-
Article
Open AccessSpatial and Texture Analysis of Root System distribution with Earth mover’s Distance (STARSEED)
Root system architectures are complex and challenging to characterize effectively for agronomic and ecological discovery.
-
Article
New approach for measuring interconnectivity of fission gas pores in nuclear fuels from 2D micrographs
In this work, we developed a simple and easily reproducible method to measure the interconnectivity of fission gas pore phases in irradiated nuclear fuels. The formation, growth and interconnection of fission ...
-
Article
Root identification in minirhizotron imagery with multiple instance learning
In this paper, multiple instance learning (MIL) algorithms to automatically perform root detection and segmentation in minirhizotron imagery using only image-level labels are proposed. Root and soil characteri...
-
Chapter and Conference Paper
Weakly Supervised Minirhizotron Image Segmentation with MIL-CAM
We present a multiple instance learning class activation map (MIL-CAM) approach for pixel-level minirhizotron image segmentation given weak image-level labels. Minirhizotrons are used to image plant roots in situ
-
Chapter
Addressing the Inevitable Imprecision: Multiple Instance Learning for Hyperspectral Image Analysis
In many remote sensing and hyperspectral image analysis applications, ground truth information is unavailable or impossible to obtain. Imprecision in ground truth often results from highly mixed or sub- spe...
-
Chapter and Conference Paper
Toward Resilient Smart Grid Communications Using Distributed SDN with ML-Based Anomaly Detection
Next generation “Smart” systems, including cyber-physical systems like smart grid and Internet-of-Things, integrate control, communication and computation to achieve stability, efficiency and robustness of phy...
-
Article
Measures of the Shapley index for learning lower complexity fuzzy integrals
The fuzzy integral (FI) is used frequently as a parametric nonlinear aggregation operator for data or information fusion. To date, numerous data-driven algorithms have been put forth to learn the FI for tasks ...