Canopy complexity and plant morphology determine detectability in multi-perspective drone imagery
Multi-perspective drone imagery (adding oblique views to top-down shots) raised crop classification accuracy from 35.73% to 52.93% across five species. The improvement scaled with canopy complexity, from +4.2% for simple rice to +38.1% for structurally complex sugarcane.
Read More...Comparative study on three machine learning models in novel autonomous drone-based detection of invasive plant Brassica nigra
Autonomous drone imaging combined with machine learning offers a promising approach for early detection of invasive species. In this study, students built an autonomous drone and compared three models: CNN, SGDC, and XGBoost, to identify Brassica nigra from aerial footage. Their results show that CNNs most effectively recognize key visual features, demonstrating strong potential for supporting conservation and invasive plant management.
Read More...Mapping equity in California K-12 school solar adoption using computer vision
The authors investigated adoption rates of solar photovoltaic power at K-12 schools in California.
Read More...Quantifying right atrial dilation relative to atrial septal defect size using an experimental model
To address the limitations in predicting the severity of Atrial Septal Defect (ASD), here the authors utilized a fluid-filled chamber model to quantify the relationship between defect size and right atrial fluid output. The findings confirmed that larger ASD diameters result in a linear increase in fluid output, validating a cost-effective model that can improve clinical prognosis and treatment planning for heart failure risks.
Read More...