS PROJECT WILL UTILIZE AN ADVANCED COMPUTER VISION PLATFORM (NUTRACK SYSTEM) TO UNDERSTAND THE COMPLEX ETIOLOGY OF TAIL BITING AND PROVIDE EARLY RECOGNITION OF TAIL BITING OUTBREAKS IN PIGS. EARLY RECOGNITION OF TAIL BITING WILL ALLOW EARLY INTERVENTIONS THAT PREVENT OR REDUCE TAIL BITING AND IMPROVE HEALTH AND WELLBEING OF PIGS. OUR PROPOSED OBJECTIVES ARE: 1) UTILIZE AN ADVANCED COMPUTER VISION PLATFORM TO IDENTIFY CHANGES IN POSTURES AND ACTIVITIES ASSOCIATED WITH TAIL BITING OUTBREAKS (TBO) TO PREDICT AND PREVENT TBO THROUGH EARLY INTERVENTION; 2) CHARACTERIZE BEHAVIORAL PATTERNS OF TAIL BITERS AND VICTIMIZED PIGS FOR EARLY IDENTIFICATION OF THESE PIGS; 3) EVALUATE SOCIAL POSITIONS OF PIGS INVOLVED WITH TAIL BITING AND THEIR ROLES IN THE DEVELOPMENT OF TBO; 4) ASSESS STRESS AND IMMUNE STATUS OF INDIVIDUAL PIGS THAT MAY PREDISPOSE THEM TO TAIL BITING EVENTS; AND 5) VISUALLY IDENTIFY TAIL BITING EVENTS FROM PROCESSED VIDEO TO DEVELOP AI AND MACHINE LEARNING PROGRAMS THAT WILL BE CAPABLE OF AUTONOMOUSLY IDENTIFYING TAIL BITING EVENTS AND ASSOCIATED PIGS. THREE EXPERIMENTS WILL BE COMPLETED: EXP. 1 AND 2 AT THE UNIVERSITY OF MINNESOTA TO ADDRESS OBJ. 1-5, AND EXP. 3 AT THE UNIVERSITY OF NEBRASKA-LINCOLN TO ADDRESS OBJ. 1 AND 5. THE PROJECT CONTRIBUTES TO SUSTAINABLE AGRICULTURE AND FOOD SYSTEMS BY PREVENTING TAIL BITING IN A WAY THAT IS MORE ANIMAL WELFARE FRIENDLY THAN TAIL DOCKING.
$650,000Regents Of The University Of Minnesota · · FY2022 · National Institute of Food and Agriculture
Using Excitations to Understand and Predict Dynamic Properties of Amorphous Condensed Matter
$650,000Marcus T Cicerone · Georgia Tech Research Corporation · · FY2025 · MPS
CAREER: Many-Body Green's Function Framework for Materials Spectroscopy
$650,000Tianyu Zhu · Yale University · · FY2024 · MPS
** AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** ALABAMA IS A HIGH POVERTY STATE WITH SIGNIFICANT PORTIONS, THE BLACK BELT COUNTIES, AFFECTED BY THE LACK OF AVAILABLE, AFFORDABLE, AND NUTRITIOUS FOOD. THIS PROJECT ADDRESSES THE ISSUE OF FOOD AND NUTRITION SECURITY AMONG DISADVANTAGED AND MINORITY HOUSEHOLDS AND COMMUNITIES THAT ARE IMPACTED BY DISASTERS SUCH AS EXTREME WEATHER EVENTS (HURRICANES, TORNADOES, AND FLOODS) AND ALSO HIGHLIGHTED BY THE ONGOING PANDEMIC. THE LONG-TERM GOAL IS TO APPLY MACHINE LEARNING AND DIGITAL TECHNIQUES TO TRANSFORM ALABAMA EMERGENCY FOOD DISTRIBUTION CENTERS STRATEGICALLY, MANAGERIALLY, TECHNOLOGICALLY, AND SOCIALLY TO POSITION THEM AS SUSTAINABLE FOOD DISTRIBUTION AND COLLECTION SYSTEMS CAPABLE OF PROVIDING SUFFICIENT AND NUTRITIOUS FOODS TO PEOPLE IN NEED. OUR TEAM WILL ENGAGE IN RESEARCH, EXTENSION, AND EDUCATIONAL ACTIVITIES TO:1) DEVELOP DIGITAL AND MACHINE LEARNING TECHNOLOGIES TO UNDERSTAND FOOD DEMAND AT ALABAMA EMERGENCY FOOD DISTRIBUTION CENTERS TOWARD A CONSUMER-CENTRIC ENVIRONMENT, 2) DEVELOP DIGITAL TECHNOLOGIES TO DETECT FOOD SUPPLY AT ALABAMA EMERGENCY FOOD DISTRIBUTION CENTERS TOWARD A HIGHER OPERATIONAL EFFICIENCY ENVIRONMENT, 3) INCREASE THE ALABAMA EMERGENCY FOOD DISTRIBUTION SYSTEM'S CAPACITY FOR PROVIDING HEALTHY FOOD TO THE FOOD-INSECURE, 4) STRENGTHEN THE AI/MACHINE LEARNING EDUCATION AT TUSKEGEE UNIVERSITY BY INTEGRATING EDUCATION WITH RESEARCH AND EXTENSION. THE PROPOSED PROJECT WILL ENHANCE EFFECTIVE FOOD PANTRY-BASED EXTENSION PROGRAMS THAT STRESS AND REINFORCE HUMAN CAPACITY BUILDING. OUR PROJECT HAS AN ADVISORY BOARD REPRESENTING EMERGENCY FOOD DISTRIBUTORS, PROFESSIONALS, AND BLACK FARMERS AND HAS A PROJECT EVALUATOR. THE OUTCOME OF OUR EFFORTS WILL BE AN EFFICIENT AND CONSUMER-CENTRIC FOOD DISTRIBUTION SYSTEM THAT ENABLES THE FOOD-INSECURITY COMMUNITY LIKELIER TO ACCRUE NUTRITIOUS FOOD.
