S. V. Krishna Jagadish

This paper uses deep learning models to detect sorghum panicles from aerial and lab images, improving yield prediction through machine learning regression.

The paper evaluates how normalization methods affect differential gene expression analysis in sorghum, showing that spike-in controls reveal biases in gene expression related to time of day and chilling stress.

The paper develops a fully automated method using Faster R-CNN to detect root anatomical features in cross-section images and estimates key measurements with high accuracy.

This paper introduces ExRANGES, a method that improves gene regulatory network inference by incorporating rates of transcriptional change, showing better performance in identifying known regulator-target relationships across multiple species.