Progress 08/15/24 to 08/14/25
Outputs Target Audience:The target audience includes undergraduates, data scientists, community partners and stakeholders. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?The project created effective Machine Learning technologies in evaluating the predictive strength of the antioxidants in determining healthy foods. Through hands-on proficiency with Jupyter Notebook, Python ML libraries, the DSU students were able to determine food and regionality by identifying food choices for health-conscious consumers while emphasizing regional dietary strengths and deficiencies. While at UD, the project has developed multiple training modules, workshops, and experiential learning modules for students. How have the results been disseminated to communities of interest?DSU students participated in the poster presentation during the 2025 Delaware State University research day activities. While at UD,the developed training modules, and demos are offered during undergraduate courses, including Food Sensory Evaluation and Food Science Capstone. What do you plan to do during the next reporting period to accomplish the goals?We plan to continue training the recruited students and develop summer training programs on data sciences, and to convert the research-day poster and other data products into a manuscript for submission to a food science journal.
Impacts What was accomplished under these goals?
The three DSU students gained experience drafting competition-ready technical narratives and presenting scholarly work to a multidisciplinary audience and stakeholders. At UD, the recruited student has taken threetraining modules using AI models to process food quality-related data, one online workshop on food quality & safety data processing, and two experiential learning modules on food processing.
Publications
|
Progress 08/15/23 to 08/14/24
Outputs Target Audience:Theprogram was designed to empower undergraduate students from diverse academic backgrounds, particularly in the Food and Ag Sciences, to explore the application of machine learning (ML) in healthy food research. The initiative aimed to bridge the gap between computational techniques and human-centered perspectives, enabling participants to address complex food-related challenges through a multidisciplinary lens. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?Participants left the program with: Technical Skills: Foundational proficiency in ML tools like Python, or scikit-learn, and experience in analyzing food-related datasets. Critical Thinking: The ability to evaluate and interpret ML results through a human-centered approach, considering ethical and social implications. Collaboration: Enhanced teamwork skills across disciplines, blending computational and non-technical expertise. Impactful Solutions: Creative recommendations for improving access to and understanding of healthy foods. How have the results been disseminated to communities of interest?Workshop on Machine Learning for Food Science Research: Faculty and participants co-hosted workshops to showcase the integration of ML into social sciences research. What do you plan to do during the next reporting period to accomplish the goals?Encourage the participation of other students and expose to students to ML.
Impacts What was accomplished under these goals?
Workshops and Training: Students attended workshops on topics such as: Basics of machine learning and Python programming. Understanding nutrition datasets. Ethical considerations in AI and food research. Collaborative Projects: One team comprised students from different disciplines to ensure diverse perspectives. Projects included: Predicting nutritional quality from ingredient lists using ML models. Exploring global food trends with clustering and visualization techniques. Mentorship and Guidance:The team was paired with a mentor from computational social science, providing interdisciplinary support throughout the program. Capstone Presentations:At the end of the internship, teams presented their findings to a panel of faculty, researchers, and industry experts.
Publications
|
Progress 08/15/22 to 08/14/23
Outputs Target Audience:The first year of the grant was used by the PIs for planning. In the second year, the target audience are students and especially under-represented minority students in Food and Agricultural Science majors from the three collaborating institutions. Recruiting and getting enough participants to participate is a challenge. One other the PI changed institutions.The first year of the grant was used by the PIs for planning. In the second year, the target audience are students and especially under-represented minority students in Food and Agricultural Science majors from the three collaborating institutions. Recruiting and getting enough participants to participate is a challenge. One of the PIs changed institutions. Changes/Problems:One of the PIs has changed institutions. It has been a challenge recruiting and getting enough participants to participate in the program. We plan to engage one graduate student to assist with tours and webinars about graduate school and research. What opportunities for training and professional development has the project provided?We have been providing informal presentations to faculty and students on summer experiential learning opportunities, interdisciplinary, participatory research and extension on food systems, range of opportunities for underrepresented students to be trained in workforce development experiences. How have the results been disseminated to communities of interest?We have disseminated the framework of the project to students and faculty through informal presentations. What do you plan to do during the next reporting period to accomplish the goals?We plan to convene two speaking opportunities on careers in the 21st-century digitized workforce. We also recruit and on-board students and hold PIs meeting. We also plan to disseminate information about our summer camps to attract high school at neighboring schools.
Impacts What was accomplished under these goals?
The project is collaborating across four main themes including 1) providing food and agricultural science students with technical depth knowledge in the fundamentals of data analytics and understanding the underlying principles and implementations of analytical methods; (2) supporting and preparing scholars for careers in the 21st-century digitized workforce; (3) integrating data science in workshops and summer camps to attract high school students to food and agriculture science programs and career opportunities within USDA and beyond; and (4) increasing enrollment, retention, and graduation rates in food and agricultural science degree programs infused with data science education at the participating institutions. We have started our recruitment efforts and hope to expand this opportunity. We have started the first year of the project. This summer, objective 3 will be launched.
Publications
|
|