Research

Below are the current projects being conducted by students.

A Hybrid YOLO Framework for Enhanced Detection of Small Trash Objects in Complex Trash Streams
Yan Pang
(Masters Thesis – Spring 2025 to Fall 2025)

I am developing and evaluating a novel hybrid YOLO object detection model, combining YOLOv8 and YOLOv11, designed to enhance the automated sorting of trash materials, particularly focusing on improving the detection accuracy of small waste objects within complex and varied waste streams.

Multi-Species Plant Disease Detection via Integrated Leaf and Lesion Segmentation with Deep Learning
Hangyu Yao
(Masters Project – Spring 2025 to Fall 2025)

his project proposes a robust and scalable deep learning framework for plant disease detection across multiple species. To address the challenges of background noise, overlapping symptoms, and limited datasets in real-world agricultural settings, the system integrates three main stages: leaf segmentation, disease lesion segmentation, and disease classification, with optional plant species identification.

DA3-BES+: A Multi-Agent Simulation with Population Dependent Behavioral Features
Caleb Sutton
(URCA Project – Fall 2023 to Spring 2024)

I am currently expanding upon the multi agent system bee simulation by Benjamin Wingerter to analyze variables that have a correlation to positive or negative outlooks on bee population, and will design experiments in order to analyze how bees react to various environmental struggles

Past Projects

  • Joseph Haenel, “Comprehensive Study of Deep Learning and Machine Learning Algorithms on Leaf Diseases in Sorghum and Maize“. URCA Project – Fall 2023 to Spring 2024.
  • Caleb Sutton, “DA3-BES+: A Multi-Agent Simulation with Population Dependent Behavioral Features. URCA Project – Fall 2023 to Spring 2024.