$650,000Tuskegee University · · FY2023 · National Institute of Food and Agriculture
Microdata for Analysis of Early Life Conditions, Health, and Population
$650,000Steven Ruggles · University Of Minnesota · R01 · FY2019 · AG
THE PERSISTENCE OF FOODBORNE PATHOGENS IN POSTHARVEST PROCESSING ENVIRONMENTS IS A MAJOR CONTRIBUTOR TO FOODBORNE OUTBREAKS. A RAPID AND RELIABLE VERIFICATION TOOL IS URGENTLY NEEDED TO ENSURE SURFACE SANITATION EFFECTIVENESS AND ADDRESS CROSS-CONTAMINATION RISKS IN FOOD PROCESSING PLANTS. THE CURRENT FOOD INDUSTRY HEAVILY RELIES ON ATP BIOLUMINESCENCE SWAB TESTS AS A RAPID VERIFICATION METHOD FOR ENVIRONMENTAL MONITORING. HOWEVER, THESE TESTS PRIMARILY ASSESS SURFACE CLEANLINESS RATHER THAN ACTUAL MICROBIAL INACTIVATION, OFTEN RESULTING IN LOW SENSITIVITY AND ACCURACY. TO ADDRESS THESE CHALLENGES, THIS RESEARCH AIMS TO DEVELOP A REAL-TIME, ON-SITE PLATFORM FOR VERIFYING THE EFFICACY OF SURFACE SANITATION PROCESSES IN FOOD PROCESSING ENVIRONMENTS. THE SPECIFIC RESEARCH OBJECTIVES ARE: 1) TO DEVELOP A BIOMIMETIC SURROGATE INTERFACE (BSI) COMBINED WITH VIBRATIONAL SPECTROSCOPY AND MACHINE LEARNING TO PREDICT SANITATION EFFECTIVENESS ON ZONE 1 AND ZONE 2 SURFACES ACROSS VARIOUS WEAR LEVELS; 2) TO ENHANCE THE PREDICTIVE ACCURACY OF SANITATION EFFICACY AGAINST BIOFILMS BY INCORPORATING THE BSI WITH FOOD-GRADE ARTIFICIAL BIOFILM MATRICES; AND 3) TO DEMONSTRATE THE PERFORMANCE OF THE BSI-BASED APPROACH UNDER PILOT-SCALE AND IN SITU PROCESS CONDITIONS AND BENCHMARK ITS INTEGRATION WITH CONVENTIONAL METHODS. THE SUCCESS OF THIS RESEARCH WILL ENHANCE THE VERIFICATION OF SURFACE SANITATION EFFICACY, REDUCE MICROBIAL CROSS-CONTAMINATION RISK, AND SUPPORT REDUCED USE OF WATER AND SANITIZERS, PROMOTING ENVIRONMENTAL SUSTAINABILITY AND BENEFITING ECOSYSTEMS. THE LONG-TERM IMPACT OF THIS RESEARCH IS IN SUPPORT OF PROGRAM AREA GOALS BY DEVELOPING AND VALIDATING ADVANCED AND INNOVATIVE TECHNOLOGIES OR PROCESSES FOR CLEANING AND SANITATION TO EFFECTIVELY REDUCE THE PRESENCE OF ENTERIC PATHOGENS IN FOOD PROCESSING FACILITIES.
