Category: Conference Papers

Abstract: 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. Minirhizotron imagery is often composed of soil containing a few long and thin root objects of small diameter. The roots prove to be challenging for […]

Congratulations to our labmates and collaborators Keerthiraj Nagaraj, Nader Aljohani, Sheng Zou, Cody Ruben, Arturo Bretas, Alina Zare and Janise McNair!  Their paper, “State Estimator and Machine Learning Analysis of Residual Differences to Detect and Identify FDI and Parameter Errors in Smart Grids” , was recently accepted to the 2020 North American Power Symposium (NAPS). Check […]

Abstract: In the modern Smart Grid (SG), cyber-security is an increasingly important topic of research. An attacker can mislead the State Estimation (SE) process through a False Data Injection (FDI) on real-time measurement values or they can attack the parameters of the network that represent the system topology. While research has been done in SE […]

Abstract: Many machine learning classification systems lack competency awareness. Specifically, many systems lack the ability to identify when outliers (e.g., samples that are distinct from and not represented in the training data distribution) are being presented to the system. The ability to detect outliers is of practical significance since it can help the system behave […]

Congratulations to Gatorsense alumna, Xiaoxiao Du!  Her paper, titled “Multiple Instance Choquet Integral with Binary Fuzzy Measures for Remote Sensing Classifier Fusion with Imprecise Labels”, was recently accepted for publication with The 2019 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2019).  Xiaoxiao will present her work at the conference in Xiamen, China later this […]

Abstract: Classifier fusion methods integrate complementary information from multiple classifiers or detectors and can aid remote sensing applications such as target detection and hyperspectral image analysis. The Choquet integral (CI), parameterized by fuzzy measures (FMs), has been widely used in the literature as an effective non-linear fusion framework. Standard supervised CI fusion algorithms often require […]

Abstract: With the increasing popularity of using autonomous underwater vehicles (AUVs) to gather large quantities of Synthetic Aperture Sonar (SAS) seafloor imagery, the burden on human operators to identify targets in these seafloor images has increased significantly. Existing methods of automated target detection can have perfect or near-perfect accuracy, but often produce a high ratio […]

Abstract: In underwater synthetic aperture sonar (SAS) imagery, there is a need for accurate target recognition algorithms. Automated detection of underwater objects has many applications, not the least of which being the safe extraction of dangerous explosives. In this paper, we discuss experiments on a deep learning approach to binary classification of target and non-target […]

Abstract: Traditional methods of developing spectral libraries for unmixing hyperspectral images tend to require domain knowledge of the study area and the material’s spectra. In this paper, we propose using the Multiple Target Multiple Instance Adaptive Cosine/Coherence Estimator (Multi-Target MI-ACE) algorithm to develop spectral libraries that will capture the same spectral variability as traditional methods […]

Abstract: The increasing popularity of hyperspectral sensors is dramatically increasing the temporal availability of data. To date, algorithms struggle to compare hyperspectral data collected across dates due to different environmental conditions during collection. In this work, we develop a temporal mapping in order to map data collected from one year to a different year. We […]