Embedded Files
The TARGET VI Program (The Academy at Rutgers for Girls in Engineering and Technology) provides high school students with opportunities to explore engineering, technology, and scientific research through hands-on projects and mentorship. During Summer 2026, I will serve as a TARGET Graduate Mentor.
Project Title: Can Artificial Intelligence Help People Make Better Decisions?
The project introduces students to artificial intelligence (AI), machine learning, and data-driven decision making through real-world applications in healthcare, transportation, manufacturing, and sustainability. Students explored publicly available datasets, trained image-classification models, and learned how AI systems can support decision-making in practical settings.
Throughout the program, students progressed from learning the fundamentals of AI and machine learning to building models using Google Teachable Machine, exploring neural networks through TensorFlow Playground, and working with Python in Google Colab. The project emphasized both conceptual understanding and hands-on experimentation, allowing students to connect computational ideas with real-world applications.
The program concluded with a symposium presentation in which students presented their AI application ideas, demonstrated their models, and discussed the opportunities and limitations of artificial intelligence in decision-making.
Topics Covered: Artificial Intelligence, Machine Learning, Data-Driven Decision Making, Image Classification, Neural Networks, Python, Google Colab, TensorFlow Playground, and Scientific Communication.
Aresty Research Assistant Program provides undergraduate students with research opportunities mentored by faculty and Ph.D. students, culminating in presentations at the Aresty Research Symposium, one of the largest undergraduate research celebrations in the country. I work with Aresty advisees in the Mathematical Optimization Research Group (MathOptRG) led by my advisor, Dr. Farzad Yousefian. The advisees also present their works at the Department of Industrial and Systems Engineering’s annual Research Day.
In the MathOptRG, I prepare and deliver lecture notes to introduce key concepts and help advisees get ready for their research projects, focusing on Python libraries and algorithm implementation over data, such as Stochastic Gradient Descent (SGD). Example lecture notes include Note 1: NumPy and Binary Classification and Note 2: NumPy, Pandas, and Multiclass Classification. I participate in weekly group meetings to discuss progress, challenges, and next steps. I also meet one-on-one with my advisee to clarify project goals, prepare heterogeneous data, explain algorithm convergence theory, and implement federated learning algorithms. Additionally, I support my advisee in presenting research at the Aresty Research Symposium and the Department of Industrial and Systems Engineering’s annual Research Day, including poster preparation and presentation.
Advisees List:
Hong Si Wu
Undergraduate, Computer Science and Data Science Major, Rutgers University
Advising Period: Fall 2025–Spring 2026
Project: Federated Hyperparameter Learning on Heterogeneous Datasets with Sparsity Considerations
Navya Joshi
Undergraduate, Computer Science Major at Rutgers
Advising Period: Fall 2024 – Spring 2025
Project: Regularized FedProx (R-FedProx): Addressing Heterogeneity and Inducing Sparse Local Solutions in Federated Learning
Poster Link: View
Presented at:
– Research Day Poster Session, Department of Industrial and Systems Engineering, Rutgers, The State University of New Jersey
– Aresty Research Symposium, Rutgers, The State University of New Jersey
Edison Wang
Undergraduate, Computer Science Major at Rutgers
Advising Period: Fall 2023–Spring 2024
Project: Numerical Analysis of a Federated Learning Method for Heterogeneous Datasets
Poster Link: View
Presented at:
– Research Day Poster Session, Department of Industrial and Systems Engineering, Rutgers, The State University of New Jersey
– Aresty Research Symposium, Rutgers, The State University of New Jersey
Page updated
Report abuse