$650,000Washington State University · · FY2025 · National Institute of Food and Agriculture
** AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** THIS RESEARCH PROJECT AIMS TO STUDY HOW AND HOW WELL LOCAL SMALL FARMERS IN NORTH/CENTRAL FLORIDA USE SOCIAL MEDIA FOR THEIR AGRICULTURAL BUSINESSES, AND FIND OUT HOW TO OPTIMIZE THEIR SPECIFIC OPERATIONAL STRATEGIES USING ADVANCED SOCIAL MEDIA MARKETING TECHNIQUES. THE STRATEGIC USE OF SOCIAL MEDIA BY SMALL FARMERS CAN SIGNIFICANTLY BOOST REGIONAL ECONOMIES AS THEY REPRESENT THE MAJORITY OF THE LOCAL FARM AND RURAL COMMUNITY. IT FOSTERS SUSTAINABLE AGRICULTURE, ECONOMIC GROWTH, AND VITALITY IN RURAL AREAS IN NORTH/CENTRAL FLORIDA.THIS PROJECT WILL CONDUCT COMPREHENSIVE INTERVIEWS AND COLLECT SPECIALLY DESIGNED SURVEYS TO UNDERSTAND SOCIAL MEDIA ADOPTIONS AMONG LOCAL SMALL FARMERS. IT WILL ALSO LEVERAGE AI, MACHINE LEARNING, AND OPERATIONS RESEARCH METHODS TO CREATE TOOLS AND APPROACHES FOR SMALL FARMERS TO FULLY TAKE ADVANTAGE OF SOCIAL MEDIA TO IMPROVE THEIR BUSINESSES.THE GOAL OF THIS RESEARCH PROJECTIS TO ASSIST SMALL-SCALE AGRICULTURAL ENTERPRISES IN NORTHEAST AND CENTRAL FLORIDA IN OPTIMIZING THEIR OPERATIONAL STRATEGIES THROUGH THE UTILIZATION OF ADVANCED SOCIAL MEDIA MARKETING TECHNIQUES AND SUBSEQUENTLY ENHANCE THEIR INCOMES. IF SUCCESSFUL, THIS PROJECT IS EXPECTED TO HELP INCREASE THE ECONOMIC ACTIVITIES IN THE REGION, DRIVE SALES IN LOCAL RURAL AGRICULTURE BUSINESSES AND BENEFIT THE LOCAL COMMUNITY BY INCREASING FARM INCOME AND CIRCULATING MONEY LOCALLY. THE DIRECT RESULTS AND SOCIAL BENEFITS WILL BE THREE FOLDED. FIRST, THE PROJECT WILL HELP INCREASE THE ADOPTION OF SOCIAL MEDIA AMONG SMALL TO MEDIUM FARMERS TO HELP THEM REACH OUT TO CUSTOMERS; SECOND, IT WILL HELP SMALL TO MEDIUM FARMERS INCREASE ENGAGEMENT OF LOCAL CONSUMERS OF AGRICULTURAL PRODUCES AND SERVICES; THIRD, EVENTUALLY IT CAN HELP ENHANCE THE CONNECTION BETWEEN SMALL TO MEDIUM FARMERS AND LOCAL CONSUMERS AMONG THE LOCAL COMMUNITIES IN THE NORTHEASTERN AND CENTRAL FLORIDA REGION.
$650,000The University Of Central Florida Board Of Trustees · · FY2024 · National Institute of Food and Agriculture
Student Work Experiences in Remote and Virtualized Environments
$650,000Michelle Leidel · South Florida State College · · FY2023 · EDU
CAREER: Statistics through the Sum of Squares Lens
$650,000Samuel Hopkins · Massachusetts Institute Of Technology · · FY2023 · CSE
CAREER: Complexity of Matrix Operations
$650,000Joshua Alman · Columbia University · · FY2023 · CSE
Collaborative Research: FW-HTF-RL: Understanding the Ethics, Development, Design, and Integration of Interactive Artificial Intelligence Teammates in Future Mental Health Work
$650,000Saeed Abdullah · Pennsylvania State Univ University Park · · FY2023 · TIP
** AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** THIS PROJECT GENERATES NEW KNOWLEDGE REGARDING FARMERS' MARKETSTRUCTURE AND PERFORMANCE, CONSUMER CHOICES, AND FOOD POLICY THROUGH BIG MOBILE LOCATION DATA AND ADVANCED MACHINE LEARNING (ML) METHODS. DIRECT MARKETING BENEFITS PRODUCERS, CONSUMERS, AND THE LOCAL COMMUNITY AND IS A KEY COMPONENT OF FOOD-BASED POLICIES. PREVIOUS WORK ON FARMERS' MARKETS HASRELIED ON CASE STUDIES AND SURVEY DATA, WHICH WERE GENERALLY LOCALIZED WITH SMALL SAMPLE SIZES, QUESTIONING THEIR EXTERNAL VALIDITY AND MERIT FOR CAUSAL INFERENCE. WE PROPOSE TO ADDRESS THESE LIMITATIONS BY EXPLOITING A UNIQUE DATASET OF MOBILE LOCATION DATA FOR 125 MILLION CELLPHONE USERS THROUGHOUT THE UNITED STATES. THIS NOVEL DATASET ALLOWS US TO ANSWER CRITICAL QUESTIONS OF INTEREST TO PRODUCERS, POLICYMAKERS, AND MARKET MANAGERS. OUR RESEARCH PROVIDES FOUR PRIMARY CONTRIBUTIONS. FIRST, WE WILL GENERATE NEW INSIGHTS REGARDING CONSUMER DECISIONS SURROUNDING FARMERS' MARKETS. SECOND, WE CAN IDENTIFY THE SPILLOVER EFFECTSOF FARMERS' MARKETSON NEARBY BUSINESSES. THIRD, AS POLICYMAKERS USE FARMERS' MARKETSTO ADDRESS FOOD INSECURITY IN LOW-INCOME NEIGHBORHOODS, WE WILL MEASURE THE DEGREE TO WHICH TARGETED CUSTOMERS ATTEND THESE MARKETS. FOURTH, GIVEN INCREASING CONCERNS ABOUT THESATURATION OF FARMERS' MARKETS, WE WILL ASSESS THE COMPETITIVE LANDSCAPE AND HOW THAT IMPACTS ATTENDANCE AND COMPLEMENTARY BEHAVIOR. THE PANEL NATURE OF OUR DATA ALSO ALLOWS US TO IDENTIFY COVID-19 IMPACTS USING CAUSAL INFERENCE METHODS AND REVEALED CONSUMER CHOICE DATA FROM 2019-2022. THIS INNOVATIVE AND INTERDISCIPLINARY RESEARCH WILL PROVIDE ESSENTIAL KNOWLEDGE OF THE FUNCTIONING OF AGRICULTURAL MARKETS. IT WILL PAVE PATHWAYS FOR NOVEL RESEARCH INTO CONSUMER CHOICES THROUGH MULTIDISCIPLINARY COLLABORATION AND TRAINING, BIG ECONOMIC DATA, AND ADVANCED ML METHODS.
$650,000University Of Connecticut · · FY2023 · National Institute of Food and Agriculture
CAREER: Hydrazone-Based Switches - Simple Systems for Sophisticated Functions
$650,000Ivan Aprahamian · Dartmouth College · · FY2013 · MPS
CAREER: Development of Novel Domain-Tailored Machine Learning Tools for Organic Reaction Development and Discovery
$650,000Connor W Coley · Massachusetts Institute Of Technology · · FY2022 · MPS
** AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** NITRATE CONTAMINATION IN STREAMS, LAKES, AND ESTUARIES IS A CRITICAL PROBLEM IN MANY AGRICULTURAL WATERSHEDS. WATER QUALITY DATA AVAILABILITY IS CRITICAL IN MONITORING STREAM HEALTH AND MAKING MANAGEMENT DECISIONS. IN THE US, THE ENVIRONMENTAL PROTECTION AGENCY (EPA) AND US GEOLOGICAL SURVEY (USGS) ALONG WITH STATE AGENCIES MONITOR WATER QUALITY AND QUANTITY. WATER QUALITY MONITORING, ESPECIALLY NITRATE DATA IS TYPICALLY AT COARSE TEMPORAL RESOLUTION. WITH THE CONTINUED ADVANCEMENT OF IN-STREAM NITRATE SENSOR TECHNOLOGY, USGS AND SEVERAL STATE AGENCIES ARE COLLECTING HIGH-FREQUENCY (15- TO 60-MINUTE INTERVALS) NITRATE DATA USING OPTICAL SENSORS OVER THE LAST DECADE. OUR TEAM WILL DEVELOP AN INTEGRATED (FIELD DATA COLLECTION, BIOPHYSICAL, AND MACHINE LEARNING) MODELING FRAMEWORK FOR UNDERSTANDING THE NITRATE DYNAMICS OF A REGION AND GENERATE SPATIALLY AND TEMPORALLY CONTINUOUS DAILY NITRATE CONCENTRATION DATA, WHICH COULD BE USED FOR EVALUATING ECOSYSTEM HEALTH AND DESIGNING MORE EFFECTIVE AND TARGETED WATERSHED MANAGEMENT STRATEGIES.
$650,000The Pennsylvania State University · · FY2024 · National Institute of Food and Agriculture